1
0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-18 06:57:24 +08:00

Merge branch 'master' of https://github.com/rg3/youtube-dl into multipart_videos

Conflicts:
	youtube_dl/YoutubeDL.py
	youtube_dl/__init__.py
	youtube_dl/extractor/common.py
	youtube_dl/extractor/mtv.py
	youtube_dl/extractor/tudou.py
	youtube_dl/postprocessor/__init__.py
	youtube_dl/postprocessor/ffmpeg.py
This commit is contained in:
Mark Lee 2015-02-20 21:50:44 -08:00
commit b01fa6bdbc
353 changed files with 14435 additions and 3702 deletions

2
.gitignore vendored
View File

@ -31,3 +31,5 @@ updates_key.pem
test/testdata
.tox
youtube-dl.zsh
.idea
.idea/*

View File

@ -4,12 +4,14 @@ python:
- "2.7"
- "3.3"
- "3.4"
before_install:
- sudo apt-get update -qq
- sudo apt-get install -yqq rtmpdump
script: nosetests test --verbose
notifications:
email:
- filippo.valsorda@gmail.com
- phihag@phihag.de
- jaime.marquinez.ferrandiz+travis@gmail.com
- yasoob.khld@gmail.com
# irc:
# channels:

23
AUTHORS
View File

@ -88,3 +88,26 @@ Dao Hoang Son
Oskar Jauch
Matthew Rayfield
t0mm0
Tithen-Firion
Zack Fernandes
cryptonaut
Adrian Kretz
Mathias Rav
Petr Kutalek
Will Glynn
Max Reimann
Cédric Luthi
Thijs Vermeir
Joel Leclerc
Christopher Krooss
Ondřej Caletka
Dinesh S
Johan K. Jensen
Yen Chi Hsuan
Enam Mijbah Noor
David Luhmer
Shaya Goldberg
Paul Hartmann
Frans de Jonge
Robin de Rooij
Ryan Schmidt

138
CONTRIBUTING.md Normal file
View File

@ -0,0 +1,138 @@
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
### Is the description of the issue itself sufficient?
We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts.
So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious
- What the problem is
- How it could be fixed
- How your proposed solution would look like
If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
### Are you using the latest version?
Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
### Is the issue already documented?
Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
### Why are existing options not enough?
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
### Is there enough context in your bug report?
People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one).
We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful.
### Does the issue involve one problem, and one problem only?
Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
### Is anyone going to need the feature?
Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
### Is your question about youtube-dl?
It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
# DEVELOPER INSTRUCTIONS
Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
To run youtube-dl as a developer, you don't need to build anything either. Simply execute
python -m youtube_dl
To run the test, simply invoke your favorite test runner, or execute a test file directly; any of the following work:
python -m unittest discover
python test/test_download.py
nosetests
If you want to create a build of youtube-dl yourself, you'll need
* python
* make
* pandoc
* zip
* nosetests
### Adding support for a new site
If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
```python
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class YourExtractorIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://yourextractor.com/watch/42',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': {
'id': '42',
'ext': 'mp4',
'title': 'Video title goes here',
'thumbnail': 're:^https?://.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py
$ git add youtube_dl/extractor/yourextractor.py
$ git commit -m '[yourextractor] Add new extractor'
$ git push origin yourextractor
10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
In any case, thank you very much for your contributions!

View File

@ -1,10 +1,7 @@
all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean:
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part
cleanall: clean
rm -f youtube-dl youtube-dl.exe
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
PREFIX ?= /usr/local
BINDIR ?= $(PREFIX)/bin
@ -35,13 +32,22 @@ install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtu
install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions
install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish
codetest:
flake8 .
test:
#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
nosetests --verbose test
$(MAKE) codetest
ot: offlinetest
offlinetest: codetest
nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations --exclude test_youtube_lists
tar: youtube-dl.tar.gz
.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion
.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites
pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
@ -54,7 +60,13 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
chmod a+x youtube-dl
README.md: youtube_dl/*.py youtube_dl/*/*.py
COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py
COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
CONTRIBUTING.md: README.md
python devscripts/make_contributing.py README.md CONTRIBUTING.md
supportedsites:
python devscripts/make_supportedsites.py docs/supportedsites.md
README.txt: README.md
pandoc -f markdown -t plain README.md -o README.txt

253
README.md
View File

@ -1,7 +1,15 @@
youtube-dl - download videos from youtube.com or other video platforms
# SYNOPSIS
**youtube-dl** [OPTIONS] URL [URL...]
- [INSTALLATION](#installation)
- [DESCRIPTION](#description)
- [OPTIONS](#options)
- [CONFIGURATION](#configuration)
- [OUTPUT TEMPLATE](#output-template)
- [VIDEO SELECTION](#video-selection)
- [FAQ](#faq)
- [DEVELOPER INSTRUCTIONS](#developer-instructions)
- [BUGS](#bugs)
- [COPYRIGHT](#copyright)
# INSTALLATION
@ -34,6 +42,8 @@ YouTube.com and a few more sites. It requires the Python interpreter, version
your Unix box, on Windows or on Mac OS X. It is released to the public domain,
which means you can modify it, redistribute it or use it however you like.
youtube-dl [OPTIONS] URL [URL...]
# OPTIONS
-h, --help print this help text and exit
--version print program version and exit
@ -50,10 +60,6 @@ which means you can modify it, redistribute it or use it however you like.
they would handle
--extractor-descriptions Output descriptions of all supported
extractors
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in
an empty string (--proxy "") for direct
connection
--socket-timeout None Time to wait before giving up, in seconds
--default-search PREFIX Use this prefix for unqualified URLs. For
example "gvsearch2:" downloads two videos
from google videos for youtube-dl "large
@ -65,16 +71,37 @@ which means you can modify it, redistribute it or use it however you like.
this is not possible instead of searching.
--ignore-config Do not read configuration files. When given
in the global configuration file /etc
/youtube-dl.conf: do not read the user
configuration in ~/.config/youtube-dl.conf
(%APPDATA%/youtube-dl/config.txt on
Windows)
/youtube-dl.conf: Do not read the user
configuration in ~/.config/youtube-
dl/config (%APPDATA%/youtube-dl/config.txt
on Windows)
--flat-playlist Do not extract the videos of a playlist,
only list them.
--no-color Do not emit color codes in output.
## Network Options:
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in
an empty string (--proxy "") for direct
connection
--socket-timeout SECONDS Time to wait before giving up, in seconds
--source-address IP Client-side IP address to bind to
(experimental)
-4, --force-ipv4 Make all connections via IPv4
(experimental)
-6, --force-ipv6 Make all connections via IPv6
(experimental)
## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
--playlist-items ITEM_SPEC playlist video items to download. Specify
indices of the videos in the playlist
seperated by commas like: "--playlist-items
1,2,5,8" if you want to download videos
indexed 1, 2, 5, 8 in the playlist. You can
specify range: "--playlist-items
1-3,7,10-13", it will download the videos
at index 1, 2, 3, 7, 10, 11, 12 and 13.
--match-title REGEX download only matching titles (regex or
caseless sub-string)
--reject-title REGEX skip download for matching titles (regex or
@ -93,6 +120,23 @@ which means you can modify it, redistribute it or use it however you like.
COUNT views
--max-views COUNT Do not download any videos with more than
COUNT views
--match-filter FILTER (Experimental) Generic video filter.
Specify any key (see help for -o for a list
of available keys) to match if the key is
present, !key to check if the key is not
present,key > NUMBER (like "comment_count >
12", also works with >=, <, <=, !=, =) to
compare against a number, and & to require
multiple matches. Values which are not
known are excluded unless you put a
question mark (?) after the operator.For
example, to only match videos that have
been liked more than 100 times and disliked
less than 50 times (or the dislike
functionality is not available at the given
service), but who also have a description,
use --match-filter "like_count > 100 &
dislike_count <? 50 & description" .
--no-playlist If the URL refers to a video and a
playlist, download only the video.
--age-limit YEARS download only videos suitable for the given
@ -106,19 +150,27 @@ which means you can modify it, redistribute it or use it however you like.
## Download Options:
-r, --rate-limit LIMIT maximum download rate in bytes per second
(e.g. 50K or 4.2M)
-R, --retries RETRIES number of retries (default is 10)
-R, --retries RETRIES number of retries (default is 10), or
"infinite".
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer do not automatically adjust the buffer
size. By default, the buffer size is
automatically resized from an initial value
of SIZE.
--playlist-reverse Download playlist videos in reverse order
--xattr-set-filesize (experimental) set file xattribute
ytdl.filesize with expected filesize
--hls-prefer-native (experimental) Use the native HLS
downloader instead of ffmpeg.
--external-downloader COMMAND (experimental) Use the specified external
downloader. Currently supports
aria2c,curl,wget
## Filesystem Options:
-a, --batch-file FILE file containing URLs to download ('-' for
stdin)
--id use only video ID in file name
-A, --auto-number number downloaded files starting from 00000
-o, --output TEMPLATE output filename template. Use %(title)s to
get the title, %(uploader)s for the
uploader name, %(uploader_id)s for the
@ -152,6 +204,9 @@ which means you can modify it, redistribute it or use it however you like.
--restrict-filenames Restrict filenames to only ASCII
characters, and avoid "&" and spaces in
filenames
-A, --auto-number [deprecated; use -o
"%(autonumber)s-%(title)s.%(ext)s" ] number
downloaded files starting from 00000
-t, --title [deprecated] use title in file name
(default)
-l, --literal [deprecated] alias of --title
@ -170,7 +225,6 @@ which means you can modify it, redistribute it or use it however you like.
--write-info-json write video metadata to a .info.json file
--write-annotations write video annotations to a .annotation
file
--write-thumbnail write thumbnail image to disk
--load-info FILE json file containing the video information
(created with the "--write-json" option)
--cookies FILE file to read cookies from and dump cookie
@ -185,6 +239,12 @@ which means you can modify it, redistribute it or use it however you like.
--no-cache-dir Disable filesystem caching
--rm-cache-dir Delete all filesystem cache files
## Thumbnail images:
--write-thumbnail write thumbnail image to disk
--write-all-thumbnails write all thumbnail image formats to disk
--list-thumbnails Simulate and list all available thumbnail
formats
## Verbosity / Simulation Options:
-q, --quiet activates quiet mode
--no-warnings Ignore warnings
@ -206,6 +266,8 @@ which means you can modify it, redistribute it or use it however you like.
for each command-line argument. If the URL
refers to a playlist, dump the whole
playlist information in a single line.
--print-json Be quiet and print the video information as
JSON (video is still being downloaded).
--newline output progress bar as new lines
--no-progress do not print progress bar
--console-title display progress in console titlebar
@ -216,6 +278,10 @@ which means you can modify it, redistribute it or use it however you like.
files in the current directory to debug
problems
--print-traffic Display sent and read HTTP traffic
-C, --call-home Contact the youtube-dl server for
debugging.
--no-call-home Do NOT contact the youtube-dl server for
debugging.
## Workarounds:
--encoding ENCODING Force the specified encoding (experimental)
@ -232,17 +298,34 @@ which means you can modify it, redistribute it or use it however you like.
--bidi-workaround Work around terminals that lack
bidirectional text support. Requires bidiv
or fribidi executable in PATH
--sleep-interval SECONDS Number of seconds to sleep before each
download.
## Video Format Options:
-f, --format FORMAT video format code, specify the order of
preference using slashes: -f 22/17/18 . -f
mp4 , -f m4a and -f flv are also
supported. You can also use the special
names "best", "bestvideo", "bestaudio",
"worst", "worstvideo" and "worstaudio". By
default, youtube-dl will pick the best
quality. Use commas to download multiple
audio formats, such as -f
preference using slashes, as in -f 22/17/18
. Instead of format codes, you can select
by extension for the extensions aac, m4a,
mp3, mp4, ogg, wav, webm. You can also use
the special names "best", "bestvideo",
"bestaudio", "worst". You can filter the
video results by putting a condition in
brackets, as in -f "best[height=720]" (or
-f "[filesize>10M]"). This works for
filesize, height, width, tbr, abr, vbr,
asr, and fps and the comparisons <, <=, >,
>=, =, != and for ext, acodec, vcodec,
container, and protocol and the comparisons
=, != . Formats for which the value is not
known are excluded unless you put a
question mark (?) after the operator. You
can combine format filters, so -f "[height
<=? 720][tbr>500]" selects up to 720p
videos (or videos where the height is not
known) with a bitrate of at least 500
KBit/s. By default, youtube-dl will pick
the best quality. Use commas to download
multiple audio formats, such as -f
136/137/mp4/bestvideo,140/m4a/bestaudio.
You can merge the video and audio of two
formats into a single file using -f <video-
@ -256,6 +339,10 @@ which means you can modify it, redistribute it or use it however you like.
-F, --list-formats list all available formats
--youtube-skip-dash-manifest Do not download the DASH manifest on
YouTube videos
--merge-output-format FORMAT If a merge is required (e.g.
bestvideo+bestaudio), output to given
container format. One of mkv, mp4, ogg,
webm, flv.Ignored if no merge is required
## Subtitle Options:
--write-sub write subtitle file
@ -272,7 +359,8 @@ which means you can modify it, redistribute it or use it however you like.
## Authentication Options:
-u, --username USERNAME login with this account ID
-p, --password PASSWORD account password
-p, --password PASSWORD account password. If this option is left
out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR two-factor auth code
-n, --netrc use .netrc authentication data
--video-password PASSWORD video password (vimeo, smotri)
@ -302,10 +390,18 @@ which means you can modify it, redistribute it or use it however you like.
--add-metadata write metadata to the video file
--xattrs write metadata to the video file's xattrs
(using dublin core and xdg standards)
--fixup POLICY Automatically correct known faults of the
file. One of never (do nothing), warn (only
emit a warning), detect_or_warn(the
default; fix file if we can, warn
otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the
postprocessors (default)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
postprocessors
--ffmpeg-location PATH Location of the ffmpeg/avconv binary;
either the path to the binary or its
containing directory.
--exec CMD Execute a command on the file after
downloading, similar to find's -exec
syntax. Example: --exec 'adb push {}
@ -313,7 +409,7 @@ which means you can modify it, redistribute it or use it however you like.
# CONFIGURATION
You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
# OUTPUT TEMPLATE
@ -407,17 +503,27 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
### The links provided by youtube-dl -g are not working anymore
### I extracted a video URL with -g, but it does not play on another machine / in my webbrowser.
The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well.
If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn.
### ERROR: no fmt_url_map or conn information found in video info
youtube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`.
YouTube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
### ERROR: unable to download video ###
youtube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`.
YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
### ExtractorError: Could not find JS function u'OF'
In February 2015, the new YouTube player contained a character sequence in a string that was misinterpreted by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
### SyntaxError: Non-ASCII character ###
@ -436,6 +542,41 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
If you put youtube-dl and ffmpeg in the same directory that you're running the command from, it will work, but that's rather cumbersome.
To make a different directory work - either for ffmpeg, or for youtube-dl, or for both - simply create the directory (say, `C:\bin`, or `C:\Users\<User name>\bin`), put all the executables directly in there, and then [set your PATH environment variable](https://www.java.com/en/download/help/path.xml) to include that directory.
From then on, after restarting your shell, you will be able to access both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) by simply typing `youtube-dl` or `ffmpeg`, no matter what directory you're in.
### How do I put downloads into a specific folder?
Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
### How do I download a video starting with a `-` ?
Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
youtube-dl -- -wNyEUrxzFU
youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
### Can you add support for this anime video site, or site which shows current movies for free?
As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
A note on the service that they don't host the infringing content, but just link to those who do, is evidence that the service should **not** be included into youtube-dl. The same goes for any DMCA note when the whole front page of the service is filled with videos they are not allowed to distribute. A "fair use" note is equally unconvincing if the service shows copyright-protected videos in full without authorization.
Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
### How can I detect whether a given URL is supported by youtube-dl?
For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/video/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program.
# DEVELOPER INSTRUCTIONS
Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
@ -508,7 +649,7 @@ If you want to add support for a new site, you can follow this quick list (assum
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py
@ -526,23 +667,61 @@ youtube-dl makes the best effort to be a good command-line program, and thus sho
From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
import youtube_dl
```python
import youtube_dl
ydl_opts = {}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
ydl_opts = {}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
```
Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
```python
import youtube_dl
class MyLogger(object):
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
print(msg)
def my_hook(d):
if d['status'] == 'finished':
print('Done downloading, now converting ...')
ydl_opts = {
'format': 'bestaudio/best',
'postprocessors': [{
'key': 'FFmpegExtractAudio',
'preferredcodec': 'mp3',
'preferredquality': '192',
}],
'logger': MyLogger(),
'progress_hooks': [my_hook],
}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
```
# BUGS
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email.
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode.
Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
**Please include the full output of youtube-dl when run with `-v`**.
For discussions, join us in the irc channel #youtube-dl on freenode.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist):
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
### Is the description of the issue itself sufficient?
@ -586,7 +765,7 @@ In particular, every site support request issue should only pertain to services
### Is anyone going to need the feature?
Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
### Is your question about youtube-dl?

View File

@ -16,7 +16,7 @@ def main():
template = tmplf.read()
ie_htmls = []
for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()):
for ie in youtube_dl.list_extractors(age_limit=None):
ie_html = '<b>{}</b>'.format(ie.IE_NAME)
ie_desc = getattr(ie, 'IE_DESC', None)
if ie_desc is False:

32
devscripts/make_contributing.py Executable file
View File

@ -0,0 +1,32 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import io
import optparse
import re
def main():
parser = optparse.OptionParser(usage='%prog INFILE OUTFILE')
options, args = parser.parse_args()
if len(args) != 2:
parser.error('Expected an input and an output filename')
infile, outfile = args
with io.open(infile, encoding='utf-8') as inf:
readme = inf.read()
bug_text = re.search(
r'(?s)#\s*BUGS\s*[^\n]*\s*(.*?)#\s*COPYRIGHT', readme).group(1)
dev_text = re.search(
r'(?s)(#\s*DEVELOPER INSTRUCTIONS.*?)#\s*EMBEDDING YOUTUBE-DL',
readme).group(1)
out = bug_text + dev_text
with io.open(outfile, 'w', encoding='utf-8') as outf:
outf.write(out)
if __name__ == '__main__':
main()

View File

@ -0,0 +1,45 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import io
import optparse
import os
import sys
# Import youtube_dl
ROOT_DIR = os.path.join(os.path.dirname(__file__), '..')
sys.path.append(ROOT_DIR)
import youtube_dl
def main():
parser = optparse.OptionParser(usage='%prog OUTFILE.md')
options, args = parser.parse_args()
if len(args) != 1:
parser.error('Expected an output filename')
outfile, = args
def gen_ies_md(ies):
for ie in ies:
ie_md = '**{0}**'.format(ie.IE_NAME)
ie_desc = getattr(ie, 'IE_DESC', None)
if ie_desc is False:
continue
if ie_desc is not None:
ie_md += ': {0}'.format(ie.IE_DESC)
if not ie.working():
ie_md += ' (Currently broken)'
yield ie_md
ies = sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower())
out = '# Supported sites\n' + ''.join(
' - ' + md + '\n'
for md in gen_ies_md(ies))
with io.open(outfile, 'w', encoding='utf-8') as outf:
outf.write(out)
if __name__ == '__main__':
main()

View File

@ -11,8 +11,19 @@ README_FILE = os.path.join(ROOT_DIR, 'README.md')
with io.open(README_FILE, encoding='utf-8') as f:
readme = f.read()
PREFIX = '%YOUTUBE-DL(1)\n\n# NAME\n'
readme = re.sub(r'(?s)# INSTALLATION.*?(?=# DESCRIPTION)', '', readme)
PREFIX = '''%YOUTUBE-DL(1)
# NAME
youtube\-dl \- download videos from youtube.com or other video platforms
# SYNOPSIS
**youtube-dl** \[OPTIONS\] URL [URL...]
'''
readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
readme = PREFIX + readme
if sys.version_info < (3, 0):

View File

@ -35,7 +35,7 @@ if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $us
if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
/bin/echo -e "\n### First of all, testing..."
make cleanall
make clean
if $skip_tests ; then
echo 'SKIPPING TESTS'
else
@ -45,9 +45,9 @@ fi
/bin/echo -e "\n### Changing version in version.py..."
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
make README.md
git add README.md youtube_dl/version.py
/bin/echo -e "\n### Committing documentation and youtube_dl/version.py..."
make README.md CONTRIBUTING.md supportedsites
git add README.md CONTRIBUTING.md docs/supportedsites.md youtube_dl/version.py
git commit -m "release $version"
/bin/echo -e "\n### Now tagging, signing and pushing..."

565
docs/supportedsites.md Normal file
View File

@ -0,0 +1,565 @@
# Supported sites
- **1tv**: Первый канал
- **1up.com**
- **220.ro**
- **24video**
- **3sat**
- **4tube**
- **56.com**
- **5min**
- **8tracks**
- **9gag**
- **abc.net.au**
- **Abc7News**
- **AcademicEarth:Course**
- **AddAnime**
- **AdobeTV**
- **AdultSwim**
- **Aftenposten**
- **Aftonbladet**
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
- **anitube.se**
- **AnySex**
- **Aparat**
- **AppleDailyAnimationNews**
- **AppleDailyRealtimeNews**
- **AppleTrailers**
- **archive.org**: archive.org videos
- **ARD**
- **ARD:mediathek**
- **arte.tv**
- **arte.tv:+7**
- **arte.tv:concert**
- **arte.tv:creative**
- **arte.tv:ddc**
- **arte.tv:embed**
- **arte.tv:future**
- **AtresPlayer**
- **ATTTechChannel**
- **audiomack**
- **audiomack:album**
- **Azubu**
- **bambuser**
- **bambuser:channel**
- **Bandcamp**
- **Bandcamp:album**
- **bbc.co.uk**: BBC iPlayer
- **Beeg**
- **BehindKink**
- **Bet**
- **Bild**: Bild.de
- **BiliBili**
- **blinkx**
- **blip.tv:user**
- **BlipTV**
- **Bloomberg**
- **Bpb**: Bundeszentrale für politische Bildung
- **BR**: Bayerischer Rundfunk Mediathek
- **Break**
- **Brightcove**
- **BuzzFeed**
- **BYUtv**
- **Camdemy**
- **CamdemyFolder**
- **Canal13cl**
- **canalc2.tv**
- **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
- **CBS**
- **CBSNews**: CBS News
- **CBSSports**
- **CeskaTelevize**
- **channel9**: Channel 9
- **Chilloutzone**
- **Cinchcast**
- **Cinemassacre**
- **clipfish**
- **cliphunter**
- **Clipsyndicate**
- **Cloudy**
- **Clubic**
- **cmt.com**
- **CNET**
- **CNN**
- **CNNArticle**
- **CNNBlogs**
- **CollegeHumor**
- **CollegeRama**
- **ComCarCoff**
- **ComedyCentral**
- **ComedyCentralShows**: The Daily Show / The Colbert Report
- **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
- **Cracked**
- **Criterion**
- **Crunchyroll**
- **crunchyroll:playlist**
- **CSpan**: C-SPAN
- **CtsNews**
- **culturebox.francetvinfo.fr**
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
- **daum.net**
- **DBTV**
- **DctpTv**
- **DeezerPlaylist**
- **defense.gouv.fr**
- **Discovery**
- **divxstage**: DivxStage
- **Dotsub**
- **DRBonanza**
- **Dropbox**
- **DrTuber**
- **DRTV**
- **Dump**
- **dvtv**: http://video.aktualne.cz/
- **EbaumsWorld**
- **EchoMsk**
- **eHow**
- **Einthusan**
- **eitb.tv**
- **EllenTV**
- **EllenTV:clips**
- **ElPais**: El País
- **Embedly**
- **EMPFlix**
- **Engadget**
- **Eporner**
- **EroProfile**
- **Escapist**
- **EveryonesMixtape**
- **exfm**: ex.fm
- **ExpoTV**
- **ExtremeTube**
- **facebook**
- **faz.net**
- **fc2**
- **fernsehkritik.tv**
- **fernsehkritik.tv:postecke**
- **Firedrive**
- **Firstpost**
- **Flickr**
- **Folketinget**: Folketinget (ft.dk; Danish parliament)
- **Foxgay**
- **FoxNews**
- **france2.fr:generation-quoi**
- **FranceCulture**
- **FranceInter**
- **francetv**: France 2, 3, 4, 5 and Ô
- **francetvinfo.fr**
- **Freesound**
- **freespeech.org**
- **FreeVideo**
- **FunnyOrDie**
- **Gamekings**
- **GameOne**
- **gameone:playlist**
- **GameSpot**
- **GameStar**
- **Gametrailers**
- **GDCVault**
- **generic**: Generic downloader that works on some sites
- **GiantBomb**
- **Giga**
- **Glide**: Glide mobile video messages (glide.me)
- **Globo**
- **GodTube**
- **GoldenMoustache**
- **Golem**
- **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in
- **Goshgay**
- **Grooveshark**
- **Groupon**
- **Hark**
- **HearThisAt**
- **Heise**
- **HellPorno**
- **Helsinki**: helsinki.fi
- **HentaiStigma**
- **HistoricFilms**
- **History**
- **hitbox**
- **hitbox:live**
- **HornBunny**
- **HostingBulk**
- **HotNewHipHop**
- **Howcast**
- **HowStuffWorks**
- **HuffPost**: Huffington Post
- **Hypem**
- **Iconosquare**
- **ign.com**
- **imdb**: Internet Movie Database trailers
- **imdb:list**: Internet Movie Database lists
- **Imgur**
- **Ina**
- **InfoQ**
- **Instagram**
- **instagram:user**: Instagram user profile
- **InternetVideoArchive**
- **IPrima**
- **ivi**: ivi.ru
- **ivi:compilation**: ivi.ru compilations
- **Izlesene**
- **JadoreCettePub**
- **JeuxVideo**
- **Jove**
- **jpopsuki.tv**
- **Jukebox**
- **Kankan**
- **Karaoketv**
- **keek**
- **KeezMovies**
- **KhanAcademy**
- **KickStarter**
- **kontrtube**: KontrTube.ru - Труба зовёт
- **KrasView**: Красвью
- **Ku6**
- **la7.tv**
- **Laola1Tv**
- **lifenews**: LIFE | NEWS
- **LiveLeak**
- **livestream**
- **livestream:original**
- **LnkGo**
- **lrt.lt**
- **lynda**: lynda.com videos
- **lynda:course**: lynda.com online courses
- **m6**
- **macgamestore**: MacGameStore trailers
- **mailru**: Видео@Mail.Ru
- **Malemotion**
- **MDR**
- **media.ccc.de**
- **metacafe**
- **Metacritic**
- **Mgoon**
- **Minhateca**
- **MinistryGrid**
- **mitele.es**
- **mixcloud**
- **MLB**
- **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
- **Mofosex**
- **Mojvideo**
- **Moniker**: allmyvideos.net and vidspot.net
- **mooshare**: Mooshare.biz
- **Morningstar**: morningstar.com
- **Motherless**
- **Motorsport**: motorsport.com
- **MovieClips**
- **Moviezine**
- **movshare**: MovShare
- **MPORA**
- **MTV**
- **mtviggy.com**
- **mtvservices:embedded**
- **MuenchenTV**: münchen.tv
- **MusicPlayOn**
- **MusicVault**
- **muzu.tv**
- **MySpace**
- **MySpace:album**
- **MySpass**
- **myvideo**
- **MyVidster**
- **n-tv.de**
- **NationalGeographic**
- **Naver**
- **NBA**
- **NBC**
- **NBCNews**
- **ndr**: NDR.de - Mediathek
- **NDTV**
- **NerdCubedFeed**
- **Nerdist**
- **Netzkino**
- **Newgrounds**
- **Newstube**
- **NextMedia**
- **NextMediaActionNews**
- **nfb**: National Film Board of Canada
- **nfl.com**
- **nhl.com**
- **nhl.com:news**: NHL news
- **nhl.com:videocenter**: NHL videocenter category
- **niconico**: ニコニコ動画
- **NiconicoPlaylist**
- **Noco**
- **Normalboots**
- **NosVideo**
- **novamov**: NovaMov
- **Nowness**
- **nowvideo**: NowVideo
- **npo.nl**
- **npo.nl:live**
- **npo.nl:radio**
- **npo.nl:radio:fragment**
- **NRK**
- **NRKTV**
- **ntv.ru**
- **Nuvid**
- **NYTimes**
- **ocw.mit.edu**
- **OktoberfestTV**
- **on.aol.com**
- **Ooyala**
- **OpenFilm**
- **orf:fm4**: radio FM4
- **orf:oe1**: Radio Österreich 1
- **orf:tvthek**: ORF TVthek
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
- **PBS**
- **Phoenix**
- **Photobucket**
- **PlanetaPlay**
- **play.fm**
- **played.to**
- **Playvid**
- **plus.google**: Google Plus
- **pluzz.francetv.fr**
- **podomatic**
- **PornHd**
- **PornHub**
- **PornHubPlaylist**
- **Pornotube**
- **PornoXO**
- **PromptFile**
- **prosiebensat1**: ProSiebenSat.1 Digital
- **Pyvideo**
- **QuickVid**
- **radio.de**
- **radiobremen**
- **radiofrance**
- **Rai**
- **RBMARadio**
- **RedTube**
- **Restudy**
- **ReverbNation**
- **RingTV**
- **RottenTomatoes**
- **Roxwel**
- **RTBF**
- **Rte**
- **rtl.nl**: rtl.nl and rtlxl.nl
- **RTL2**
- **RTLnow**
- **RTP**
- **RTS**: RTS.ch
- **rtve.es:alacarta**: RTVE a la carta
- **rtve.es:live**: RTVE.es live streams
- **RUHD**
- **rutube**: Rutube videos
- **rutube:channel**: Rutube channels
- **rutube:embed**: Rutube embedded videos
- **rutube:movie**: Rutube movies
- **rutube:person**: Rutube person videos
- **RUTV**: RUTV.RU
- **Sandia**: Sandia National Laboratories
- **Sapo**: SAPO Vídeos
- **savefrom.net**
- **SBS**: sbs.com.au
- **SciVee**
- **screen.yahoo:search**: Yahoo screen search
- **Screencast**
- **ScreencastOMatic**
- **ScreenwaveMedia**
- **ServingSys**
- **Sexu**
- **SexyKarma**: Sexy Karma and Watch Indian Porn
- **Shared**
- **ShareSix**
- **Sina**
- **Slideshare**
- **Slutload**
- **smotri**: Smotri.com
- **smotri:broadcast**: Smotri.com broadcasts
- **smotri:community**: Smotri.com community videos
- **smotri:user**: Smotri.com user videos
- **Snotr**
- **Sockshare**
- **Sohu**
- **soundcloud**
- **soundcloud:playlist**
- **soundcloud:set**
- **soundcloud:user**
- **Soundgasm**
- **southpark.cc.com**
- **southpark.de**
- **Space**
- **Spankwire**
- **Spiegel**
- **Spiegel:Article**: Articles on spiegel.de
- **Spiegeltv**
- **Spike**
- **Sport5**
- **SportBox**
- **SportDeutschland**
- **SRMediathek**: Saarländischer Rundfunk
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
- **SunPorno**
- **SVTPlay**
- **SWRMediathek**
- **Syfy**
- **SztvHu**
- **Tagesschau**
- **Tapely**
- **Tass**
- **teachertube**: teachertube.com videos
- **teachertube:user:collection**: teachertube.com user and collection videos
- **TeachingChannel**
- **Teamcoco**
- **TeamFour**
- **TechTalks**
- **techtv.mit.edu**
- **TED**
- **tegenlicht.vpro.nl**
- **TeleBruxelles**
- **telecinco.es**
- **TeleMB**
- **TeleTask**
- **TenPlay**
- **TestTube**
- **TF1**
- **TheOnion**
- **ThePlatform**
- **TheSixtyOne**
- **ThisAV**
- **THVideo**
- **THVideoPlaylist**
- **tinypic**: tinypic.com videos
- **tlc.com**
- **tlc.de**
- **TMZ**
- **TNAFlix**
- **tou.tv**
- **Toypics**: Toypics user profile
- **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken)
- **Trilulilu**
- **TruTube**
- **Tube8**
- **Tudou**
- **Tumblr**
- **TuneIn**
- **Turbo**
- **Tutv**
- **tv.dfb.de**
- **TV4**: tv4.se and tv4play.se
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvp.pl**
- **tvp.pl:Series**
- **TVPlay**: TV3Play and related services
- **Tweakers**
- **twitch:bookmarks**
- **twitch:chapter**
- **twitch:past_broadcasts**
- **twitch:profile**
- **twitch:stream**
- **twitch:video**
- **twitch:vod**
- **Ubu**
- **udemy**
- **udemy:course**
- **Unistra**
- **Urort**: NRK P3 Urørt
- **ustream**
- **ustream:channel**
- **Vbox7**
- **VeeHD**
- **Veoh**
- **Vesti**: Вести.Ru
- **Vevo**
- **VGTV**
- **vh1.com**
- **Vice**
- **Viddler**
- **video.google:search**: Google Video search
- **video.mit.edu**
- **VideoBam**
- **VideoDetective**
- **videofy.me**
- **videolectures.net**
- **VideoMega**
- **VideoPremium**
- **VideoTt**: video.tt - Your True Tube
- **videoweed**: VideoWeed
- **Vidme**
- **Vidzi**
- **vier**
- **vier:videos**
- **viki**
- **vimeo**
- **vimeo:album**
- **vimeo:channel**
- **vimeo:group**
- **vimeo:likes**: Vimeo user likes
- **vimeo:review**: Review pages on vimeo
- **vimeo:user**
- **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
- **Vimple**: Vimple.ru
- **Vine**
- **vine:user**
- **vk.com**
- **vk.com:user-videos**: vk.com:All of a user's videos
- **Vodlocker**
- **Vporn**
- **VRT**
- **vube**: Vube.com
- **VuClip**
- **vulture.com**
- **Walla**
- **WashingtonPost**
- **wat.tv**
- **WayOfTheMaster**
- **WDR**
- **wdr:mobile**
- **WDRMaus**: Sendung mit der Maus
- **WebOfStories**
- **Weibo**
- **Wimp**
- **Wistia**
- **WorldStarHipHop**
- **wrzuta.pl**
- **WSJ**: Wall Street Journal
- **XBef**
- **XboxClips**
- **XHamster**
- **XMinus**
- **XNXX**
- **XTube**
- **XTubeUser**: XTube user profile
- **Xuite**
- **XVideos**
- **XXXYMovies**
- **Yahoo**: Yahoo screen and movies
- **Yam**
- **YesJapan**
- **Ynet**
- **YouJizz**
- **Youku**
- **YouPorn**
- **YourUpload**
- **youtube**: YouTube.com
- **youtube:channel**: YouTube.com channels
- **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
- **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
- **youtube:playlist**: YouTube.com playlists
- **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
- **youtube:search**: YouTube.com searches
- **youtube:search:date**: YouTube.com searches, newest videos first
- **youtube:search_url**: YouTube.com search URLs
- **youtube:show**: YouTube.com (multi-season) shows
- **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **ZDF**
- **ZDFChannel**
- **zingmp3:album**: mp3.zing.vn albums
- **zingmp3:song**: mp3.zing.vn songs

View File

@ -1,2 +1,6 @@
[wheel]
universal = True
[flake8]
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build,.git
ignore = E402,E501,E731

View File

@ -82,24 +82,14 @@ class FakeYDL(YoutubeDL):
def gettestcases(include_onlymatching=False):
for ie in youtube_dl.extractor.gen_extractors():
t = getattr(ie, '_TEST', None)
if t:
assert not hasattr(ie, '_TESTS'), \
'%s has _TEST and _TESTS' % type(ie).__name__
tests = [t]
else:
tests = getattr(ie, '_TESTS', [])
for t in tests:
if not include_onlymatching and t.get('only_matching', False):
continue
t['name'] = type(ie).__name__[:-len('IE')]
yield t
for tc in ie.get_testcases(include_onlymatching):
yield tc
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
def expect_info_dict(self, expected_dict, got_dict):
def expect_info_dict(self, got_dict, expected_dict):
for info_field, expected in expected_dict.items():
if isinstance(expected, compat_str) and expected.startswith('re:'):
got = got_dict.get(info_field)
@ -113,6 +103,26 @@ def expect_info_dict(self, expected_dict, got_dict):
self.assertTrue(
match_rex.match(got),
'field %s (value: %r) should match %r' % (info_field, got, match_str))
elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
got = got_dict.get(info_field)
start_str = expected[len('startswith:'):]
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, info_field))
self.assertTrue(
got.startswith(start_str),
'field %s (value: %r) should start with %r' % (info_field, got, start_str))
elif isinstance(expected, compat_str) and expected.startswith('contains:'):
got = got_dict.get(info_field)
contains_str = expected[len('contains:'):]
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, info_field))
self.assertTrue(
contains_str in got,
'field %s (value: %r) should contain %r' % (info_field, got, contains_str))
elif isinstance(expected, type):
got = got_dict.get(info_field)
self.assertTrue(isinstance(got, expected),
@ -120,6 +130,20 @@ def expect_info_dict(self, expected_dict, got_dict):
else:
if isinstance(expected, compat_str) and expected.startswith('md5:'):
got = 'md5:' + md5(got_dict.get(info_field))
elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
got = got_dict.get(info_field)
self.assertTrue(
isinstance(got, list),
'Expected field %s to be a list, but it is of type %s' % (
info_field, type(got).__name__))
expected_num = int(expected.partition(':')[2])
assertGreaterEqual(
self, len(got), expected_num,
'Expected %d items in field %s, but only got %d' % (
expected_num, info_field, len(got)
)
)
continue
else:
got = got_dict.get(info_field)
self.assertEqual(expected, got,
@ -137,7 +161,7 @@ def expect_info_dict(self, expected_dict, got_dict):
# Are checkable fields missing from the test case definition?
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
for key, value in got_dict.items()
if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
if missing_keys:
def _repr(v):
@ -145,11 +169,19 @@ def expect_info_dict(self, expected_dict, got_dict):
return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
else:
return repr(v)
info_dict_str = ''.join(
' %s: %s,\n' % (_repr(k), _repr(v))
for k, v in test_info_dict.items())
info_dict_str = ''
if len(missing_keys) != len(expected_dict):
info_dict_str += ''.join(
' %s: %s,\n' % (_repr(k), _repr(v))
for k, v in test_info_dict.items() if k not in missing_keys)
if info_dict_str:
info_dict_str += '\n'
info_dict_str += ''.join(
' %s: %s,\n' % (_repr(k), _repr(test_info_dict[k]))
for k in missing_keys)
write_string(
'\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
'\n\'info_dict\': {\n' + info_dict_str + '},\n', out=sys.stderr)
self.assertFalse(
missing_keys,
'Missing keys in test definition: %s' % (
@ -162,7 +194,9 @@ def assertRegexpMatches(self, text, regexp, msg=None):
else:
m = re.match(regexp, text)
if not m:
note = 'Regexp didn\'t match: %r not found in %r' % (regexp, text)
note = 'Regexp didn\'t match: %r not found' % (regexp)
if len(text) < 1000:
note += ' in %r' % text
if msg is None:
msg = note
else:

View File

@ -39,5 +39,6 @@
"writesubtitles": false,
"allsubtitles": false,
"listssubtitles": false,
"socket_timeout": 20
"socket_timeout": 20,
"fixup": "never"
}

View File

@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
def test_html_search_meta(self):
ie = self.ie
html = '''
<meta name="a" content="1" />
<meta name='b' content='2'>
<meta name="c" content='3'>
<meta name=d content='4'>
<meta property="e" content='5' >
<meta content="6" name="f">
'''
self.assertEqual(ie._html_search_meta('a', html), '1')
self.assertEqual(ie._html_search_meta('b', html), '2')
self.assertEqual(ie._html_search_meta('c', html), '3')
self.assertEqual(ie._html_search_meta('d', html), '4')
self.assertEqual(ie._html_search_meta('e', html), '5')
self.assertEqual(ie._html_search_meta('f', html), '6')
if __name__ == '__main__':
unittest.main()

View File

@ -8,9 +8,12 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import copy
from test.helper import FakeYDL, assertRegexpMatches
from youtube_dl import YoutubeDL
from youtube_dl.extractor import YoutubeIE
from youtube_dl.postprocessor.common import PostProcessor
class YDL(FakeYDL):
@ -192,6 +195,37 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'vid-high')
def test_format_selection_audio_exts(self):
formats = [
{'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
]
info_dict = _make_result(formats)
ydl = YDL({'format': 'best'})
ie = YoutubeIE(ydl)
ie._sort_formats(info_dict['formats'])
ydl.process_ie_result(copy.deepcopy(info_dict))
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'aac-64')
ydl = YDL({'format': 'mp3'})
ie = YoutubeIE(ydl)
ie._sort_formats(info_dict['formats'])
ydl.process_ie_result(copy.deepcopy(info_dict))
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'mp3-64')
ydl = YDL({'prefer_free_formats': True})
ie = YoutubeIE(ydl)
ie._sort_formats(info_dict['formats'])
ydl.process_ie_result(copy.deepcopy(info_dict))
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'ogg-64')
def test_format_selection_video(self):
formats = [
{'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
@ -218,7 +252,7 @@ class TestFormatSelection(unittest.TestCase):
# 3D
'85', '84', '102', '83', '101', '82', '100',
# Dash video
'138', '137', '248', '136', '247', '135', '246',
'137', '248', '136', '247', '135', '246',
'245', '244', '134', '243', '133', '242', '160',
# Dash audio
'141', '172', '140', '171', '139',
@ -248,6 +282,61 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1id)
def test_format_filtering(self):
formats = [
{'format_id': 'A', 'filesize': 500, 'width': 1000},
{'format_id': 'B', 'filesize': 1000, 'width': 500},
{'format_id': 'C', 'filesize': 1000, 'width': 400},
{'format_id': 'D', 'filesize': 2000, 'width': 600},
{'format_id': 'E', 'filesize': 3000},
{'format_id': 'F'},
{'format_id': 'G', 'filesize': 1000000},
]
for f in formats:
f['url'] = 'http://_/'
f['ext'] = 'unknown'
info_dict = _make_result(formats)
ydl = YDL({'format': 'best[filesize<3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'D')
ydl = YDL({'format': 'best[filesize<=3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'E')
ydl = YDL({'format': 'best[filesize <= ? 3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'F')
ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'B')
ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'C')
ydl = YDL({'format': '[filesize>?1]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'G')
ydl = YDL({'format': '[filesize<1M]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'E')
ydl = YDL({'format': '[filesize<1MiB]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'G')
def test_add_extra_info(self):
test_dict = {
'extractor': 'Foo',
@ -282,5 +371,35 @@ class TestFormatSelection(unittest.TestCase):
'vbr': 10,
}), '^\s*10k$')
def test_postprocessors(self):
filename = 'post-processor-testfile.mp4'
audiofile = filename + '.mp3'
class SimplePP(PostProcessor):
def run(self, info):
with open(audiofile, 'wt') as f:
f.write('EXAMPLE')
info['filepath']
return False, info
def run_pp(params):
with open(filename, 'wt') as f:
f.write('EXAMPLE')
ydl = YoutubeDL(params)
ydl.add_post_processor(SimplePP())
ydl.post_process(filename, {'filepath': filename})
run_pp({'keepvideo': True})
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(filename)
os.unlink(audiofile)
run_pp({'keepvideo': False})
self.assertFalse(os.path.exists(filename), '%s exists' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(audiofile)
if __name__ == '__main__':
unittest.main()

View File

@ -45,11 +45,6 @@ class TestAgeRestriction(unittest.TestCase):
'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'505835.mp4', 2, old_age=25)
def test_pornotube(self):
self._assert_restricted(
'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
'1689755.flv', 13)
if __name__ == '__main__':
unittest.main()

View File

@ -14,7 +14,6 @@ from test.helper import gettestcases
from youtube_dl.extractor import (
FacebookIE,
gen_extractors,
TwitchIE,
YoutubeIE,
)
@ -72,18 +71,6 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
def test_twitch_channelid_matching(self):
self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv'))
self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv'))
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv'))
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/'))
def test_twitch_videoid_matching(self):
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
def test_twitch_chapterid_matching(self):
self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
def test_youtube_extract(self):
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
@ -115,8 +102,6 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch(':ythistory', ['youtube:history'])
self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
self.assertMatch(':tds', ['ComedyCentralShows'])
self.assertMatch(':colbertreport', ['ComedyCentralShows'])
self.assertMatch(':cr', ['ComedyCentralShows'])
def test_vimeo_matching(self):
self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])

View File

@ -89,7 +89,7 @@ def generator(test_case):
for tc in test_cases:
info_dict = tc.get('info_dict', {})
if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
if not (info_dict.get('id') and info_dict.get('ext')):
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
if 'skip' in test_case:
@ -116,7 +116,7 @@ def generator(test_case):
expect_warnings(ydl, test_case.get('expected_warnings', []))
def get_tc_filename(tc):
return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
return ydl.prepare_filename(tc.get('info_dict', {}))
res_dict = None
@ -155,7 +155,7 @@ def generator(test_case):
if is_playlist:
self.assertEqual(res_dict['_type'], 'playlist')
self.assertTrue('entries' in res_dict)
expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
if 'playlist_mincount' in test_case:
assertGreaterEqual(
@ -204,7 +204,7 @@ def generator(test_case):
with io.open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof)
expect_info_dict(self, tc.get('info_dict', {}), info_dict)
expect_info_dict(self, info_dict, tc.get('info_dict', {}))
finally:
try_rm_tcs_files()
if is_playlist and res_dict is not None and res_dict.get('entries'):

72
test/test_http.py Normal file
View File

@ -0,0 +1,72 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl import YoutubeDL
from youtube_dl.compat import compat_http_server
import ssl
import threading
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
def log_message(self, format, *args):
pass
def do_GET(self):
if self.path == '/video.html':
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.end_headers()
self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
elif self.path == '/vid.mp4':
self.send_response(200)
self.send_header('Content-Type', 'video/mp4')
self.end_headers()
self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
else:
assert False
class FakeLogger(object):
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
pass
class TestHTTP(unittest.TestCase):
def setUp(self):
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.httpd = compat_http_server.HTTPServer(
('localhost', 0), HTTPTestRequestHandler)
self.httpd.socket = ssl.wrap_socket(
self.httpd.socket, certfile=certfn, server_side=True)
self.port = self.httpd.socket.getsockname()[1]
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
def test_nocheckcertificate(self):
if sys.version_info >= (2, 7, 9): # No certificate checking anyways
ydl = YoutubeDL({'logger': FakeLogger()})
self.assertRaises(
Exception,
ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
if __name__ == '__main__':
unittest.main()

106
test/test_jsinterp.py Normal file
View File

@ -0,0 +1,106 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.jsinterp import JSInterpreter
class TestJSInterpreter(unittest.TestCase):
def test_basic(self):
jsi = JSInterpreter('function x(){;}')
self.assertEqual(jsi.call_function('x'), None)
jsi = JSInterpreter('function x3(){return 42;}')
self.assertEqual(jsi.call_function('x3'), 42)
def test_calc(self):
jsi = JSInterpreter('function x4(a){return 2*a+1;}')
self.assertEqual(jsi.call_function('x4', 3), 7)
def test_empty_return(self):
jsi = JSInterpreter('function f(){return; y()}')
self.assertEqual(jsi.call_function('f'), None)
def test_morespace(self):
jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
self.assertEqual(jsi.call_function('x', 3), 7)
jsi = JSInterpreter('function f () { x = 2 ; return x; }')
self.assertEqual(jsi.call_function('f'), 2)
def test_strange_chars(self):
jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
self.assertEqual(jsi.call_function('$_xY1', 20), 21)
def test_operators(self):
jsi = JSInterpreter('function f(){return 1 << 5;}')
self.assertEqual(jsi.call_function('f'), 32)
jsi = JSInterpreter('function f(){return 19 & 21;}')
self.assertEqual(jsi.call_function('f'), 17)
jsi = JSInterpreter('function f(){return 11 >> 2;}')
self.assertEqual(jsi.call_function('f'), 2)
def test_array_access(self):
jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
self.assertEqual(jsi.call_function('f'), [5, 2, 7])
def test_parens(self):
jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
self.assertEqual(jsi.call_function('f'), 7)
jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
self.assertEqual(jsi.call_function('f'), 9)
def test_assignments(self):
jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), 31)
jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), 51)
jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), -11)
def test_comments(self):
'Skipping: Not yet fully implemented'
return
jsi = JSInterpreter('''
function x() {
var x = /* 1 + */ 2;
var y = /* 30
* 40 */ 50;
return x + y;
}
''')
self.assertEqual(jsi.call_function('x'), 52)
jsi = JSInterpreter('''
function f() {
var x = "/*";
var y = 1 /* comment */ + 2;
return y;
}
''')
self.assertEqual(jsi.call_function('f'), 3)
def test_precedence(self):
jsi = JSInterpreter('''
function x() {
var a = [10, 20, 30, 40, 50];
var b = 6;
a[0]=a[b%a.length];
return a;
}''')
self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
if __name__ == '__main__':
unittest.main()

View File

@ -17,6 +17,7 @@ from youtube_dl.extractor import (
TEDIE,
VimeoIE,
WallaIE,
CeskaTelevizeIE,
)
@ -88,6 +89,14 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None)
def test_youtube_translated_subtitles(self):
# This video has a subtitles track, which can be translated
self.url = 'Ky9eprVWzlI'
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None)
def test_youtube_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'n5BB19UTcdA'
@ -129,7 +138,7 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 5)
self.assertTrue(len(subtitles.keys()) >= 6)
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
@ -309,5 +318,32 @@ class TestWallaSubtitles(BaseTestSubtitles):
self.assertEqual(len(subtitles), 0)
class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
IE = CeskaTelevizeIE
def test_list_subtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['cs']))
self.assertTrue(len(subtitles['cs']) > 20000)
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0)
if __name__ == '__main__':
unittest.main()

View File

@ -1,9 +1,13 @@
from __future__ import unicode_literals
import io
# Allow direct execution
import os
import re
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import io
import re
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
@ -14,6 +18,9 @@ IGNORED_FILES = [
]
from test.helper import assertRegexpMatches
class TestUnicodeLiterals(unittest.TestCase):
def test_all_files(self):
for dirpath, _, filenames in os.walk(rootDir):
@ -29,9 +36,10 @@ class TestUnicodeLiterals(unittest.TestCase):
if "'" not in code and '"' not in code:
continue
self.assertRegexpMatches(
assertRegexpMatches(
self,
code,
r'(?:#.*\n*)?from __future__ import (?:[a-z_]+,\s*)*unicode_literals',
r'(?:(?:#.*?|\s*)\n)*from __future__ import (?:[a-z_]+,\s*)*unicode_literals',
'unicode_literals import missing in %s' % fn)
m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code)

View File

@ -16,38 +16,44 @@ import json
import xml.etree.ElementTree
from youtube_dl.utils import (
age_restricted,
args_to_str,
clean_html,
DateRange,
detect_exe_version,
encodeFilename,
escape_rfc3986,
escape_url,
find_xpath_attr,
fix_xml_ampersands,
orderedSet,
OnDemandPagedList,
InAdvancePagedList,
intlist_to_bytes,
is_html,
js_to_json,
limit_length,
OnDemandPagedList,
orderedSet,
parse_duration,
parse_filesize,
parse_iso8601,
read_batch_urls,
sanitize_filename,
shell_quote,
smuggle_url,
str_to_int,
strip_jsonp,
struct_unpack,
timeconvert,
unescapeHTML,
unified_strdate,
unsmuggle_url,
uppercase_escape,
url_basename,
urlencode_postdata,
version_tuple,
xpath_with_ns,
parse_iso8601,
strip_jsonp,
uppercase_escape,
limit_length,
escape_rfc3986,
escape_url,
js_to_json,
intlist_to_bytes,
args_to_str,
parse_filesize,
render_table,
match_str,
)
@ -76,6 +82,10 @@ class TestUtil(unittest.TestCase):
tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
self.assertEqual(sanitize_filename(tests), tests)
self.assertEqual(
sanitize_filename('New World record at 0:12:34'),
'New World record at 0_12_34')
forbidden = '"\0\\/'
for fc in forbidden:
for fbc in forbidden:
@ -141,8 +151,15 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_strdate('8/7/2009'), '20090708')
self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
self.assertEqual(unified_strdate('1968 12 10'), '19681210')
self.assertEqual(unified_strdate('1968-12-10'), '19681210')
self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
self.assertEqual(
unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
'20141126')
self.assertEqual(
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
def test_find_xpath_attr(self):
testxml = '''<root>
@ -202,6 +219,8 @@ class TestUtil(unittest.TestCase):
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
self.assertEqual(parse_duration(False), None)
self.assertEqual(parse_duration('invalid'), None)
self.assertEqual(parse_duration('1'), 1)
self.assertEqual(parse_duration('1337:12'), 80232)
self.assertEqual(parse_duration('9:12:43'), 33163)
@ -220,6 +239,11 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('0s'), 0)
self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
self.assertEqual(parse_duration('T30M38S'), 1838)
self.assertEqual(parse_duration('5 s'), 5)
self.assertEqual(parse_duration('3 min'), 180)
self.assertEqual(parse_duration('2.5 hours'), 9000)
self.assertEqual(parse_duration('02:03:04'), 7384)
self.assertEqual(parse_duration('01:02:03:04'), 93784)
def test_fix_xml_ampersands(self):
self.assertEqual(
@ -346,6 +370,10 @@ class TestUtil(unittest.TestCase):
"playlist":[{"controls":{"all":null}}]
}''')
inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
json_code = js_to_json(inp)
self.assertEqual(json.loads(json_code), json.loads(inp))
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@ -353,6 +381,16 @@ class TestUtil(unittest.TestCase):
on = js_to_json('{"abc": true}')
self.assertEqual(json.loads(on), {'abc': True})
# Ignore JavaScript code as well
on = js_to_json('''{
"x": 1,
y: "a",
z: some.code
}''')
d = json.loads(on)
self.assertEqual(d['x'], 1)
self.assertEqual(d['y'], 'a')
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
@ -376,6 +414,87 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_filesize('2 MiB'), 2097152)
self.assertEqual(parse_filesize('5 GB'), 5000000000)
self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
self.assertEqual(parse_filesize('1,24 KB'), 1240)
def test_version_tuple(self):
self.assertEqual(version_tuple('1'), (1,))
self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
def test_detect_exe_version(self):
self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
configuration: --prefix=/usr --extra-'''), '1.2.1')
self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
Trying to open render node...
Success at /dev/dri/renderD128.
ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
def test_age_restricted(self):
self.assertFalse(age_restricted(None, 10)) # unrestricted content
self.assertFalse(age_restricted(1, None)) # unrestricted policy
self.assertFalse(age_restricted(8, 10))
self.assertTrue(age_restricted(18, 14))
self.assertFalse(age_restricted(18, 18))
def test_is_html(self):
self.assertFalse(is_html(b'\x49\x44\x43<html'))
self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
self.assertTrue(is_html( # UTF-8 with BOM
b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
self.assertTrue(is_html( # UTF-16-LE
b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
))
self.assertTrue(is_html( # UTF-16-BE
b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
))
self.assertTrue(is_html( # UTF-32-BE
b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
self.assertTrue(is_html( # UTF-32-LE
b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
def test_render_table(self):
self.assertEqual(
render_table(
['a', 'bcd'],
[[123, 4], [9999, 51]]),
'a bcd\n'
'123 4\n'
'9999 51')
def test_match_str(self):
self.assertRaises(ValueError, match_str, 'xy>foobar', {})
self.assertFalse(match_str('xy', {'x': 1200}))
self.assertTrue(match_str('!xy', {'x': 1200}))
self.assertTrue(match_str('x', {'x': 1200}))
self.assertFalse(match_str('!x', {'x': 1200}))
self.assertTrue(match_str('x', {'x': 0}))
self.assertFalse(match_str('x>0', {'x': 0}))
self.assertFalse(match_str('x>0', {}))
self.assertTrue(match_str('x>?0', {}))
self.assertTrue(match_str('x>1K', {'x': 1200}))
self.assertFalse(match_str('x>2K', {'x': 1200}))
self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 90, 'description': 'foo'}))
self.assertTrue(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'description': 'foo'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 10}))
if __name__ == '__main__':
unittest.main()

View File

@ -1,76 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_params
import io
import json
import youtube_dl.YoutubeDL
import youtube_dl.extractor
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
super(YoutubeDL, self).__init__(*args, **kwargs)
self.to_stderr = self.to_screen
params = get_params({
'writeinfojson': True,
'skip_download': True,
'writedescription': True,
})
TEST_ID = 'BaW_jenozKc'
INFO_JSON_FILE = TEST_ID + '.info.json'
DESCRIPTION_FILE = TEST_ID + '.mp4.description'
EXPECTED_DESCRIPTION = '''test chars: "'/\ä↭𝕐
test URL: https://github.com/rg3/youtube-dl/issues/1892
This is a test video for youtube-dl.
For more information, contact phihag@phihag.de .'''
class TestInfoJSON(unittest.TestCase):
def setUp(self):
# Clear old files
self.tearDown()
def test_info_json(self):
ie = youtube_dl.extractor.YoutubeIE()
ydl = YoutubeDL(params)
ydl.add_info_extractor(ie)
ydl.download([TEST_ID])
self.assertTrue(os.path.exists(INFO_JSON_FILE))
with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
jd = json.load(jsonf)
self.assertEqual(jd['upload_date'], '20121002')
self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
self.assertEqual(jd['id'], TEST_ID)
self.assertEqual(jd['extractor'], 'youtube')
self.assertEqual(jd['title'], '''youtube-dl test video "'/\ä↭𝕐''')
self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
self.assertTrue(os.path.exists(DESCRIPTION_FILE))
with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf:
descr = descf.read()
self.assertEqual(descr, EXPECTED_DESCRIPTION)
def tearDown(self):
if os.path.exists(INFO_JSON_FILE):
os.remove(INFO_JSON_FILE)
if os.path.exists(DESCRIPTION_FILE):
os.remove(DESCRIPTION_FILE)
if __name__ == '__main__':
unittest.main()

View File

@ -8,11 +8,11 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import io
import re
import string
from test.helper import FakeYDL
from youtube_dl.extractor import YoutubeIE
from youtube_dl.compat import compat_str, compat_urlretrieve
@ -64,6 +64,12 @@ _TESTS = [
'js',
'4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
'82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
'js',
'312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
'112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
)
]
@ -88,7 +94,8 @@ def make_tfunc(url, stype, sig_input, expected_sig):
if not os.path.exists(fn):
compat_urlretrieve(url, fn)
ie = YoutubeIE()
ydl = FakeYDL()
ie = YoutubeIE(ydl)
if stype == 'js':
with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read()

52
test/testcert.pem Normal file
View File

@ -0,0 +1,52 @@
-----BEGIN PRIVATE KEY-----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-----END PRIVATE KEY-----
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

View File

@ -7,8 +7,10 @@ import collections
import datetime
import errno
import io
import itertools
import json
import locale
import operator
import os
import platform
import re
@ -23,9 +25,11 @@ if os.name == 'nt':
import ctypes
from .compat import (
compat_basestring,
compat_cookiejar,
compat_expanduser,
compat_http_client,
compat_kwargs,
compat_str,
compat_urllib_error,
compat_urllib_request,
@ -47,27 +51,38 @@ from .utils import (
make_HTTPS_handler,
MaxDownloadsReached,
PagedList,
parse_filesize,
PostProcessingError,
platform_name,
preferredencoding,
render_table,
SameFileError,
sanitize_filename,
std_headers,
subtitles_filename,
build_part_filename,
takewhile_inclusive,
UnavailableVideoError,
url_basename,
version_tuple,
write_json_file,
write_string,
YoutubeDLHandler,
prepend_extension,
args_to_str,
age_restricted,
)
from .cache import Cache
from .extractor import get_info_extractor, gen_extractors
from .downloader import get_suitable_downloader
from .downloader.rtmp import rtmpdump_version
from .postprocessor import FFmpegMergerPP, FFmpegPostProcessor
from .postprocessor import (
FFmpegFixupM4aPP,
FFmpegFixupStretchedPP,
FFmpegMergerPP,
FFmpegPostProcessor,
get_postprocessor,
)
from .version import __version__
@ -116,7 +131,7 @@ class YoutubeDL(object):
dump_single_json: Force printing the info_dict of the whole playlist
(or video) as a single JSON line.
simulate: Do not download the video files.
format: Video format code.
format: Video format code. See options.py for more information.
format_limit: Highest quality format to try.
outtmpl: Template for output names.
restrictfilenames: Do not allow "&" and spaces in file names
@ -124,6 +139,8 @@ class YoutubeDL(object):
nooverwrites: Prevent overwriting files.
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
playlist_items: Specific indices of playlist to download.
playlistreverse: Download playlist items in reverse order.
matchtitle: Download only matching titles.
rejecttitle: Reject downloads for matching titles.
logger: Log messages to a logging.Logger instance.
@ -132,6 +149,7 @@ class YoutubeDL(object):
writeinfojson: Write the video description to a .info.json file
writeannotations: Write the video annotations to a .annotations.xml file
writethumbnail: Write the thumbnail image to a file
write_all_thumbnails: Write all thumbnail formats to files
writesubtitles: Write the video subtitles to a file
writeautomaticsub: Write the automatic subtitles to a file
allsubtitles: Downloads all the subtitles of the video
@ -175,11 +193,65 @@ class YoutubeDL(object):
extract_flat: Do not resolve URLs, return the immediate result.
Pass in 'in_playlist' to only show this behavior for
playlist items.
postprocessors: A list of dictionaries, each with an entry
* key: The name of the postprocessor. See
youtube_dl/postprocessor/__init__.py for a list.
as well as any further keyword arguments for the
postprocessor.
progress_hooks: A list of functions that get called on download
progress, with a dictionary with the entries
* status: One of "downloading", "error", or "finished".
Check this first and ignore unknown values.
If status is one of "downloading", or "finished", the
following properties may also be present:
* filename: The final filename (always present)
* tmpfilename: The filename we're currently writing to
* downloaded_bytes: Bytes on disk
* total_bytes: Size of the whole file, None if unknown
* total_bytes_estimate: Guess of the eventual file size,
None if unavailable.
* elapsed: The number of seconds since download started.
* eta: The estimated time in seconds, None if unknown
* speed: The download speed in bytes/second, None if
unknown
* fragment_index: The counter of the currently
downloaded video fragment.
* fragment_count: The number of fragments (= individual
files that will be merged)
Progress hooks are guaranteed to be called at least once
(with status "finished") if the download is successful.
merge_output_format: Extension to use when merging formats.
fixup: Automatically correct known faults of the file.
One of:
- "never": do nothing
- "warn": only emit a warning
- "detect_or_warn": check whether we can do anything
about it, warn otherwise (default)
source_address: (Experimental) Client-side IP address to bind to.
call_home: Boolean, true iff we are allowed to contact the
youtube-dl servers for debugging.
sleep_interval: Number of seconds to sleep before each download.
listformats: Print an overview of available video formats and exit.
list_thumbnails: Print a table of all thumbnails and exit.
match_filter: A function that gets called with the info_dict of
every video.
If it returns a message, the video is ignored.
If it returns None, the video is downloaded.
match_filter_func in utils.py is one example for this.
no_color: Do not emit color codes in output.
The following options determine which downloader is picked:
external_downloader: Executable of the external downloader to call.
None or unset for standard (built-in) downloader.
hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv.
The following parameters are not used by YoutubeDL itself, they are used by
the FileDownloader:
nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
noresizebuffer, retries, continuedl, noprogress, consoletitle
noresizebuffer, retries, continuedl, noprogress, consoletitle,
xattr_set_filesize.
The following options are used by the post processors:
prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available,
@ -255,6 +327,16 @@ class YoutubeDL(object):
self.print_debug_header()
self.add_default_info_extractors()
for pp_def_raw in self.params.get('postprocessors', []):
pp_class = get_postprocessor(pp_def_raw['key'])
pp_def = dict(pp_def_raw)
del pp_def['key']
pp = pp_class(self, **compat_kwargs(pp_def))
self.add_post_processor(pp)
for ph in self.params.get('progress_hooks', []):
self.add_progress_hook(ph)
def warn_if_short_id(self, argv):
# short YouTube ID starting with dash?
idxs = [
@ -420,7 +502,7 @@ class YoutubeDL(object):
else:
if self.params.get('no_warnings'):
return
if self._err_file.isatty() and os.name != 'nt':
if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m'
else:
_msg_header = 'WARNING:'
@ -432,7 +514,7 @@ class YoutubeDL(object):
Do the same as trouble, but prefixes the message with 'ERROR:', colored
in red if stderr is a tty file.
'''
if self._err_file.isatty() and os.name != 'nt':
if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':
_msg_header = '\033[0;31mERROR:\033[0m'
else:
_msg_header = 'ERROR:'
@ -479,12 +561,17 @@ class YoutubeDL(object):
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
tmpl = compat_expanduser(outtmpl)
filename = tmpl % template_dict
# Temporary fix for #4787
# 'Treat' all problem characters by passing filename through preferredencoding
# to workaround encoding issues with subprocess on python2 @ Windows
if sys.version_info < (3, 0) and sys.platform == 'win32':
filename = encodeFilename(filename, True).decode(preferredencoding())
return filename
except ValueError as err:
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
return None
def _match_entry(self, info_dict):
def _match_entry(self, info_dict, incomplete):
""" Returns None iff the file should be downloaded """
video_title = info_dict.get('title', info_dict.get('id', 'video'))
@ -512,15 +599,18 @@ class YoutubeDL(object):
max_views = self.params.get('max_views')
if max_views is not None and view_count > max_views:
return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
age_limit = self.params.get('age_limit')
if age_limit is not None:
actual_age_limit = info_dict.get('age_limit')
if actual_age_limit is None:
actual_age_limit = 0
if age_limit < actual_age_limit:
return 'Skipping "' + title + '" because it is age restricted'
if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
return 'Skipping "%s" because it is age restricted' % video_title
if self.in_download_archive(info_dict):
return '%s has already been recorded in archive' % video_title
if not incomplete:
match_filter = self.params.get('match_filter')
if match_filter is not None:
ret = match_filter(info_dict)
if ret is not None:
return ret
return None
@staticmethod
@ -622,23 +712,15 @@ class YoutubeDL(object):
ie_result['url'], ie_key=ie_result.get('ie_key'),
extra_info=extra_info, download=False, process=False)
def make_result(embedded_info):
new_result = ie_result.copy()
for f in ('_type', 'url', 'ext', 'player_url', 'formats',
'entries', 'ie_key', 'duration',
'subtitles', 'annotations', 'format',
'thumbnail', 'thumbnails'):
if f in new_result:
del new_result[f]
if f in embedded_info:
new_result[f] = embedded_info[f]
return new_result
new_result = make_result(info)
force_properties = dict(
(k, v) for k, v in ie_result.items() if v is not None)
for f in ('_type', 'url'):
if f in force_properties:
del force_properties[f]
new_result = info.copy()
new_result.update(force_properties)
assert new_result.get('_type') != 'url_transparent'
if new_result.get('_type') == 'compat_list':
new_result['entries'] = [
make_result(e) for e in new_result['entries']]
return self.process_ie_result(
new_result, download=download, extra_info=extra_info)
@ -655,24 +737,61 @@ class YoutubeDL(object):
if playlistend == -1:
playlistend = None
if isinstance(ie_result['entries'], list):
n_all_entries = len(ie_result['entries'])
entries = ie_result['entries'][playliststart:playlistend]
playlistitems_str = self.params.get('playlist_items', None)
playlistitems = None
if playlistitems_str is not None:
def iter_playlistitems(format):
for string_segment in format.split(','):
if '-' in string_segment:
start, end = string_segment.split('-')
for item in range(int(start), int(end) + 1):
yield int(item)
else:
yield int(string_segment)
playlistitems = iter_playlistitems(playlistitems_str)
ie_entries = ie_result['entries']
if isinstance(ie_entries, list):
n_all_entries = len(ie_entries)
if playlistitems:
entries = [ie_entries[i - 1] for i in playlistitems]
else:
entries = ie_entries[playliststart:playlistend]
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
(ie_result['extractor'], playlist, n_all_entries, n_entries))
else:
assert isinstance(ie_result['entries'], PagedList)
entries = ie_result['entries'].getslice(
playliststart, playlistend)
elif isinstance(ie_entries, PagedList):
if playlistitems:
entries = []
for item in playlistitems:
entries.extend(ie_entries.getslice(
item - 1, item
))
else:
entries = ie_entries.getslice(
playliststart, playlistend)
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Downloading %d videos" %
(ie_result['extractor'], playlist, n_entries))
else: # iterable
if playlistitems:
entry_list = list(ie_entries)
entries = [entry_list[i - 1] for i in playlistitems]
else:
entries = list(itertools.islice(
ie_entries, playliststart, playlistend))
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Downloading %d videos" %
(ie_result['extractor'], playlist, n_entries))
if self.params.get('playlistreverse', False):
entries = entries[::-1]
for i, entry in enumerate(entries, 1):
self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
extra = {
'n_entries': n_entries,
'playlist': playlist,
@ -685,7 +804,7 @@ class YoutubeDL(object):
'extractor_key': ie_result['extractor_key'],
}
reason = self._match_entry(entry)
reason = self._match_entry(entry, incomplete=True)
if reason is not None:
self.to_screen('[download] ' + reason)
continue
@ -720,7 +839,76 @@ class YoutubeDL(object):
else:
raise Exception('Invalid result type: %s' % result_type)
def _apply_format_filter(self, format_spec, available_formats):
" Returns a tuple of the remaining format_spec and filtered formats "
OPERATORS = {
'<': operator.lt,
'<=': operator.le,
'>': operator.gt,
'>=': operator.ge,
'=': operator.eq,
'!=': operator.ne,
}
operator_rex = re.compile(r'''(?x)\s*\[
(?P<key>width|height|tbr|abr|vbr|asr|filesize|fps)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
(?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
\]$
''' % '|'.join(map(re.escape, OPERATORS.keys())))
m = operator_rex.search(format_spec)
if m:
try:
comparison_value = int(m.group('value'))
except ValueError:
comparison_value = parse_filesize(m.group('value'))
if comparison_value is None:
comparison_value = parse_filesize(m.group('value') + 'B')
if comparison_value is None:
raise ValueError(
'Invalid value %r in format specification %r' % (
m.group('value'), format_spec))
op = OPERATORS[m.group('op')]
if not m:
STR_OPERATORS = {
'=': operator.eq,
'!=': operator.ne,
}
str_operator_rex = re.compile(r'''(?x)\s*\[
\s*(?P<key>ext|acodec|vcodec|container|protocol)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
\s*(?P<value>[a-zA-Z0-9_-]+)
\s*\]$
''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
m = str_operator_rex.search(format_spec)
if m:
comparison_value = m.group('value')
op = STR_OPERATORS[m.group('op')]
if not m:
raise ValueError('Invalid format specification %r' % format_spec)
def _filter(f):
actual_value = f.get(m.group('key'))
if actual_value is None:
return m.group('none_inclusive')
return op(actual_value, comparison_value)
new_formats = [f for f in available_formats if _filter(f)]
new_format_spec = format_spec[:-len(m.group(0))]
if not new_format_spec:
new_format_spec = 'best'
return (new_format_spec, new_formats)
def select_format(self, format_spec, available_formats):
while format_spec.endswith(']'):
format_spec, available_formats = self._apply_format_filter(
format_spec, available_formats)
if not available_formats:
return None
if format_spec == 'best' or format_spec is None:
return available_formats[-1]
elif format_spec == 'worst':
@ -750,7 +938,7 @@ class YoutubeDL(object):
if video_formats:
return video_formats[0]
else:
extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a']
extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav']
if format_spec in extensions:
filter_f = lambda f: f['ext'] == format_spec
else:
@ -760,6 +948,24 @@ class YoutubeDL(object):
return matches[-1]
return None
def _calc_headers(self, info_dict):
res = std_headers.copy()
add_headers = info_dict.get('http_headers')
if add_headers:
res.update(add_headers)
cookies = self._calc_cookies(info_dict)
if cookies:
res['Cookie'] = cookies
return res
def _calc_cookies(self, info_dict):
pr = compat_urllib_request.Request(info_dict['url'])
self.cookiejar.add_cookie_header(pr)
return pr.get_header('Cookie')
def process_video_result(self, info_dict, download=True):
assert info_dict.get('_type', 'video') == 'video'
@ -774,12 +980,19 @@ class YoutubeDL(object):
info_dict['playlist_index'] = None
thumbnails = info_dict.get('thumbnails')
if thumbnails is None:
thumbnail = info_dict.get('thumbnail')
if thumbnail:
info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
if thumbnails:
thumbnails.sort(key=lambda t: (
t.get('width'), t.get('height'), t.get('url')))
for t in thumbnails:
t.get('preference'), t.get('width'), t.get('height'),
t.get('id'), t.get('url')))
for i, t in enumerate(thumbnails):
if 'width' in t and 'height' in t:
t['resolution'] = '%dx%d' % (t['width'], t['height'])
if t.get('id') is None:
t['id'] = '%d' % i
if thumbnails and 'thumbnail' not in info_dict:
info_dict['thumbnail'] = thumbnails[-1]['url']
@ -788,6 +1001,10 @@ class YoutubeDL(object):
info_dict['display_id'] = info_dict['id']
if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
# Working around negative timestamps in Windows
# (see http://bugs.python.org/issue1646728)
if info_dict['timestamp'] < 0 and os.name == 'nt':
info_dict['timestamp'] = 0
upload_date = datetime.datetime.utcfromtimestamp(
info_dict['timestamp'])
info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
@ -829,6 +1046,11 @@ class YoutubeDL(object):
# Automatically determine file extension if missing
if 'ext' not in format:
format['ext'] = determine_ext(format['url']).lower()
# Add HTTP headers, so that external programs can use them from the
# json output
full_format_info = info_dict.copy()
full_format_info.update(format)
format['http_headers'] = self._calc_headers(full_format_info)
format_limit = self.params.get('format_limit', None)
if format_limit:
@ -844,9 +1066,12 @@ class YoutubeDL(object):
# element in the 'formats' field in info_dict is info_dict itself,
# wich can't be exported to json
info_dict['formats'] = formats
if self.params.get('listformats', None):
if self.params.get('listformats'):
self.list_formats(info_dict)
return
if self.params.get('list_thumbnails'):
self.list_thumbnails(info_dict)
return
req_format = self.params.get('format')
if req_format is None:
@ -874,10 +1099,26 @@ class YoutubeDL(object):
'contain the video, try using '
'"-f %s+%s"' % (format_2, format_1))
return
output_ext = (
formats_info[0]['ext']
if self.params.get('merge_output_format') is None
else self.params['merge_output_format'])
selected_format = {
'requested_formats': formats_info,
'format': rf,
'ext': formats_info[0]['ext'],
'format': '%s+%s' % (formats_info[0].get('format'),
formats_info[1].get('format')),
'format_id': '%s+%s' % (formats_info[0].get('format_id'),
formats_info[1].get('format_id')),
'width': formats_info[0].get('width'),
'height': formats_info[0].get('height'),
'resolution': formats_info[0].get('resolution'),
'fps': formats_info[0].get('fps'),
'vcodec': formats_info[0].get('vcodec'),
'vbr': formats_info[0].get('vbr'),
'stretched_ratio': formats_info[0].get('stretched_ratio'),
'acodec': formats_info[1].get('acodec'),
'abr': formats_info[1].get('abr'),
'ext': output_ext,
}
else:
selected_format = None
@ -921,14 +1162,14 @@ class YoutubeDL(object):
if 'format' not in info_dict:
info_dict['format'] = info_dict['ext']
reason = self._match_entry(info_dict)
reason = self._match_entry(info_dict, incomplete=False)
if reason is not None:
self.to_screen('[download] ' + reason)
return
self._num_downloads += 1
filename = self.prepare_filename(info_dict)
info_dict['_filename'] = filename = self.prepare_filename(info_dict)
# Forced printings
if self.params.get('forcetitle', False):
@ -936,8 +1177,12 @@ class YoutubeDL(object):
if self.params.get('forceid', False):
self.to_stdout(info_dict['id'])
if self.params.get('forceurl', False):
# For RTMP URLs, also include the playpath
self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
if info_dict.get('requested_formats') is not None:
for f in info_dict['requested_formats']:
self.to_stdout(f['url'] + f.get('play_path', ''))
else:
# For RTMP URLs, also include the playpath
self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
self.to_stdout(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
@ -949,10 +1194,7 @@ class YoutubeDL(object):
if self.params.get('forceformat', False):
self.to_stdout(info_dict['format'])
if self.params.get('forcejson', False):
info_dict['_filename'] = filename
self.to_stdout(json.dumps(info_dict))
if self.params.get('dump_single_json', False):
info_dict['_filename'] = filename
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
@ -973,13 +1215,13 @@ class YoutubeDL(object):
descfn = filename + '.description'
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
self.to_screen('[info] Video description is already present')
elif info_dict.get('description') is None:
self.report_warning('There\'s no description to write.')
else:
try:
self.to_screen('[info] Writing video description to: ' + descfn)
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(info_dict['description'])
except (KeyError, TypeError):
self.report_warning('There\'s no description to write.')
except (OSError, IOError):
self.report_error('Cannot write description file ' + descfn)
return
@ -1035,97 +1277,116 @@ class YoutubeDL(object):
self.report_error('Cannot write metadata to JSON file ' + infofn)
return
if self.params.get('writethumbnail', False):
if info_dict.get('thumbnail') is not None:
thumb_format = determine_ext(info_dict['thumbnail'], 'jpg')
thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
self.to_screen('[%s] %s: Thumbnail is already present' %
(info_dict['extractor'], info_dict['id']))
else:
self.to_screen('[%s] %s: Downloading thumbnail ...' %
(info_dict['extractor'], info_dict['id']))
try:
uf = self.urlopen(info_dict['thumbnail'])
with open(thumb_filename, 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf)
self.to_screen('[%s] %s: Writing thumbnail to: %s' %
(info_dict['extractor'], info_dict['id'], thumb_filename))
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_warning('Unable to download thumbnail "%s": %s' %
(info_dict['thumbnail'], compat_str(err)))
self._write_thumbnails(info_dict, filename)
if not self.params.get('skip_download', False):
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
success = True
else:
try:
def dl(name, info):
fd = get_suitable_downloader(info)(self, self.params)
for ph in self._progress_hooks:
fd.add_progress_hook(ph)
if self.params.get('verbose'):
self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
return fd.download(name, info)
if info_dict.get('requested_formats') is not None:
downloaded = []
success = True
merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
if not merger._executable:
postprocessors = []
self.report_warning('You have requested multiple '
'formats but ffmpeg or avconv are not installed.'
' The formats won\'t be merged')
else:
postprocessors = [merger]
for f in info_dict['requested_formats']:
new_info = dict(info_dict)
new_info.update(f)
fname = self.prepare_filename(new_info)
fname = prepend_extension(fname, 'f%s' % f['format_id'])
downloaded.append(fname)
partial_success = dl(fname, new_info)
success = success and partial_success
info_dict['__postprocessors'] = postprocessors
info_dict['__files_to_merge'] = downloaded
try:
def dl(name, info):
fd = get_suitable_downloader(info, self.params)(self, self.params)
for ph in self._progress_hooks:
fd.add_progress_hook(ph)
if self.params.get('verbose'):
self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
return fd.download(name, info)
if info_dict.get('requested_formats') is not None:
downloaded = []
success = True
merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
if not merger.available:
postprocessors = []
self.report_warning('You have requested multiple '
'formats but ffmpeg or avconv are not installed.'
' The formats won\'t be merged')
else:
parts = info_dict.get('parts', [])
if not parts:
success = dl(filename, info_dict)
elif len(parts) == 1:
info_dict.update(parts[0])
success = dl(filename, info_dict)
postprocessors = [merger]
parts = info_dict.get('parts', [])
if not parts:
success = dl(filename, info_dict)
elif len(parts) == 1:
info_dict.update(parts[0])
success = dl(filename, info_dict)
else:
# We check if the final video has already been downloaded
if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)):
self.fd.report_file_already_downloaded(filename)
success = True
else:
# We check if the final video has already been downloaded
if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)):
self.fd.report_file_already_downloaded(filename)
success = True
else:
parts_success = []
self.to_screen(u'[info] Downloading %s parts' % len(parts))
for (i, part) in enumerate(parts):
part_info = dict(info_dict)
part_info.update(part)
part_filename = build_part_filename(filename, i)
parts_success.append(dl(part_filename, part_info))
success = all(parts_success)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_error('unable to download video data: %s' % str(err))
return
except (OSError, IOError) as err:
raise UnavailableVideoError(err)
except (ContentTooShortError, ) as err:
self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
parts_success = []
self.to_screen(u'[info] Downloading %s parts' % len(parts))
for (i, part) in enumerate(parts):
part_info = dict(info_dict)
part_info.update(part)
part_filename = build_part_filename(filename, i)
parts_success.append(dl(part_filename, part_info))
success = all(parts_success)
for f in info_dict['requested_formats']:
new_info = dict(info_dict)
new_info.update(f)
fname = self.prepare_filename(new_info)
fname = prepend_extension(fname, 'f%s' % f['format_id'])
downloaded.append(fname)
partial_success = dl(fname, new_info)
success = success and partial_success
info_dict['__postprocessors'] = postprocessors
info_dict['__files_to_merge'] = downloaded
else:
# Just a single file
success = dl(filename, info_dict)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_error('unable to download video data: %s' % str(err))
return
except (OSError, IOError) as err:
raise UnavailableVideoError(err)
except (ContentTooShortError, ) as err:
self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
# Fixup content
fixup_policy = self.params.get('fixup')
if fixup_policy is None:
fixup_policy = 'detect_or_warn'
stretched_ratio = info_dict.get('stretched_ratio')
if stretched_ratio is not None and stretched_ratio != 1:
if fixup_policy == 'warn':
self.report_warning('%s: Non-uniform pixel ratio (%s)' % (
info_dict['id'], stretched_ratio))
elif fixup_policy == 'detect_or_warn':
stretched_pp = FFmpegFixupStretchedPP(self)
if stretched_pp.available:
info_dict.setdefault('__postprocessors', [])
info_dict['__postprocessors'].append(stretched_pp)
else:
self.report_warning(
'%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % (
info_dict['id'], stretched_ratio))
else:
assert fixup_policy in ('ignore', 'never')
if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash':
if fixup_policy == 'warn':
self.report_warning('%s: writing DASH m4a. Only some players support this container.' % (
info_dict['id']))
elif fixup_policy == 'detect_or_warn':
fixup_pp = FFmpegFixupM4aPP(self)
if fixup_pp.available:
info_dict.setdefault('__postprocessors', [])
info_dict['__postprocessors'].append(fixup_pp)
else:
self.report_warning(
'%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % (
info_dict['id']))
else:
assert fixup_policy in ('ignore', 'never')
try:
self.post_process(filename, info_dict)
except (PostProcessingError) as err:
self.report_error('postprocessing: %s' % str(err))
return
self.record_download_archive(info_dict)
self.record_download_archive(info_dict)
def download(self, url_list):
"""Download a given list of URLs."""
@ -1168,14 +1429,15 @@ class YoutubeDL(object):
"""Run all the postprocessors on the given file."""
info = dict(ie_info)
info['filepath'] = filename
keep_video = None
pps_chain = []
if ie_info.get('__postprocessors') is not None:
pps_chain.extend(ie_info['__postprocessors'])
pps_chain.extend(self._pps)
for pp in pps_chain:
keep_video = None
old_filename = info['filepath']
try:
keep_video_wish, new_info = pp.run(info)
keep_video_wish, info = pp.run(info)
if keep_video_wish is not None:
if keep_video_wish:
keep_video = keep_video_wish
@ -1184,12 +1446,12 @@ class YoutubeDL(object):
keep_video = keep_video_wish
except PostProcessingError as e:
self.report_error(e.msg)
if keep_video is False and not self.params.get('keepvideo', False):
try:
self.to_screen('Deleting original file %s (pass -k to keep)' % filename)
os.remove(encodeFilename(filename))
except (IOError, OSError):
self.report_warning('Unable to remove downloaded video file')
if keep_video is False and not self.params.get('keepvideo', False):
try:
self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
os.remove(encodeFilename(old_filename))
except (IOError, OSError):
self.report_warning('Unable to remove downloaded video file')
def _make_archive_id(self, info_dict):
# Future-proof against any change in case
@ -1298,27 +1560,35 @@ class YoutubeDL(object):
return res
def list_formats(self, info_dict):
def line(format, idlen=20):
return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % (
format['format_id'],
format['ext'],
self.format_resolution(format),
self._format_note(format),
))
formats = info_dict.get('formats', [info_dict])
idlen = max(len('format code'),
max(len(f['format_id']) for f in formats))
formats_s = [line(f, idlen) for f in formats]
table = [
[f['format_id'], f['ext'], self.format_resolution(f), self._format_note(f)]
for f in formats
if f.get('preference') is None or f['preference'] >= -1000]
if len(formats) > 1:
formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'
formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
table[-1][-1] += (' ' if table[-1][-1] else '') + '(best)'
header_line = line({
'format_id': 'format code', 'ext': 'extension',
'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)
self.to_screen('[info] Available formats for %s:\n%s\n%s' %
(info_dict['id'], header_line, '\n'.join(formats_s)))
header_line = ['format code', 'extension', 'resolution', 'note']
self.to_screen(
'[info] Available formats for %s:\n%s' %
(info_dict['id'], render_table(header_line, table)))
def list_thumbnails(self, info_dict):
thumbnails = info_dict.get('thumbnails')
if not thumbnails:
tn_url = info_dict.get('thumbnail')
if tn_url:
thumbnails = [{'id': '0', 'url': tn_url}]
else:
self.to_screen(
'[info] No thumbnails present for %s' % info_dict['id'])
return
self.to_screen(
'[info] Thumbnails for %s:' % info_dict['id'])
self.to_screen(render_table(
['ID', 'width', 'height', 'URL'],
[[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails]))
def urlopen(self, req):
""" Start an HTTP download """
@ -1329,7 +1599,7 @@ class YoutubeDL(object):
# urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
# To work around aforementioned issue we will replace request's original URL with
# percent-encoded one
req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str)
req_is_string = isinstance(req, compat_basestring)
url = req if req_is_string else req.get_full_url()
url_escaped = escape_url(url)
@ -1381,7 +1651,7 @@ class YoutubeDL(object):
self._write_string('[debug] Python version %s - %s\n' % (
platform.python_version(), platform_name()))
exe_versions = FFmpegPostProcessor.get_versions()
exe_versions = FFmpegPostProcessor.get_versions(self)
exe_versions['rtmpdump'] = rtmpdump_version()
exe_str = ', '.join(
'%s %s' % (exe, v)
@ -1398,6 +1668,17 @@ class YoutubeDL(object):
proxy_map.update(handler.proxies)
self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
if self.params.get('call_home', False):
ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8')
self._write_string('[debug] Public IP address: %s\n' % ipaddr)
latest_version = self.urlopen(
'https://yt-dl.org/latest/version').read().decode('utf-8')
if version_tuple(latest_version) > version_tuple(__version__):
self.report_warning(
'You are using an outdated version (newest version: %s)! '
'See https://yt-dl.org/update if you need help updating.' %
latest_version)
def _setup_opener(self):
timeout_val = self.params.get('socket_timeout')
self._socket_timeout = 600 if timeout_val is None else float(timeout_val)
@ -1428,9 +1709,8 @@ class YoutubeDL(object):
proxy_handler = compat_urllib_request.ProxyHandler(proxies)
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(
self.params.get('nocheckcertificate', False), debuglevel=debuglevel)
ydlh = YoutubeDLHandler(debuglevel=debuglevel)
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
opener = compat_urllib_request.build_opener(
https_handler, proxy_handler, cookie_processor, ydlh)
# Delete the default user-agent header, which would otherwise apply in
@ -1454,3 +1734,39 @@ class YoutubeDL(object):
if encoding is None:
encoding = preferredencoding()
return encoding
def _write_thumbnails(self, info_dict, filename):
if self.params.get('writethumbnail', False):
thumbnails = info_dict.get('thumbnails')
if thumbnails:
thumbnails = [thumbnails[-1]]
elif self.params.get('write_all_thumbnails', False):
thumbnails = info_dict.get('thumbnails')
else:
return
if not thumbnails:
# No thumbnails present, so return immediately
return
for t in thumbnails:
thumb_ext = determine_ext(t['url'], 'jpg')
suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
self.to_screen('[%s] %s: Thumbnail %sis already present' %
(info_dict['extractor'], info_dict['id'], thumb_display_id))
else:
self.to_screen('[%s] %s: Downloading thumbnail %s...' %
(info_dict['extractor'], info_dict['id'], thumb_display_id))
try:
uf = self.urlopen(t['url'])
with open(thumb_filename, 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf)
self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
(info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_warning('Unable to download thumbnail "%s": %s' %
(t['url'], compat_str(err)))

View File

@ -23,9 +23,10 @@ from .compat import (
)
from .utils import (
DateRange,
DEFAULT_OUTTMPL,
decodeOption,
DEFAULT_OUTTMPL,
DownloadError,
match_filter_func,
MaxDownloadsReached,
preferredencoding,
read_batch_urls,
@ -38,19 +39,8 @@ from .update import update_self
from .downloader import (
FileDownloader,
)
from .extractor import gen_extractors
from .extractor import gen_extractors, list_extractors
from .YoutubeDL import YoutubeDL
from .postprocessor import (
AtomicParsleyPP,
FFmpegAudioFixPP,
FFmpegMetadataPP,
FFmpegVideoConvertor,
FFmpegExtractAudioPP,
FFmpegEmbedSubtitlePP,
XAttrMetadataPP,
FFmpegJoinVideosPP,
ExecAfterDownloadPP,
)
def _real_main(argv=None):
@ -106,24 +96,22 @@ def _real_main(argv=None):
_enc = preferredencoding()
all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
extractors = gen_extractors()
if opts.list_extractors:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
for ie in list_extractors(opts.age_limit):
compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
matchedUrls = [url for url in all_urls if ie.suitable(url)]
for mu in matchedUrls:
compat_print(' ' + mu)
sys.exit(0)
if opts.list_extractor_descriptions:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
for ie in list_extractors(opts.age_limit):
if not ie._WORKING:
continue
desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
if desc is False:
continue
if hasattr(ie, 'SEARCH_KEY'):
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny')
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
_COUNTS = ('', '5', '10', 'all')
desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
compat_print(desc)
@ -156,10 +144,13 @@ def _real_main(argv=None):
parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.retries is not None:
try:
opts.retries = int(opts.retries)
except (TypeError, ValueError):
parser.error('invalid retry count specified')
if opts.retries in ('inf', 'infinite'):
opts_retries = float('inf')
else:
try:
opts_retries = int(opts.retries)
except (TypeError, ValueError):
parser.error('invalid retry count specified')
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
@ -179,6 +170,7 @@ def _real_main(argv=None):
if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
parser.error('invalid video recode format specified')
if opts.date is not None:
date = DateRange.day(opts.date)
else:
@ -210,16 +202,63 @@ def _real_main(argv=None):
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
' template'.format(outtmpl))
any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
any_printing = opts.print_json
download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
# PostProcessors
postprocessors = []
# Add the metadata pp first, the other pps will copy it
if opts.addmetadata:
postprocessors.append({'key': 'FFmpegMetadata'})
if opts.extractaudio:
postprocessors.append({
'key': 'FFmpegExtractAudio',
'preferredcodec': opts.audioformat,
'preferredquality': opts.audioquality,
'nopostoverwrites': opts.nopostoverwrites,
})
if opts.recodevideo:
postprocessors.append({
'key': 'FFmpegVideoConvertor',
'preferedformat': opts.recodevideo,
})
if opts.embedsubtitles:
postprocessors.append({
'key': 'FFmpegEmbedSubtitle',
'subtitlesformat': opts.subtitlesformat,
})
if opts.xattrs:
postprocessors.append({'key': 'XAttrMetadata'})
if opts.embedthumbnail:
if not opts.addmetadata:
postprocessors.append({'key': 'FFmpegAudioFix'})
postprocessors.append({'key': 'AtomicParsley'})
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd:
postprocessors.append({
'key': 'ExecAfterDownload',
'verboseOutput': opts.verbose,
'exec_cmd': opts.exec_cmd,
})
if opts.xattr_set_filesize:
try:
import xattr
xattr # Confuse flake8
except ImportError:
parser.error('setting filesize xattr requested but python-xattr is not available')
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))
ydl_opts = {
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'twofactor': opts.twofactor,
'videopassword': opts.videopassword,
'quiet': (opts.quiet or any_printing),
'quiet': (opts.quiet or any_getting or any_printing),
'no_warnings': opts.no_warnings,
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
@ -229,9 +268,9 @@ def _real_main(argv=None):
'forceduration': opts.getduration,
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
'forcejson': opts.dumpjson,
'forcejson': opts.dumpjson or opts.print_json,
'dump_single_json': opts.dump_single_json,
'simulate': opts.simulate or any_printing,
'simulate': opts.simulate or any_getting,
'skip_download': opts.skip_download,
'format': opts.format,
'format_limit': opts.format_limit,
@ -242,7 +281,7 @@ def _real_main(argv=None):
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'retries': opts.retries,
'retries': opts_retries,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,
@ -250,6 +289,7 @@ def _real_main(argv=None):
'progress_with_newline': opts.progress_with_newline,
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'playlistreverse': opts.playlist_reverse,
'noplaylist': opts.noplaylist,
'joinparts': opts.joinparts,
'logtostderr': opts.outtmpl == '-',
@ -260,6 +300,7 @@ def _real_main(argv=None):
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail,
'write_all_thumbnails': opts.write_all_thumbnails,
'writesubtitles': opts.writesubtitles,
'writeautomaticsub': opts.writeautomaticsub,
'allsubtitles': opts.allsubtitles,
@ -298,34 +339,23 @@ def _real_main(argv=None):
'encoding': opts.encoding,
'exec_cmd': opts.exec_cmd,
'extract_flat': opts.extract_flat,
'merge_output_format': opts.merge_output_format,
'postprocessors': postprocessors,
'fixup': opts.fixup,
'source_address': opts.source_address,
'call_home': opts.call_home,
'sleep_interval': opts.sleep_interval,
'external_downloader': opts.external_downloader,
'list_thumbnails': opts.list_thumbnails,
'playlist_items': opts.playlist_items,
'xattr_set_filesize': opts.xattr_set_filesize,
'match_filter': match_filter,
'no_color': opts.no_color,
'ffmpeg_location': opts.ffmpeg_location,
'hls_prefer_native': opts.hls_prefer_native,
}
with YoutubeDL(ydl_opts) as ydl:
# PostProcessors
if opts.joinparts:
ydl.add_post_processor(FFmpegJoinVideosPP())
# Add the metadata pp first, the other pps will copy it
if opts.addmetadata:
ydl.add_post_processor(FFmpegMetadataPP())
if opts.extractaudio:
ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
if opts.recodevideo:
ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
if opts.embedsubtitles:
ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
if opts.xattrs:
ydl.add_post_processor(XAttrMetadataPP())
if opts.embedthumbnail:
if not opts.addmetadata:
ydl.add_post_processor(FFmpegAudioFixPP())
ydl.add_post_processor(AtomicParsleyPP())
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd:
ydl.add_post_processor(ExecAfterDownloadPP(
verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))
# Update version
if opts.update_self:
update_self(ydl.to_screen, opts.verbose)
@ -340,7 +370,9 @@ def _real_main(argv=None):
sys.exit()
ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
parser.error('you must provide at least one URL')
parser.error(
'You must provide at least one URL.\n'
'Type youtube-dl --help to see a list of all options.')
try:
if opts.load_info_filename is not None:
@ -363,3 +395,5 @@ def main(argv=None):
sys.exit('ERROR: fixed output name but more than one file to download')
except KeyboardInterrupt:
sys.exit('\nERROR: Interrupted by user')
__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

View File

@ -1,7 +1,5 @@
from __future__ import unicode_literals
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
import base64
from math import ceil
@ -329,3 +327,5 @@ def inc(data):
data[i] = data[i] + 1
break
return data
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']

View File

@ -4,6 +4,7 @@ import getpass
import optparse
import os
import re
import socket
import subprocess
import sys
@ -70,6 +71,11 @@ try:
except ImportError:
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
try:
import http.server as compat_http_server
except ImportError:
import BaseHTTPServer as compat_http_server
try:
from urllib.parse import unquote as compat_urllib_parse_unquote
except ImportError:
@ -108,6 +114,26 @@ except ImportError:
string += pct_sequence.decode(encoding, errors)
return string
try:
compat_str = unicode # Python 2
except NameError:
compat_str = str
try:
compat_basestring = basestring # Python 2
except NameError:
compat_basestring = str
try:
compat_chr = unichr # Python 2
except NameError:
compat_chr = chr
try:
from xml.etree.ElementTree import ParseError as compat_xml_parse_error
except ImportError: # Python 2.6
from xml.parsers.expat import ExpatError as compat_xml_parse_error
try:
from urllib.parse import parse_qs as compat_parse_qs
@ -117,7 +143,7 @@ except ImportError: # Python 2
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
qs, _coerce_result = qs, unicode
qs, _coerce_result = qs, compat_str
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
@ -156,21 +182,6 @@ except ImportError: # Python 2
parsed_result[name] = [value]
return parsed_result
try:
compat_str = unicode # Python 2
except NameError:
compat_str = str
try:
compat_chr = unichr # Python 2
except NameError:
compat_chr = chr
try:
from xml.etree.ElementTree import ParseError as compat_xml_parse_error
except ImportError: # Python 2.6
from xml.parsers.expat import ExpatError as compat_xml_parse_error
try:
from shlex import quote as shlex_quote
except ImportError: # Python < 3.3
@ -247,7 +258,7 @@ else:
userhome = compat_getenv('HOME')
elif 'USERPROFILE' in os.environ:
userhome = compat_getenv('USERPROFILE')
elif not 'HOMEPATH' in os.environ:
elif 'HOMEPATH' not in os.environ:
return path
else:
try:
@ -297,7 +308,9 @@ else:
# Old 2.6 and 2.7 releases require kwargs to be bytes
try:
(lambda x: x)(**{'x': 0})
def _testfunc(x):
pass
_testfunc(**{'x': 0})
except TypeError:
def compat_kwargs(kwargs):
return dict((bytes(k), v) for k, v in kwargs.items())
@ -305,6 +318,32 @@ else:
compat_kwargs = lambda kwargs: kwargs
if sys.version_info < (2, 7):
def compat_socket_create_connection(address, timeout, source_address=None):
host, port = address
err = None
for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
af, socktype, proto, canonname, sa = res
sock = None
try:
sock = socket.socket(af, socktype, proto)
sock.settimeout(timeout)
if source_address:
sock.bind(source_address)
sock.connect(sa)
return sock
except socket.error as _:
err = _
if sock is not None:
sock.close()
if err is not None:
raise err
else:
raise socket.error("getaddrinfo returns an empty list")
else:
compat_socket_create_connection = socket.create_connection
# Fix https://github.com/rg3/youtube-dl/issues/4223
# See http://bugs.python.org/issue9161 for what is broken
def workaround_optparse_bug9161():
@ -328,6 +367,7 @@ def workaround_optparse_bug9161():
__all__ = [
'compat_HTTPError',
'compat_basestring',
'compat_chr',
'compat_cookiejar',
'compat_expanduser',
@ -336,10 +376,12 @@ __all__ = [
'compat_html_entities',
'compat_html_parser',
'compat_http_client',
'compat_http_server',
'compat_kwargs',
'compat_ord',
'compat_parse_qs',
'compat_print',
'compat_socket_create_connection',
'compat_str',
'compat_subprocess_get_DEVNULL',
'compat_urllib_error',

View File

@ -1,35 +1,44 @@
from __future__ import unicode_literals
from .common import FileDownloader
from .external import get_external_downloader
from .f4m import F4mFD
from .hls import HlsFD
from .hls import NativeHlsFD
from .http import HttpFD
from .mplayer import MplayerFD
from .rtmp import RtmpFD
from .f4m import F4mFD
from ..utils import (
determine_ext,
determine_protocol,
)
PROTOCOL_MAP = {
'rtmp': RtmpFD,
'm3u8_native': NativeHlsFD,
'm3u8': HlsFD,
'mms': MplayerFD,
'rtsp': MplayerFD,
'f4m': F4mFD,
}
def get_suitable_downloader(info_dict):
def get_suitable_downloader(info_dict, params={}):
"""Get the downloader class that can handle the info dict."""
url = info_dict['url']
protocol = info_dict.get('protocol')
protocol = determine_protocol(info_dict)
info_dict['protocol'] = protocol
if url.startswith('rtmp'):
return RtmpFD
if protocol == 'm3u8_native':
external_downloader = params.get('external_downloader')
if external_downloader is not None:
ed = get_external_downloader(external_downloader)
if ed.supports(info_dict):
return ed
if protocol == 'm3u8' and params.get('hls_prefer_native'):
return NativeHlsFD
if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
return HlsFD
if url.startswith('mms') or url.startswith('rtsp'):
return MplayerFD
if determine_ext(url) == 'f4m':
return F4mFD
else:
return HttpFD
return PROTOCOL_MAP.get(protocol, HttpFD)
__all__ = [
'get_suitable_downloader',

View File

@ -1,12 +1,12 @@
from __future__ import unicode_literals
from __future__ import division, unicode_literals
import os
import re
import sys
import time
from ..compat import compat_str
from ..utils import (
compat_str,
encodeFilename,
format_bytes,
timeconvert,
@ -25,21 +25,23 @@ class FileDownloader(object):
Available options:
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
ratelimit: Download speed limit, in bytes/sec.
retries: Number of times to retry for HTTP error 5xx
buffersize: Size of download buffer in bytes.
noresizebuffer: Do not automatically resize the download buffer.
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
test: Download only first bytes to test the downloader.
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
ratelimit: Download speed limit, in bytes/sec.
retries: Number of times to retry for HTTP error 5xx
buffersize: Size of download buffer in bytes.
noresizebuffer: Do not automatically resize the download buffer.
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps.
test: Download only first bytes to test the downloader.
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
(experimenatal)
Subclasses of this one must re-define the real_download method.
"""
@ -52,6 +54,7 @@ class FileDownloader(object):
self.ydl = ydl
self._progress_hooks = []
self.params = params
self.add_progress_hook(self.report_progress)
@staticmethod
def format_seconds(seconds):
@ -80,6 +83,8 @@ class FileDownloader(object):
def calc_eta(start, now, total, current):
if total is None:
return None
if now is None:
now = time.time()
dif = now - start
if current == 0 or dif < 0.001: # One millisecond
return None
@ -146,18 +151,19 @@ class FileDownloader(object):
def report_error(self, *args, **kargs):
self.ydl.report_error(*args, **kargs)
def slow_down(self, start_time, byte_counter):
def slow_down(self, start_time, now, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None)
if rate_limit is None or byte_counter == 0:
return
now = time.time()
if now is None:
now = time.time()
elapsed = now - start_time
if elapsed <= 0.0:
return
speed = float(byte_counter) / elapsed
if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
time.sleep(max((byte_counter // rate_limit) - elapsed, 0))
def temp_name(self, filename):
"""Returns a temporary filename for the given filename."""
@ -221,42 +227,64 @@ class FileDownloader(object):
self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
self.to_console_title('youtube-dl ' + msg)
def report_progress(self, percent, data_len_str, speed, eta):
"""Report download progress."""
if self.params.get('noprogress', False):
def report_progress(self, s):
if s['status'] == 'finished':
if self.params.get('noprogress', False):
self.to_screen('[download] Download completed')
else:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
if s.get('elapsed') is not None:
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template = '100%% of %(_total_bytes_str)s in %(_elapsed_str)s'
else:
msg_template = '100%% of %(_total_bytes_str)s'
self._report_progress_status(
msg_template % s, is_last_line=True)
if self.params.get('noprogress'):
return
if eta is not None:
eta_str = self.format_eta(eta)
else:
eta_str = 'Unknown ETA'
if percent is not None:
percent_str = self.format_percent(percent)
else:
percent_str = 'Unknown %'
speed_str = self.format_speed(speed)
msg = ('%s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str))
self._report_progress_status(msg)
def report_progress_live_stream(self, downloaded_data_len, speed, elapsed):
if self.params.get('noprogress', False):
if s['status'] != 'downloading':
return
downloaded_str = format_bytes(downloaded_data_len)
speed_str = self.format_speed(speed)
elapsed_str = FileDownloader.format_seconds(elapsed)
msg = '%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
self._report_progress_status(msg)
def report_finish(self, data_len_str, tot_time):
"""Report download finished."""
if self.params.get('noprogress', False):
self.to_screen('[download] Download completed')
if s.get('eta') is not None:
s['_eta_str'] = self.format_eta(s['eta'])
else:
self._report_progress_status(
('100%% of %s in %s' %
(data_len_str, self.format_seconds(tot_time))),
is_last_line=True)
s['_eta_str'] = 'Unknown ETA'
if s.get('total_bytes') and s.get('downloaded_bytes') is not None:
s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes'])
elif s.get('total_bytes_estimate') and s.get('downloaded_bytes') is not None:
s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes_estimate'])
else:
if s.get('downloaded_bytes') == 0:
s['_percent_str'] = self.format_percent(0)
else:
s['_percent_str'] = 'Unknown %'
if s.get('speed') is not None:
s['_speed_str'] = self.format_speed(s['speed'])
else:
s['_speed_str'] = 'Unknown speed'
if s.get('total_bytes') is not None:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
msg_template = '%(_percent_str)s of %(_total_bytes_str)s at %(_speed_str)s ETA %(_eta_str)s'
elif s.get('total_bytes_estimate') is not None:
s['_total_bytes_estimate_str'] = format_bytes(s['total_bytes_estimate'])
msg_template = '%(_percent_str)s of ~%(_total_bytes_estimate_str)s at %(_speed_str)s ETA %(_eta_str)s'
else:
if s.get('downloaded_bytes') is not None:
s['_downloaded_bytes_str'] = format_bytes(s['downloaded_bytes'])
if s.get('elapsed'):
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s (%(_elapsed_str)s)'
else:
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s'
else:
msg_template = '%(_percent_str)s % at %(_speed_str)s ETA %(_eta_str)s'
self._report_progress_status(msg_template % s)
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
@ -281,8 +309,20 @@ class FileDownloader(object):
"""Download to a filename using the info from info_dict
Return True on success and False otherwise
"""
nooverwrites_and_exists = (
self.params.get('nooverwrites', False)
and os.path.exists(encodeFilename(filename))
)
continuedl_and_exists = (
self.params.get('continuedl', False)
and os.path.isfile(encodeFilename(filename))
and not self.params.get('nopart', False)
)
# Check file already present
if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False):
if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
self.report_file_already_downloaded(filename)
self._hook_progress({
'filename': filename,
@ -291,6 +331,11 @@ class FileDownloader(object):
})
return True
sleep_interval = self.params.get('sleep_interval')
if sleep_interval:
self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
time.sleep(sleep_interval)
return self.real_download(filename, info_dict)
def real_download(self, filename, info_dict):
@ -302,19 +347,27 @@ class FileDownloader(object):
ph(status)
def add_progress_hook(self, ph):
""" ph gets called on download progress, with a dictionary with the entries
* filename: The final filename
* status: One of "downloading" and "finished"
It can also have some of the following entries:
* downloaded_bytes: Bytes on disks
* total_bytes: Total bytes, None if unknown
* tmpfilename: The filename we're currently writing to
* eta: The estimated time in seconds, None if unknown
* speed: The download speed in bytes/second, None if unknown
Hooks are guaranteed to be called at least once (with status "finished")
if the download is successful.
"""
# See YoutubeDl.py (search for progress_hooks) for a description of
# this interface
self._progress_hooks.append(ph)
def _debug_cmd(self, args, subprocess_encoding, exe=None):
if not self.params.get('verbose', False):
return
if exe is None:
exe = os.path.basename(args[0])
if subprocess_encoding:
str_args = [
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
for a in args]
else:
str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
self.to_screen('[debug] %s command line: %s' % (
exe, shell_quote(str_args)))

View File

@ -0,0 +1,126 @@
from __future__ import unicode_literals
import os.path
import subprocess
import sys
from .common import FileDownloader
from ..utils import (
encodeFilename,
)
class ExternalFD(FileDownloader):
def real_download(self, filename, info_dict):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
retval = self._call_downloader(tmpfilename, info_dict)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
})
return True
else:
self.to_stderr('\n')
self.report_error('%s exited with code %d' % (
self.get_basename(), retval))
return False
@classmethod
def get_basename(cls):
return cls.__name__[:-2].lower()
@property
def exe(self):
return self.params.get('external_downloader')
@classmethod
def supports(cls, info_dict):
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
def _source_address(self, command_option):
source_address = self.params.get('source_address')
if source_address is None:
return []
return [command_option, source_address]
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
cmd = self._make_cmd(tmpfilename, info_dict)
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
# on Python 2.x
# See http://stackoverflow.com/a/9951851/35070
subprocess_encoding = sys.getfilesystemencoding()
cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
else:
subprocess_encoding = None
self._debug_cmd(cmd, subprocess_encoding)
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate()
if p.returncode != 0:
self.to_stderr(stderr)
return p.returncode
class CurlFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename]
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._source_address('--interface')
cmd += ['--', info_dict['url']]
return cmd
class WgetFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._source_address('--bind-address')
cmd += ['--', info_dict['url']]
return cmd
class Aria2cFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [
self.exe, '-c',
'--min-split-size', '1M', '--max-connection-per-server', '4']
dn = os.path.dirname(tmpfilename)
if dn:
cmd += ['--dir', dn]
cmd += ['--out', os.path.basename(tmpfilename)]
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._source_address('--interface')
cmd += ['--', info_dict['url']]
return cmd
_BY_NAME = dict(
(klass.get_basename(), klass)
for name, klass in globals().items()
if name.endswith('FD') and name != 'ExternalFD'
)
def list_external_downloaders():
return sorted(_BY_NAME.keys())
def get_external_downloader(external_downloader):
""" Given the name of the executable, see whether we support the given
downloader . """
bn = os.path.basename(external_downloader)
return _BY_NAME[bn]

View File

@ -1,4 +1,4 @@
from __future__ import unicode_literals
from __future__ import division, unicode_literals
import base64
import io
@ -9,11 +9,12 @@ import xml.etree.ElementTree as etree
from .common import FileDownloader
from .http import HttpFD
from ..compat import (
compat_urlparse,
)
from ..utils import (
struct_pack,
struct_unpack,
compat_urlparse,
format_bytes,
encodeFilename,
sanitize_open,
xpath_text,
@ -175,34 +176,43 @@ def build_fragments_list(boot_info):
""" Return a list of (segment, fragment) for each fragment in the video """
res = []
segment_run_table = boot_info['segments'][0]
# I've only found videos with one segment
segment_run_entry = segment_run_table['segment_run'][0]
n_frags = segment_run_entry[1]
fragment_run_entry_table = boot_info['fragments'][0]['fragments']
first_frag_number = fragment_run_entry_table[0]['first']
for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)):
res.append((1, frag_number))
fragments_counter = itertools.count(first_frag_number)
for segment, fragments_count in segment_run_table['segment_run']:
for _ in range(fragments_count):
res.append((segment, next(fragments_counter)))
return res
def write_flv_header(stream, metadata):
"""Writes the FLV header and the metadata to stream"""
def write_unsigned_int(stream, val):
stream.write(struct_pack('!I', val))
def write_unsigned_int_24(stream, val):
stream.write(struct_pack('!I', val)[1:])
def write_flv_header(stream):
"""Writes the FLV header to stream"""
# FLV header
stream.write(b'FLV\x01')
stream.write(b'\x05')
stream.write(b'\x00\x00\x00\x09')
# FLV File body
stream.write(b'\x00\x00\x00\x00')
# FLVTAG
# Script data
stream.write(b'\x12')
# Size of the metadata with 3 bytes
stream.write(struct_pack('!L', len(metadata))[1:])
stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
stream.write(metadata)
# Magic numbers extracted from the output files produced by AdobeHDS.php
#(https://github.com/K-S-V/Scripts)
stream.write(b'\x00\x00\x01\x73')
def write_metadata_tag(stream, metadata):
"""Writes optional metadata tag to stream"""
SCRIPT_TAG = b'\x12'
FLV_TAG_HEADER_LEN = 11
if metadata:
stream.write(SCRIPT_TAG)
write_unsigned_int_24(stream, len(metadata))
stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
stream.write(metadata)
write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
def _add_ns(prop):
@ -219,24 +229,32 @@ class F4mFD(FileDownloader):
A downloader for f4m manifests or AdobeHDS.
"""
def _get_unencrypted_media(self, doc):
media = doc.findall(_add_ns('media'))
if not media:
self.report_error('No media found')
for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:
self.report_error('Missing ID in f4m DRM')
media = list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
'drmAdditionalHeaderSetId' not in e.attrib,
media))
if not media:
self.report_error('Unsupported DRM')
return media
def real_download(self, filename, info_dict):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
self.to_screen('[download] Downloading f4m manifest')
manifest = self.ydl.urlopen(man_url).read()
self.report_destination(filename)
http_dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': True,
'quiet': True,
'noprogress': True,
'test': self.params.get('test', False),
}
)
doc = etree.fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
formats = [(int(f.attrib.get('bitrate', -1)), f)
for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None:
# get the best format
formats = sorted(formats, key=lambda f: f[0])
@ -253,7 +271,11 @@ class F4mFD(FileDownloader):
bootstrap = self.ydl.urlopen(bootstrap_url).read()
else:
bootstrap = base64.b64decode(bootstrap_node.text)
metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
metadata_node = media.find(_add_ns('metadata'))
if metadata_node is not None:
metadata = base64.b64decode(metadata_node.text)
else:
metadata = None
boot_info = read_bootstrap_info(bootstrap)
fragments_list = build_fragments_list(boot_info)
@ -264,38 +286,65 @@ class F4mFD(FileDownloader):
# For some akamai manifests we'll need to add a query to the fragment url
akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
self.report_destination(filename)
http_dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': True,
'quiet': True,
'noprogress': True,
'ratelimit': self.params.get('ratelimit', None),
'test': self.params.get('test', False),
}
)
tmpfilename = self.temp_name(filename)
(dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
write_flv_header(dest_stream, metadata)
write_flv_header(dest_stream)
write_metadata_tag(dest_stream, metadata)
# This dict stores the download progress, it's updated by the progress
# hook
state = {
'status': 'downloading',
'downloaded_bytes': 0,
'frag_counter': 0,
'frag_index': 0,
'frag_count': total_frags,
'filename': filename,
'tmpfilename': tmpfilename,
}
start = time.time()
def frag_progress_hook(status):
frag_total_bytes = status.get('total_bytes', 0)
estimated_size = (state['downloaded_bytes'] +
(total_frags - state['frag_counter']) * frag_total_bytes)
if status['status'] == 'finished':
def frag_progress_hook(s):
if s['status'] not in ('downloading', 'finished'):
return
frag_total_bytes = s.get('total_bytes', 0)
if s['status'] == 'finished':
state['downloaded_bytes'] += frag_total_bytes
state['frag_counter'] += 1
progress = self.calc_percent(state['frag_counter'], total_frags)
byte_counter = state['downloaded_bytes']
state['frag_index'] += 1
estimated_size = (
(state['downloaded_bytes'] + frag_total_bytes)
/ (state['frag_index'] + 1) * total_frags)
time_now = time.time()
state['total_bytes_estimate'] = estimated_size
state['elapsed'] = time_now - start
if s['status'] == 'finished':
progress = self.calc_percent(state['frag_index'], total_frags)
else:
frag_downloaded_bytes = status['downloaded_bytes']
byte_counter = state['downloaded_bytes'] + frag_downloaded_bytes
frag_downloaded_bytes = s['downloaded_bytes']
frag_progress = self.calc_percent(frag_downloaded_bytes,
frag_total_bytes)
progress = self.calc_percent(state['frag_counter'], total_frags)
progress = self.calc_percent(state['frag_index'], total_frags)
progress += frag_progress / float(total_frags)
eta = self.calc_eta(start, time.time(), estimated_size, byte_counter)
self.report_progress(progress, format_bytes(estimated_size),
status.get('speed'), eta)
state['eta'] = self.calc_eta(
start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
state['speed'] = s.get('speed')
self._hook_progress(state)
http_dl.add_progress_hook(frag_progress_hook)
frags_filenames = []
@ -319,8 +368,8 @@ class F4mFD(FileDownloader):
frags_filenames.append(frag_filename)
dest_stream.close()
self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
elapsed = time.time() - start
self.try_rename(tmpfilename, filename)
for frag_file in frags_filenames:
os.remove(frag_file)
@ -331,6 +380,7 @@ class F4mFD(FileDownloader):
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
'elapsed': elapsed,
})
return True

View File

@ -4,11 +4,14 @@ import os
import re
import subprocess
from ..postprocessor.ffmpeg import FFmpegPostProcessor
from .common import FileDownloader
from ..utils import (
from ..compat import (
compat_urlparse,
compat_urllib_request,
check_executable,
)
from ..utils import (
encodeArgument,
encodeFilename,
)
@ -19,23 +22,21 @@ class HlsFD(FileDownloader):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
args = [
'-y', '-i', url, '-f', 'mp4', '-c', 'copy',
'-bsf:a', 'aac_adtstoasc',
encodeFilename(tmpfilename, for_subprocess=True)]
for program in ['avconv', 'ffmpeg']:
if check_executable(program, ['-version']):
break
else:
ffpp = FFmpegPostProcessor(downloader=self)
if not ffpp.available:
self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
return False
cmd = [program] + args
ffpp.check_version()
retval = subprocess.call(cmd)
args = [
encodeArgument(opt)
for opt in (ffpp.executable, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
args.append(encodeFilename(tmpfilename, True))
retval = subprocess.call(args)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
@ -46,7 +47,7 @@ class HlsFD(FileDownloader):
return True
else:
self.to_stderr('\n')
self.report_error('%s exited with code %d' % (program, retval))
self.report_error('%s exited with code %d' % (ffpp.basename, retval))
return False

View File

@ -1,17 +1,19 @@
from __future__ import unicode_literals
import errno
import os
import socket
import time
from .common import FileDownloader
from ..utils import (
from ..compat import (
compat_urllib_request,
compat_urllib_error,
)
from ..utils import (
ContentTooShortError,
encodeFilename,
sanitize_open,
format_bytes,
)
@ -23,10 +25,6 @@ class HttpFD(FileDownloader):
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
if 'user_agent' in info_dict:
headers['Youtubedl-user-agent'] = info_dict['user_agent']
if 'http_referer' in info_dict:
headers['Referer'] = info_dict['http_referer']
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
@ -102,6 +100,11 @@ class HttpFD(FileDownloader):
resume_len = 0
open_mode = 'wb'
break
except socket.error as e:
if e.errno != errno.ECONNRESET:
# Connection reset is no problem, just retry
raise
# Retry
count += 1
if count <= retries:
@ -132,20 +135,24 @@ class HttpFD(FileDownloader):
self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False
data_len_str = format_bytes(data_len)
byte_counter = 0 + resume_len
block_size = self.params.get('buffersize', 1024)
start = time.time()
# measure time over whole while-loop, so slow_down() and best_block_size() work together properly
now = None # needed for slow_down() in the first loop run
before = start # start measuring
while True:
# Download and write
before = time.time()
data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
after = time.time()
if len(data_block) == 0:
break
byte_counter += len(data_block)
# Open file just in time
# exit loop when download is finished
if len(data_block) == 0:
break
# Open destination file just in time
if stream is None:
try:
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
@ -155,47 +162,68 @@ class HttpFD(FileDownloader):
except (OSError, IOError) as err:
self.report_error('unable to open for writing: %s' % str(err))
return False
if self.params.get('xattr_set_filesize', False) and data_len is not None:
try:
import xattr
xattr.setxattr(tmpfilename, 'user.ytdl.filesize', str(data_len))
except(OSError, IOError, ImportError) as err:
self.report_error('unable to set filesize xattr: %s' % str(err))
try:
stream.write(data_block)
except (IOError, OSError) as err:
self.to_stderr('\n')
self.report_error('unable to write data: %s' % str(err))
return False
# Apply rate limit
self.slow_down(start, now, byte_counter - resume_len)
# end measuring of one loop run
now = time.time()
after = now
# Adjust block size
if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block))
before = after
# Progress message
speed = self.calc_speed(start, time.time(), byte_counter - resume_len)
speed = self.calc_speed(start, now, byte_counter - resume_len)
if data_len is None:
eta = percent = None
eta = None
else:
percent = self.calc_percent(byte_counter, data_len)
eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
self.report_progress(percent, data_len_str, speed, eta)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': byte_counter,
'total_bytes': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'eta': eta,
'speed': speed,
'elapsed': now - start,
})
if is_test and byte_counter == data_len:
break
# Apply rate limit
self.slow_down(start, byte_counter - resume_len)
if stream is None:
self.to_stderr('\n')
self.report_error('Did not get any data blocks')
return False
if tmpfilename != '-':
stream.close()
self.report_finish(data_len_str, (time.time() - start))
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': data_len,
'tmpfilename': tmpfilename,
'status': 'error',
})
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, int(data_len))
self.try_rename(tmpfilename, filename)
@ -209,6 +237,7 @@ class HttpFD(FileDownloader):
'total_bytes': byte_counter,
'filename': filename,
'status': 'finished',
'elapsed': time.time() - start,
})
return True

View File

@ -4,8 +4,8 @@ import os
import subprocess
from .common import FileDownloader
from ..compat import compat_subprocess_get_DEVNULL
from ..utils import (
check_executable,
encodeFilename,
)
@ -20,11 +20,7 @@ class MplayerFD(FileDownloader):
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
'-dumpstream', '-dumpfile', tmpfilename, url]
# Check for mplayer first
try:
subprocess.call(
['mplayer', '-h'],
stdout=compat_subprocess_get_DEVNULL(), stderr=subprocess.STDOUT)
except (OSError, IOError):
if not check_executable('mplayer', ['-h']):
self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
return False

View File

@ -7,11 +7,10 @@ import sys
import time
from .common import FileDownloader
from ..compat import compat_str
from ..utils import (
check_executable,
compat_str,
encodeFilename,
format_bytes,
get_exe_version,
)
@ -51,23 +50,23 @@ class RtmpFD(FileDownloader):
if not resume_percent:
resume_percent = percent
resume_downloaded_data_len = downloaded_data_len
eta = self.calc_eta(start, time.time(), 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time.time(), downloaded_data_len - resume_downloaded_data_len)
time_now = time.time()
eta = self.calc_eta(start, time_now, 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time_now, downloaded_data_len - resume_downloaded_data_len)
data_len = None
if percent > 0:
data_len = int(downloaded_data_len * 100 / percent)
data_len_str = '~' + format_bytes(data_len)
self.report_progress(percent, data_len_str, speed, eta)
cursor_in_new_line = False
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': downloaded_data_len,
'total_bytes': data_len,
'total_bytes_estimate': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'eta': eta,
'elapsed': time_now - start,
'speed': speed,
})
cursor_in_new_line = False
else:
# no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
@ -75,15 +74,15 @@ class RtmpFD(FileDownloader):
downloaded_data_len = int(float(mobj.group(1)) * 1024)
time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len)
self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
cursor_in_new_line = False
self._hook_progress({
'downloaded_bytes': downloaded_data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'elapsed': time_now - start,
'speed': speed,
})
cursor_in_new_line = False
elif self.params.get('verbose', False):
if not cursor_in_new_line:
self.to_screen('')
@ -104,6 +103,9 @@ class RtmpFD(FileDownloader):
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn', None)
protocol = info_dict.get('rtmp_protocol', None)
real_time = info_dict.get('rtmp_real_time', False)
no_resume = info_dict.get('no_resume', False)
continue_dl = info_dict.get('continuedl', False)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
@ -141,7 +143,14 @@ class RtmpFD(FileDownloader):
basic_args += ['--conn', conn]
if protocol is not None:
basic_args += ['--protocol', protocol]
args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
if real_time:
basic_args += ['--realtime']
args = basic_args
if not no_resume and continue_dl and not live:
args += ['--resume']
if not live and continue_dl:
args += ['--skip', '1']
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
@ -152,19 +161,7 @@ class RtmpFD(FileDownloader):
else:
subprocess_encoding = None
if self.params.get('verbose', False):
if subprocess_encoding:
str_args = [
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
for a in args]
else:
str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
RD_SUCCESS = 0
RD_FAILED = 1
@ -185,7 +182,7 @@ class RtmpFD(FileDownloader):
cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED:
break
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
retval = RD_SUCCESS

View File

@ -1,10 +1,15 @@
from __future__ import unicode_literals
from .abc import ABCIE
from .abc7news import Abc7NewsIE
from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
from .adobetv import AdobeTVIE
from .adultswim import AdultSwimIE
from .aftenposten import AftenpostenIE
from .aftonbladet import AftonbladetIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .anitube import AnitubeIE
from .anysex import AnySexIE
from .aol import AolIE
@ -22,13 +27,16 @@ from .arte import (
ArteTVDDCIE,
ArteTVEmbedIE,
)
from .audiomack import AudiomackIE
from .auengine import AUEngineIE
from .atresplayer import AtresPlayerIE
from .atttechchannel import ATTTechChannelIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .azubu import AzubuIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbccouk import BBCCoUkIE
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bet import BetIE
from .bild import BildIE
from .bilibili import BiliBiliIE
from .blinkx import BlinkxIE
@ -41,15 +49,21 @@ from .brightcove import BrightcoveIE
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE
from .c56 import C56IE
from .camdemy import (
CamdemyIE,
CamdemyFolderIE
)
from .canal13cl import Canal13clIE
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
from .cbs import CBSIE
from .cbsnews import CBSNewsIE
from .cbssports import CBSSportsIE
from .ccc import CCCIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .chilloutzone import ChilloutzoneIE
from .cinemassacre import CinemassacreIE
from .cinchcast import CinchcastIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
@ -60,9 +74,13 @@ from .cnet import CNETIE
from .cnn import (
CNNIE,
CNNBlogsIE,
CNNArticleIE,
)
from .collegehumor import CollegeHumorIE
from .collegerama import CollegeRamaIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE
@ -71,6 +89,7 @@ from .crunchyroll import (
CrunchyrollShowPlaylistIE
)
from .cspan import CSpanIE
from .ctsnews import CtsNewsIE
from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
@ -78,18 +97,22 @@ from .dailymotion import (
)
from .daum import DaumIE
from .dbtv import DBTVIE
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .dfb import DFBIE
from .dotsub import DotsubIE
from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE
from .drtv import DRTVIE
from .dvtv import DVTVIE
from .dump import DumpIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .divxstage import DivxStageIE
from .dropbox import DropboxIE
from .ebaumsworld import EbaumsWorldIE
from .echomsk import EchoMskIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
@ -99,9 +122,11 @@ from .ellentv import (
EllenTVClipsIE,
)
from .elpais import ElPaisIE
from .embedly import EmbedlyIE
from .empflix import EMPFlixIE
from .engadget import EngadgetIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
@ -121,6 +146,8 @@ from .fktv import (
from .flickr import FlickrIE
from .folketinget import FolketingetIE
from .fourtube import FourTubeIE
from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE
from .francetv import (
@ -144,6 +171,8 @@ from .gamestar import GameStarIE
from .gametrailers import GametrailersIE
from .gdcvault import GDCVaultIE
from .generic import GenericIE
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
from .globo import GloboIE
from .godtube import GodTubeIE
@ -154,10 +183,16 @@ from .googlesearch import GoogleSearchIE
from .gorillavid import GorillaVidIE
from .goshgay import GoshgayIE
from .grooveshark import GroovesharkIE
from .groupon import GrouponIE
from .hark import HarkIE
from .hearthisat import HearThisAtIE
from .heise import HeiseIE
from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
from .historicfilms import HistoricFilmsIE
from .history import HistoryIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hornbunny import HornBunnyIE
from .hostingbulk import HostingBulkIE
from .hotnewhiphop import HotNewHipHopIE
@ -171,6 +206,7 @@ from .imdb import (
ImdbIE,
ImdbListIE
)
from .imgur import ImgurIE
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE, InstagramUserIE
@ -187,6 +223,7 @@ from .jove import JoveIE
from .jukebox import JukeboxIE
from .jpopsukitv import JpopsukiIE
from .kankan import KankanIE
from .karaoketv import KaraoketvIE
from .keezmovies import KeezMoviesIE
from .khanacademy import KhanAcademyIE
from .kickstarter import KickStarterIE
@ -203,6 +240,7 @@ from .livestream import (
LivestreamOriginalIE,
LivestreamShortenerIE,
)
from .lnkgo import LnkGoIE
from .lrt import LRTIE
from .lynda import (
LyndaIE,
@ -216,6 +254,7 @@ from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mgoon import MgoonIE
from .minhateca import MinhatecaIE
from .ministrygrid import MinistryGridIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mitele import MiTeleIE
@ -242,9 +281,11 @@ from .muenchentv import MuenchenTVIE
from .musicplayon import MusicPlayOnIE
from .musicvault import MusicVaultIE
from .muzu import MuzuTVIE
from .myspace import MySpaceIE
from .myspace import MySpaceIE, MySpaceAlbumIE
from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .myvidster import MyVidsterIE
from .nationalgeographic import NationalGeographicIE
from .naver import NaverIE
from .nba import NBAIE
from .nbc import (
@ -253,11 +294,24 @@ from .nbc import (
)
from .ndr import NDRIE
from .ndtv import NDTVIE
from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
from .nerdist import NerdistIE
from .newgrounds import NewgroundsIE
from .newstube import NewstubeIE
from .nextmedia import (
NextMediaIE,
NextMediaActionNewsIE,
AppleDailyRealtimeNewsIE,
AppleDailyAnimationNewsIE
)
from .nfb import NFBIE
from .nfl import NFLIE
from .nhl import NHLIE, NHLVideocenterIE
from .nhl import (
NHLIE,
NHLNewsIE,
NHLVideocenterIE,
)
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninegag import NineGagIE
from .noco import NocoIE
@ -268,17 +322,22 @@ from .nowness import NownessIE
from .nowvideo import NowVideoIE
from .npo import (
NPOIE,
NPOLiveIE,
NPORadioIE,
NPORadioFragmentIE,
TegenlichtVproIE,
)
from .nrk import (
NRKIE,
NRKTVIE,
)
from .ntv import NTVIE
from .ntvde import NTVDeIE
from .ntvru import NTVRuIE
from .nytimes import NYTimesIE
from .nuvid import NuvidIE
from .oktoberfesttv import OktoberfestTVIE
from .ooyala import OoyalaIE
from .openfilm import OpenFilmIE
from .orf import (
ORFTVthekIE,
ORFOE1IE,
@ -295,40 +354,53 @@ from .playfm import PlayFMIE
from .playvid import PlayvidIE
from .podomatic import PodomaticIE
from .pornhd import PornHdIE
from .pornhub import PornHubIE
from .pornhub import (
PornHubIE,
PornHubPlaylistIE,
)
from .pornotube import PornotubeIE
from .pornoxo import PornoXOIE
from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE
from .quickvid import QuickVidIE
from .radiode import RadioDeIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .restudy import RestudyIE
from .reverbnation import ReverbNationIE
from .ringtv import RingTVIE
from .ro220 import Ro220IE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rtbf import RTBFIE
from .rtlnl import RtlXlIE
from .rte import RteIE
from .rtlnl import RtlNlIE
from .rtlnow import RTLnowIE
from .rtl2 import RTL2IE
from .rtp import RTPIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE
from .ruhd import RUHDIE
from .rutube import (
RutubeIE,
RutubeChannelIE,
RutubeEmbedIE,
RutubeMovieIE,
RutubePersonIE,
)
from .rutv import RUTVIE
from .sandia import SandiaIE
from .sapo import SapoIE
from .savefrom import SaveFromIE
from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
from .servingsys import ServingSysIE
from .sexu import SexuIE
from .sexykarma import SexyKarmaIE
@ -370,7 +442,9 @@ from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE
from .sunporno import SunPornoIE
from .svtplay import SVTPlayIE
from .swrmediathek import SWRMediathekIE
from .syfy import SyfyIE
from .sztvhu import SztvHuIE
@ -388,8 +462,10 @@ from .ted import TEDIE
from .telebruxelles import TeleBruxellesIE
from .telecinco import TelecincoIE
from .telemb import TeleMBIE
from .teletask import TeleTaskIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE
from .testtube import TestTubeIE
from .tf1 import TF1IE
from .theonion import TheOnionIE
from .theplatform import ThePlatformIE
@ -414,10 +490,21 @@ from .tumblr import TumblrIE
from .tunein import TuneInIE
from .turbo import TurboIE
from .tutv import TutvIE
from .tv4 import TV4IE
from .tvigle import TvigleIE
from .tvp import TvpIE
from .tvp import TvpIE, TvpSeriesIE
from .tvplay import TVPlayIE
from .twitch import TwitchIE
from .tweakers import TweakersIE
from .twentyfourvideo import TwentyFourVideoIE
from .twitch import (
TwitchVideoIE,
TwitchChapterIE,
TwitchVodIE,
TwitchProfileIE,
TwitchPastBroadcastsIE,
TwitchBookmarksIE,
TwitchStreamIE,
)
from .ubu import UbuIE
from .udemy import (
UdemyIE,
@ -445,6 +532,7 @@ from .videott import VideoTtIE
from .videoweed import VideoWeedIE
from .vidme import VidmeIE
from .vidzi import VidziIE
from .vier import VierIE, VierVideosIE
from .vimeo import (
VimeoIE,
VimeoAlbumIE,
@ -480,11 +568,13 @@ from .wdr import (
WDRMobileIE,
WDRMausIE,
)
from .webofstories import WebOfStoriesIE
from .weibo import WeiboIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
from .wrzuta import WrzutaIE
from .wsj import WSJIE
from .xbef import XBefIE
from .xboxclips import XboxClipsIE
from .xhamster import XHamsterIE
@ -492,10 +582,14 @@ from .xminus import XMinusIE
from .xnxx import XNXXIE
from .xvideos import XVideosIE
from .xtube import XTubeUserIE, XTubeIE
from .xuite import XuiteIE
from .xxxymovies import XXXYMoviesIE
from .yahoo import (
YahooIE,
YahooSearchIE,
)
from .yam import YamIE
from .yesjapan import YesJapanIE
from .ynet import YnetIE
from .youjizz import YouJizzIE
from .youku import YoukuIE
@ -513,12 +607,12 @@ from .youtube import (
YoutubeSearchURLIE,
YoutubeShowIE,
YoutubeSubscriptionsIE,
YoutubeTopListIE,
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
YoutubeUserIE,
YoutubeWatchLaterIE,
)
from .zdf import ZDFIE
from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import (
ZingMp3SongIE,
ZingMp3AlbumIE,
@ -539,6 +633,17 @@ def gen_extractors():
return [klass() for klass in _ALL_CLASSES]
def list_extractors(age_limit):
"""
Return a list of extractors that are suitable for the given age,
sorted by extractor ID.
"""
return sorted(
filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()),
key=lambda ie: ie.IE_NAME.lower())
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""
return globals()[ie_name + 'IE']

View File

@ -0,0 +1,68 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_iso8601
class Abc7NewsIE(InfoExtractor):
_VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
'info_dict': {
'id': '472581',
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
'ext': 'mp4',
'title': 'East Bay museum celebrates history of synthesized music',
'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1421123075,
'upload_date': '20150113',
'uploader': 'Jonathan Bloom',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://abc7news.com/472581',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
m3u8 = self._html_search_meta(
'contentURL', webpage, 'm3u8 url', fatal=True)
formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
self._sort_formats(formats)
title = self._og_search_title(webpage).strip()
description = self._og_search_description(webpage).strip()
thumbnail = self._og_search_thumbnail(webpage)
timestamp = parse_iso8601(self._search_regex(
r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
webpage, 'upload date', fatal=False))
uploader = self._search_regex(
r'rel="author">([^<]+)</a>',
webpage, 'uploader', default=None)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'formats': formats,
}

View File

@ -0,0 +1,70 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_duration,
unified_strdate,
str_to_int,
)
class AdobeTVIE(InfoExtractor):
_VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
'info_dict': {
'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
'ext': 'mp4',
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
'thumbnail': 're:https?://.*\.jpg$',
'upload_date': '20110914',
'duration': 60,
'view_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player = self._parse_json(
self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
video_id)
title = player.get('title') or self._search_regex(
r'data-title="([^"]+)"', webpage, 'title')
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(
self._html_search_meta('datepublished', webpage, 'upload date'))
duration = parse_duration(
self._html_search_meta('duration', webpage, 'duration')
or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration'))
view_count = str_to_int(self._search_regex(
r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
webpage, 'view count'))
formats = [{
'url': source['src'],
'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
'tbr': source.get('bitrate'),
} for source in player['sources']]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
'formats': formats,
}

View File

@ -2,123 +2,152 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
xpath_text,
float_or_none,
)
class AdultSwimIE(InfoExtractor):
_VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$'
_TEST = {
'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title',
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
_TESTS = [{
'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
'playlist': [
{
'md5': '4da359ec73b58df4575cd01a610ba5dc',
'md5': '247572debc75c7652f253c8daa51a14d',
'info_dict': {
'id': '8a250ba1450996e901453d7f02ca02f5',
'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
'title': 'Rick and Morty - Pilot Part 1',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
{
'md5': 'ffbdf55af9331c509d95350bd0cc1819',
'md5': '77b0e037a4b20ec6b98671c4c379f48d',
'info_dict': {
'id': '8a250ba1450996e901453d7f4bd102f6',
'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
'title': 'Rick and Morty - Pilot Part 4',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
],
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'title': 'Rick and Morty - Pilot',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
}
}, {
'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
'playlist': [
{
'md5': 'b92409635540304280b4b6c36bd14a0a',
'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
'info_dict': {
'id': '8a250ba1450996e901453d7fa73c02f7',
'id': '-t8CamQlQ2aYZ49ItZCFog-0',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
},
{
'md5': 'e8818891d60e47b29cd89d7b0278156d',
'info_dict': {
'id': '8a250ba1450996e901453d7fc8ba02f8',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}
]
}
],
'info_dict': {
'id': '-t8CamQlQ2aYZ49ItZCFog',
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}]
_video_extensions = {
'3500': 'flv',
'640': 'mp4',
'150': 'mp4',
'ipad': 'm3u8',
'iphone': 'm3u8'
}
_video_dimensions = {
'3500': (1280, 720),
'640': (480, 270),
'150': (320, 180)
}
@staticmethod
def find_video_info(collection, slug):
for video in collection.get('videos'):
if video.get('slug') == slug:
return video
@staticmethod
def find_collection_by_linkURL(collections, linkURL):
for collection in collections:
if collection.get('linkURL') == linkURL:
return collection
@staticmethod
def find_collection_containing_video(collections, slug):
for collection in collections:
for video in collection.get('videos'):
if video.get('slug') == slug:
return collection, video
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_path = mobj.group('path')
show_path = mobj.group('show_path')
episode_path = mobj.group('episode_path')
is_playlist = True if mobj.group('is_playlist') else False
webpage = self._download_webpage(url, video_path)
episode_id = self._html_search_regex(
r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>',
webpage, 'episode_id')
title = self._og_search_title(webpage)
webpage = self._download_webpage(url, episode_path)
index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id
idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index')
# Extract the value of `bootstrappedData` from the Javascript in the page.
bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
episode_el = idoc.find('.//episode')
show_title = episode_el.attrib.get('collectionTitle')
episode_title = episode_el.attrib.get('title')
thumbnail = episode_el.attrib.get('thumbnailUrl')
description = episode_el.find('./description').text.strip()
try:
bootstrappedData = json.loads(bootstrappedDataJS)
except ValueError as ve:
errmsg = '%s: Failed to parse JSON ' % episode_path
raise ExtractorError(errmsg, cause=ve)
# Downloading videos from a /videos/playlist/ URL needs to be handled differently.
# NOTE: We are only downloading one video (the current one) not the playlist
if is_playlist:
collections = bootstrappedData['playlists']['collections']
collection = self.find_collection_by_linkURL(collections, show_path)
video_info = self.find_video_info(collection, episode_path)
show_title = video_info['showTitle']
segment_ids = [video_info['videoPlaybackID']]
else:
collections = bootstrappedData['show']['collections']
collection, video_info = self.find_collection_containing_video(collections, episode_path)
show = bootstrappedData['show']
show_title = show['title']
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
episode_id = video_info['id']
episode_title = video_info['title']
episode_description = video_info['description']
episode_duration = video_info.get('duration')
entries = []
segment_els = episode_el.findall('./segments/segment')
for part_num, segment_id in enumerate(segment_ids):
segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
for part_num, segment_el in enumerate(segment_els):
segment_id = segment_el.attrib.get('id')
segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1)
thumbnail = segment_el.attrib.get('thumbnailUrl')
duration = segment_el.attrib.get('duration')
segment_title = '%s - %s' % (show_title, episode_title)
if len(segment_ids) > 1:
segment_title += ' Part %d' % (part_num + 1)
segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
idoc = self._download_xml(
segment_url, segment_title,
'Downloading segment information', 'Unable to download segment information')
segment_duration = float_or_none(
xpath_text(idoc, './/trt', 'segment duration').strip())
formats = []
file_els = idoc.findall('.//files/file')
for file_el in file_els:
bitrate = file_el.attrib.get('bitrate')
type = file_el.attrib.get('type')
width, height = self._video_dimensions.get(bitrate, (None, None))
ftype = file_el.attrib.get('type')
formats.append({
'format_id': '%s-%s' % (bitrate, type),
'url': file_el.text,
'ext': self._video_extensions.get(bitrate, 'mp4'),
'format_id': '%s_%s' % (bitrate, ftype),
'url': file_el.text.strip(),
# The bitrate may not be a number (for example: 'iphone')
'tbr': int(bitrate) if bitrate.isdigit() else None,
'height': height,
'width': width
'quality': 1 if ftype == 'hd' else -1
})
self._sort_formats(formats)
@ -127,18 +156,16 @@ class AdultSwimIE(InfoExtractor):
'id': segment_id,
'title': segment_title,
'formats': formats,
'uploader': show_title,
'thumbnail': thumbnail,
'duration': duration,
'description': description
'duration': segment_duration,
'description': episode_description
})
return {
'_type': 'playlist',
'id': episode_id,
'display_id': video_path,
'display_id': episode_path,
'entries': entries,
'title': '%s %s' % (show_title, episode_title),
'description': description,
'thumbnail': thumbnail
'title': '%s - %s' % (show_title, episode_title),
'description': episode_description,
'duration': episode_duration
}

View File

@ -0,0 +1,103 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
xpath_with_ns,
xpath_text,
find_xpath_attr,
)
class AftenpostenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html'
_TEST = {
'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=&section=webtv_serierogprogrammer_sweatshop_sweatshopenglish',
'md5': 'fd828cd29774a729bf4d4425fe192972',
'info_dict': {
'id': '21039',
'ext': 'mov',
'title': 'TRAILER: "Sweatshop" - I can´t take any more',
'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
'timestamp': 1416927969,
'upload_date': '20141125',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'data-xs-id="(\d+)"', webpage, 'video id')
data = self._download_xml(
'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)
NS_MAP = {
'atom': 'http://www.w3.org/2005/Atom',
'xt': 'http://xstream.dk/',
'media': 'http://search.yahoo.com/mrss/',
}
entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
title = xpath_text(
entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
description = xpath_text(
entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
timestamp = parse_iso8601(xpath_text(
entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
formats = []
media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
media_url = media_content.get('url')
if not media_url:
continue
tbr = int_or_none(media_content.get('bitrate'))
mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
if mobj:
formats.append({
'url': mobj.group('url'),
'play_path': 'mp4:%s' % mobj.group('playpath'),
'app': mobj.group('app'),
'ext': 'flv',
'tbr': tbr,
'format_id': 'rtmp-%d' % tbr,
})
else:
formats.append({
'url': media_url,
'tbr': tbr,
})
self._sort_formats(formats)
link = find_xpath_attr(
entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
if link is not None:
formats.append({
'url': link.get('href'),
'format_id': link.get('rel'),
})
thumbnails = [{
'url': splash.get('url'),
'width': int_or_none(splash.get('width')),
'height': int_or_none(splash.get('height')),
} for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'formats': formats,
'thumbnails': thumbnails,
}

View File

@ -1,8 +1,6 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
@ -21,9 +19,7 @@ class AftonbladetIE(InfoExtractor):
}
def _real_extract(self, url):
mobj = re.search(self._VALID_URL, url)
video_id = mobj.group('video_id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# find internal video meta data

View File

@ -0,0 +1,35 @@
from __future__ import unicode_literals
from .common import InfoExtractor
class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
_TEST = {
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
'info_dict': {
'id': '3792260579001',
'ext': 'mp4',
'title': 'The Slum - Episode 1: Deliverance',
'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
'uploader': 'Al Jazeera English',
},
'add_ie': ['Brightcove'],
}
def _real_extract(self, url):
program_name = self._match_id(url)
webpage = self._download_webpage(url, program_name)
brightcove_id = self._search_regex(
r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
return {
'_type': 'url',
'url': (
'brightcove:'
'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
'&%40videoPlayer={0}'.format(brightcove_id)
),
'ie_key': 'Brightcove',
}

View File

@ -5,15 +5,14 @@ import re
import json
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
compat_str,
qualities,
determine_ext,
)
class AllocineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?'
_VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
_TESTS = [{
'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
@ -45,6 +44,9 @@ class AllocineIE(InfoExtractor):
'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://www.allocine.fr/video/video-19550147/',
'only_matching': True,
}]
def _real_extract(self, url):
@ -75,9 +77,7 @@ class AllocineIE(InfoExtractor):
'format_id': format_id,
'quality': quality(format_id),
'url': v,
'ext': determine_ext(v),
})
self._sort_formats(formats)
return {

View File

@ -0,0 +1,77 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
parse_duration,
parse_filesize,
int_or_none,
)
class AlphaPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
'info_dict': {
'id': '258807',
'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
'ext': 'mp4',
'title': 'Sensual striptease porn with Samantha Alexandra',
'thumbnail': 're:https?://.*\.jpg$',
'timestamp': 1418694611,
'upload_date': '20141216',
'duration': 387,
'filesize_approx': 54120000,
'tbr': 1145,
'categories': list,
'age_limit': 18,
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
video_url = self._search_regex(
r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
ext = self._html_search_meta(
'encodingFormat', webpage, 'ext', default='.mp4')[1:]
title = self._search_regex(
[r'<meta content="([^"]+)" itemprop="description">',
r'class="title" itemprop="name">([^<]+)<'],
webpage, 'title')
thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date'))
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration'))
filesize_approx = parse_filesize(self._html_search_meta(
'contentSize', webpage, 'file size'))
bitrate = int_or_none(self._html_search_meta(
'bitrate', webpage, 'bitrate'))
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'filesize_approx': filesize_approx,
'tbr': bitrate,
'categories': categories,
'age_limit': age_limit,
}

View File

@ -3,7 +3,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .fivemin import FiveMinIE
class AolIE(InfoExtractor):
@ -42,31 +41,30 @@ class AolIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
playlist_id = mobj.group('playlist_id')
if playlist_id and not self._downloader.params.get('noplaylist'):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
if not playlist_id or self._downloader.params.get('noplaylist'):
return self.url_result('5min:%s' % video_id)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
playlist_html = self._search_regex(
r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
'playlist HTML')
entries = [{
'_type': 'url',
'url': 'aol-video:%s' % m.group('id'),
'ie_key': 'Aol',
} for m in re.finditer(
r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
playlist_html)]
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
return {
'_type': 'playlist',
'id': playlist_id,
'display_id': mobj.group('playlist_display_id'),
'title': title,
'entries': entries,
}
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(
r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
playlist_html = self._search_regex(
r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
'playlist HTML')
entries = [{
'_type': 'url',
'url': 'aol-video:%s' % m.group('id'),
'ie_key': 'Aol',
} for m in re.finditer(
r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
playlist_html)]
return FiveMinIE._build_result(video_id)
return {
'_type': 'playlist',
'id': playlist_id,
'display_id': mobj.group('playlist_display_id'),
'title': title,
'entries': entries,
}

View File

@ -20,6 +20,7 @@ class AparatIE(InfoExtractor):
'id': 'wP8On',
'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
'age_limit': 0,
},
# 'skip': 'Extremely unreliable',
}
@ -34,7 +35,8 @@ class AparatIE(InfoExtractor):
video_id + '/vt/frame')
webpage = self._download_webpage(embed_url, video_id)
video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
for i, video_url in enumerate(video_urls):
req = HEADRequest(video_url)
res = self._request_webpage(
@ -46,7 +48,7 @@ class AparatIE(InfoExtractor):
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
thumbnail = self._search_regex(
r'\s+image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
@ -54,4 +56,5 @@ class AparatIE(InfoExtractor):
'url': video_url,
'ext': 'mp4',
'thumbnail': thumbnail,
'age_limit': self._family_friendly_search(webpage),
}

View File

@ -4,8 +4,8 @@ import re
import json
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
compat_urlparse,
int_or_none,
)
@ -14,6 +14,9 @@ class AppleTrailersIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TEST = {
"url": "http://trailers.apple.com/trailers/wb/manofsteel/",
'info_dict': {
'id': 'manofsteel',
},
"playlist": [
{
"md5": "d97a8e575432dbcb81b7c3acb741f8a8",
@ -122,14 +125,15 @@ class AppleTrailersIE(InfoExtractor):
playlist.append({
'_type': 'video',
'id': video_id,
'title': title,
'formats': formats,
'title': title,
'duration': duration,
'thumbnail': thumbnail,
'upload_date': upload_date,
'uploader_id': uploader_id,
'user_agent': 'QuickTime compatible (youtube-dl)',
'http_headers': {
'User-Agent': 'QuickTime compatible (youtube-dl)',
},
})
return {

View File

@ -1,42 +1,48 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate,
)
from ..utils import unified_strdate
class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
_VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TEST = {
"url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect",
'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
_VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TESTS = [{
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': {
"title": "1968 Demo - FJCC Conference Presentation Reel #1",
"description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>",
"upload_date": "19681210",
"uploader": "SRI International"
'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'ext': 'ogv',
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
'description': 'md5:1780b464abaca9991d8968c877bb53ed',
'upload_date': '19681210',
'uploader': 'SRI International'
}
}
}, {
'url': 'https://archive.org/details/Cops1922',
'md5': '18f2a19e6d89af8425671da1cf3d4e04',
'info_dict': {
'id': 'Cops1922',
'ext': 'ogv',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:70f72ee70882f713d4578725461ffcc3',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
json_url = url + ('?' if '?' in url else '&') + 'output=json'
json_data = self._download_webpage(json_url, video_id)
data = json.loads(json_data)
data = self._download_json(json_url, video_id)
title = data['metadata']['title'][0]
description = data['metadata']['description'][0]
uploader = data['metadata']['creator'][0]
upload_date = unified_strdate(data['metadata']['date'][0])
def get_optional(data_dict, field):
return data_dict['metadata'].get(field, [None])[0]
title = get_optional(data, 'title')
description = get_optional(data, 'description')
uploader = get_optional(data, 'creator')
upload_date = unified_strdate(get_optional(data, 'date'))
formats = [
{

View File

@ -23,13 +23,7 @@ class ARDMediathekIE(InfoExtractor):
_TESTS = [{
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'file': '22429276.mp4',
'md5': '469751912f1de0816a9fc9df8336476c',
'info_dict': {
'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
},
'skip': 'Blocked outside of Germany',
'only_matching': True,
}, {
'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
'info_dict': {

View File

@ -37,7 +37,7 @@ class ArteTvIE(InfoExtractor):
config_xml_url, video_id, note='Downloading configuration')
formats = [{
'forma_id': q.attrib['quality'],
'format_id': q.attrib['quality'],
# The playpath starts at 'mp4:', if we don't manually
# split the url, rtmpdump will incorrectly parse them
'url': q.text.split('mp4:', 1)[0],
@ -133,7 +133,7 @@ class ArteTVPlus7IE(InfoExtractor):
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'tbr': int_or_none(f.get('bitrate')),
'quality': qfunc(f['quality']),
'quality': qfunc(f.get('quality')),
'source_preference': source_pref,
}

View File

@ -0,0 +1,163 @@
from __future__ import unicode_literals
import time
import hmac
from .subtitles import SubtitlesInfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
int_or_none,
float_or_none,
xpath_text,
ExtractorError,
)
class AtresPlayerIE(SubtitlesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
_TESTS = [
{
'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
'md5': 'efd56753cda1bb64df52a3074f62e38a',
'info_dict': {
'id': 'capitulo-10-especial-solidario-nochebuena',
'ext': 'mp4',
'title': 'Especial Solidario de Nochebuena',
'description': 'md5:e2d52ff12214fa937107d21064075bf1',
'duration': 5527.6,
'thumbnail': 're:^https?://.*\.jpg$',
},
},
{
'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
'only_matching': True,
},
]
_USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
_MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
_TIMESTAMP_SHIFT = 30000
_TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
_URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
_PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
_EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
_LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
def _real_initialize(self):
self._login()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_form = {
'j_username': username,
'j_password': password,
}
request = compat_urllib_request.Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
error = self._html_search_regex(
r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
episode_id = self._search_regex(
r'episode="([^"]+)"', webpage, 'episode id')
timestamp = int_or_none(self._download_webpage(
self._TIME_API_URL,
video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
token = hmac.new(
self._MAGIC.encode('ascii'),
(episode_id + timestamp_shifted).encode('utf-8')
).hexdigest()
formats = []
for fmt in ['windows', 'android_tablet']:
request = compat_urllib_request.Request(
self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
request.add_header('User-Agent', self._USER_AGENT)
fmt_json = self._download_json(
request, video_id, 'Downloading %s video JSON' % fmt)
result = fmt_json.get('resultDes')
if result.lower() != 'ok':
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, result), expected=True)
for format_id, video_url in fmt_json['resultObject'].items():
if format_id == 'token' or not video_url.startswith('http'):
continue
if video_url.endswith('/Manifest'):
if 'geodeswowsmpra3player' in video_url:
f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
# this videos are protected by DRM, the f4m downloader doesn't support them
continue
else:
f4m_url = video_url[:-9] + '/manifest.f4m'
formats.extend(self._extract_f4m_formats(f4m_url, video_id))
else:
formats.append({
'url': video_url,
'format_id': 'android-%s' % format_id,
'preference': 1,
})
self._sort_formats(formats)
player = self._download_json(
self._PLAYER_URL_TEMPLATE % episode_id,
episode_id)
path_data = player.get('pathData')
episode = self._download_xml(
self._EPISODE_URL_TEMPLATE % path_data,
video_id, 'Downloading episode XML')
duration = float_or_none(xpath_text(
episode, './media/asset/info/technical/contentDuration', 'duration'))
art = episode.find('./media/asset/info/art')
title = xpath_text(art, './name', 'title')
description = xpath_text(art, './description', 'description')
thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
subtitles = {}
subtitle = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
if subtitle:
subtitles['es'] = subtitle
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id, subtitles)
return
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': self.extract_subtitles(video_id, subtitles),
}

View File

@ -0,0 +1,55 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_strdate
class ATTTechChannelIE(InfoExtractor):
_VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
_TEST = {
'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'info_dict': {
'id': '11316',
'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'ext': 'flv',
'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140127',
},
'params': {
# rtmp download
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r"url\s*:\s*'(rtmp://[^']+)'",
webpage, 'video URL')
video_id = self._search_regex(
r'mediaid\s*=\s*(\d+)',
webpage, 'video id', fatal=False)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
webpage, 'upload date', fatal=False), False)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': 'flv',
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
}

View File

@ -1,11 +1,15 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
import time
from .common import InfoExtractor
from .soundcloud import SoundcloudIE
from ..utils import ExtractorError
import time
from ..utils import (
ExtractorError,
url_basename,
)
class AudiomackIE(InfoExtractor):
@ -17,53 +21,124 @@ class AudiomackIE(InfoExtractor):
'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
'info_dict':
{
'id': 'roosh-williams/extraordinary',
'id': '310086',
'ext': 'mp3',
'title': 'Roosh Williams - Extraordinary'
'uploader': 'Roosh Williams',
'title': 'Extraordinary'
}
},
# hosted on soundcloud via audiomack
# audiomack wrapper around soundcloud song
{
'add_ie': ['Soundcloud'],
'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
'file': '172419696.mp3',
'info_dict': {
'id': '172419696',
'ext': 'mp3',
'description': 'md5:1fc3272ed7a635cce5be1568c2822997',
'title': 'Young Thug ft Lil Wayne - Take Kare',
'uploader': 'Young Thug World',
'upload_date': '20141016',
}
},
]
def _real_extract(self, url):
# URLs end with [uploader name]/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url)
# Request the extended version of the api for extra fields like artist and title
api_response = self._download_json(
'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
album_url_tag, time.time()),
album_url_tag)
# API is inconsistent with errors
if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
raise ExtractorError('Invalid url %s', url)
# Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# if so, pass the work off to the soundcloud extractor
if SoundcloudIE.suitable(api_response['url']):
return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'}
return {
'id': api_response.get('id', album_url_tag),
'uploader': api_response.get('artist'),
'title': api_response.get('title'),
'url': api_response['url'],
}
class AudiomackAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audiomack\.com/album/(?P<id>[\w/-]+)'
IE_NAME = 'audiomack:album'
_TESTS = [
# Standard album playlist
{
'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
'playlist_count': 15,
'info_dict':
{
'ext': 'mp3',
'title': 'Young Thug ft Lil Wayne - Take Kare',
"upload_date": "20141016",
"description": "New track produced by London On Da Track called “Take Kare\"\n\nhttp://instagram.com/theyoungthugworld\nhttps://www.facebook.com/ThuggerThuggerCashMoney\n",
"uploader": "Young Thug World"
'id': '812251',
'title': 'Tha Tour: Part 2 (Official Mixtape)'
}
},
# Album playlist ripped from fakeshoredrive with no metadata
{
'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
'info_dict': {
'title': 'PPP (Pistol P Project)',
'id': '837572',
},
'playlist': [{
'info_dict': {
'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)',
'id': '837577',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
}],
'params': {
'playliststart': 9,
'playlistend': 9,
}
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
# URLs end with [uploader name]/[uploader title]
# this title is whatever the user types in, and is rarely
# the proper song title. Real metadata is in the api response
album_url_tag = self._match_id(url)
result = {'_type': 'playlist', 'entries': []}
# There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
# Therefore we don't know how many songs the album has and must infi-loop until failure
for track_no in itertools.count():
# Get song's metadata
api_response = self._download_json(
'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
% (album_url_tag, track_no, time.time()), album_url_tag,
note='Querying song information (%d)' % (track_no + 1))
api_response = self._download_json(
"http://www.audiomack.com/api/music/url/song/%s?_=%d" % (
video_id, time.time()),
video_id)
if "url" not in api_response:
raise ExtractorError("Unable to deduce api url of song")
realurl = api_response["url"]
# Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# - if so, pass the work off to the soundcloud extractor
if SoundcloudIE.suitable(realurl):
return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}
webpage = self._download_webpage(url, video_id)
artist = self._html_search_regex(
r'<span class="artist">(.*?)</span>', webpage, "artist")
songtitle = self._html_search_regex(
r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>',
webpage, "title")
title = artist + " - " + songtitle
return {
'id': video_id,
'title': title,
'url': realurl,
}
# Total failure, only occurs when url is totally wrong
# Won't happen in middle of valid playlist (next case)
if 'url' not in api_response or 'error' in api_response:
raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
# URL is good but song id doesn't exist - usually means end of playlist
elif not api_response['url']:
break
else:
# Pull out the album metadata and add to result (if it exists)
for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
if apikey in api_response and resultkey not in result:
result[resultkey] = api_response[apikey]
song_id = url_basename(api_response['url']).rpartition('.')[0]
result['entries'].append({
'id': api_response.get('id', song_id),
'uploader': api_response.get('artist'),
'title': api_response.get('title', song_id),
'url': api_response['url'],
})
return result

View File

@ -1,54 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
determine_ext,
ExtractorError,
)
class AUEngineIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
_TEST = {
'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
'info_dict': {
'id': 'lfvlytY6',
'ext': 'mp4',
'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
title = title.strip()
links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
links = map(compat_urllib_parse.unquote, links)
thumbnail = None
video_url = None
for link in links:
if link.endswith('.png'):
thumbnail = link
elif '/videos/' in link:
video_url = link
if not video_url:
raise ExtractorError('Could not find video URL')
ext = '.' + determine_ext(video_url)
if ext == title[-len(ext):]:
title = title[:-len(ext)]
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
}

View File

@ -0,0 +1,93 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import float_or_none
class AzubuIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1',
'md5': 'a88b42fcf844f29ad6035054bd9ecaf4',
'info_dict': {
'id': '15575',
'ext': 'mp4',
'title': '2014 HOT6 CUP LAST BIG MATCH Ro8 Day 1',
'description': 'md5:d06bdea27b8cc4388a90ad35b5c66c01',
'thumbnail': 're:^https?://.*\.jpe?g',
'timestamp': 1417523507.334,
'upload_date': '20141202',
'duration': 9988.7,
'uploader': 'GSL',
'uploader_id': 414310,
'view_count': int,
},
},
{
'url': 'http://www.azubu.tv/FnaticTV#!/play/9344/-fnatic-at-worlds-2014:-toyz---%22i-love-rekkles,-he-has-amazing-mechanics%22-',
'md5': 'b72a871fe1d9f70bd7673769cdb3b925',
'info_dict': {
'id': '9344',
'ext': 'mp4',
'title': 'Fnatic at Worlds 2014: Toyz - "I love Rekkles, he has amazing mechanics"',
'description': 'md5:4a649737b5f6c8b5c5be543e88dc62af',
'thumbnail': 're:^https?://.*\.jpe?g',
'timestamp': 1410530893.320,
'upload_date': '20140912',
'duration': 172.385,
'uploader': 'FnaticTV',
'uploader_id': 272749,
'view_count': int,
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data']
title = data['title'].strip()
description = data['description']
thumbnail = data['thumbnail']
view_count = data['view_count']
uploader = data['user']['username']
uploader_id = data['user']['id']
stream_params = json.loads(data['stream_params'])
timestamp = float_or_none(stream_params['creationDate'], 1000)
duration = float_or_none(stream_params['length'], 1000)
renditions = stream_params.get('renditions') or []
video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength')
if video:
renditions.append(video)
formats = [{
'url': fmt['url'],
'width': fmt['frameWidth'],
'height': fmt['frameHeight'],
'vbr': float_or_none(fmt['encodingRate'], 1000),
'filesize': fmt['size'],
'vcodec': fmt['videoCodec'],
'container': fmt['videoContainer'],
} for fmt in renditions if fmt['url']]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'formats': formats,
}

View File

@ -5,7 +5,7 @@ import json
import itertools
from .common import InfoExtractor
from ..utils import (
from ..compat import (
compat_urllib_request,
)
@ -50,7 +50,7 @@ class BambuserIE(InfoExtractor):
'duration': int(info['length']),
'view_count': int(info['views_total']),
'uploader': info['username'],
'uploader_id': info['uid'],
'uploader_id': info['owner']['uid'],
}

View File

@ -4,9 +4,11 @@ import json
import re
from .common import InfoExtractor
from ..utils import (
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
ExtractorError,
)
@ -70,26 +72,29 @@ class BandcampIE(InfoExtractor):
download_link = m_download.group(1)
video_id = self._search_regex(
r'var TralbumData = {.*?id: (?P<id>\d+),?$',
webpage, 'video id', flags=re.MULTILINE | re.DOTALL)
r'(?ms)var TralbumData = {.*?id: (?P<id>\d+),?$',
webpage, 'video id')
download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
# We get the dictionary of the track from some javascript code
info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0]
all_info = self._parse_json(self._search_regex(
r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
info = all_info[0]
# We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info['downloads']['mp3-320']
# If we try to use this url it says the link has expired
initial_url = mp3_info['url']
re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
m_url = re.match(re_url, initial_url)
m_url = re.match(
r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
initial_url)
# We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js
request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
# If we could correctly generate the .rand field the url would be
# in the "download_url" key
final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
final_url = self._search_regex(
r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL')
return {
'id': video_id,
@ -104,7 +109,7 @@ class BandcampIE(InfoExtractor):
class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^?#]+)|/?(?:$|[?#]))'
_TESTS = [{
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@ -128,36 +133,49 @@ class BandcampAlbumIE(InfoExtractor):
],
'info_dict': {
'title': 'Jazz Format Mixtape vol.1',
'id': 'jazz-format-mixtape-vol-1',
'uploader_id': 'blazo',
},
'params': {
'playlistend': 2
},
'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
'skip': 'Bandcamp imposes download limits.'
}, {
'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
'info_dict': {
'title': 'Hierophany of the Open Grave',
'uploader_id': 'nightbringer',
'id': 'hierophany-of-the-open-grave',
},
'playlist_mincount': 9,
}, {
'url': 'http://dotscale.bandcamp.com',
'info_dict': {
'title': 'Loom',
'id': 'dotscale',
'uploader_id': 'dotscale',
},
'playlist_mincount': 7,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('subdomain')
title = mobj.group('title')
display_id = title or playlist_id
webpage = self._download_webpage(url, display_id)
uploader_id = mobj.group('subdomain')
album_id = mobj.group('album_id')
playlist_id = album_id or uploader_id
webpage = self._download_webpage(url, playlist_id)
tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
if not tracks_paths:
raise ExtractorError('The page doesn\'t contain any tracks')
entries = [
self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
for t_path in tracks_paths]
title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
title = self._search_regex(
r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
return {
'_type': 'playlist',
'uploader_id': uploader_id,
'id': playlist_id,
'display_id': display_id,
'title': title,
'entries': entries,
}

View File

@ -1,15 +1,16 @@
from __future__ import unicode_literals
import re
import xml.etree.ElementTree
from .subtitles import SubtitlesInfoExtractor
from ..utils import ExtractorError
from ..compat import compat_HTTPError
class BBCCoUkIE(SubtitlesInfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
_TESTS = [
{
@ -17,8 +18,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
'info_dict': {
'id': 'b039d07m',
'ext': 'flv',
'title': 'Kaleidoscope: Leonard Cohen',
'description': 'md5:db4755d7a665ae72343779f7dacb402c',
'title': 'Kaleidoscope, Leonard Cohen',
'description': 'The Canadian poet and songwriter reflects on his musical career.',
'duration': 1740,
},
'params': {
@ -55,6 +56,71 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
'skip_download': True,
},
'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
},
{
'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
'info_dict': {
'id': 'b03k3pb7',
'ext': 'flv',
'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
'description': '2. Invasion',
'duration': 3600,
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
}, {
'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
'info_dict': {
'id': 'b04v209v',
'ext': 'flv',
'title': 'Pete Tong, The Essential New Tune Special',
'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
'duration': 10800,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
'note': 'Audio',
'info_dict': {
'id': 'p02frcch',
'ext': 'flv',
'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
'duration': 3507,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
'note': 'Video',
'info_dict': {
'id': 'p025c103',
'ext': 'flv',
'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
'duration': 226,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
'only_matching': True,
}, {
'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
'only_matching': True,
}, {
'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
'only_matching': True,
}
]
@ -102,6 +168,10 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
def _extract_medias(self, media_selection):
error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
if error is not None:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
def _extract_connections(self, media):
@ -158,54 +228,101 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
subtitles[lang] = srt
return subtitles
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
group_id = mobj.group('id')
def _download_media_selector(self, programme_id):
try:
media_selection = self._download_xml(
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
else:
raise
webpage = self._download_webpage(url, group_id, 'Downloading video page')
if re.search(r'id="emp-error" class="notinuk">', webpage):
raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only',
expected=True)
formats = []
subtitles = None
playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
'Downloading playlist XML')
for media in self._extract_medias(media_selection):
kind = media.get('kind')
if kind == 'audio':
formats.extend(self._extract_audio(media, programme_id))
elif kind == 'video':
formats.extend(self._extract_video(media, programme_id))
elif kind == 'captions':
subtitles = self._extract_captions(media, programme_id)
return formats, subtitles
def _download_playlist(self, playlist_id):
try:
playlist = self._download_json(
'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
playlist_id, 'Downloading playlist JSON')
version = playlist.get('defaultAvailableVersion')
if version:
smp_config = version['smpConfig']
title = smp_config['title']
description = smp_config['summary']
for item in smp_config['items']:
kind = item['kind']
if kind != 'programme' and kind != 'radioProgramme':
continue
programme_id = item.get('vpid')
duration = int(item.get('duration'))
formats, subtitles = self._download_media_selector(programme_id)
return programme_id, title, description, duration, formats, subtitles
except ExtractorError as ee:
if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
raise
# fallback to legacy playlist
playlist = self._download_xml(
'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
playlist_id, 'Downloading legacy playlist XML')
no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
if no_items is not None:
reason = no_items.get('reason')
if reason == 'preAvailability':
msg = 'Episode %s is not yet available' % group_id
msg = 'Episode %s is not yet available' % playlist_id
elif reason == 'postAvailability':
msg = 'Episode %s is no longer available' % group_id
msg = 'Episode %s is no longer available' % playlist_id
elif reason == 'noMedia':
msg = 'Episode %s is not currently available' % playlist_id
else:
msg = 'Episode %s is not available: %s' % (group_id, reason)
msg = 'Episode %s is not available: %s' % (playlist_id, reason)
raise ExtractorError(msg, expected=True)
formats = []
subtitles = None
for item in self._extract_items(playlist):
kind = item.get('kind')
if kind != 'programme' and kind != 'radioProgramme':
continue
title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
programme_id = item.get('identifier')
duration = int(item.get('duration'))
formats, subtitles = self._download_media_selector(programme_id)
media_selection = self._download_xml(
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
programme_id, 'Downloading media selection XML')
return programme_id, title, description, duration, formats, subtitles
for media in self._extract_medias(media_selection):
kind = media.get('kind')
if kind == 'audio':
formats.extend(self._extract_audio(media, programme_id))
elif kind == 'video':
formats.extend(self._extract_video(media, programme_id))
elif kind == 'captions':
subtitles = self._extract_captions(media, programme_id)
def _real_extract(self, url):
group_id = self._match_id(url)
webpage = self._download_webpage(url, group_id, 'Downloading video page')
programme_id = self._search_regex(
r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
if programme_id:
player = self._download_json(
'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id,
group_id)['jsConf']['player']
title = player['title']
description = player['subtitle']
duration = player['duration']
formats, subtitles = self._download_media_selector(programme_id)
else:
programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(programme_id, subtitles)

View File

@ -9,7 +9,7 @@ class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://beeg.com/5416503',
'md5': '634526ae978711f6b748fe0dd6c11f57',
'md5': '1bff67111adb785c51d1b42959ec10e5',
'info_dict': {
'id': '5416503',
'ext': 'mp4',

View File

@ -10,15 +10,15 @@ from ..utils import url_basename
class BehindKinkIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
_TEST = {
'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/',
'md5': '41ad01222b8442089a55528fec43ec01',
'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
'info_dict': {
'id': '36370',
'id': '37127',
'ext': 'mp4',
'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!',
'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...',
'upload_date': '20140814',
'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg',
'title': 'What are you passionate about Marley Blaze',
'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
'upload_date': '20141205',
'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
'age_limit': 18,
}
}
@ -26,26 +26,19 @@ class BehindKinkIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
year = mobj.group('year')
month = mobj.group('month')
day = mobj.group('day')
upload_date = year + month + day
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r"'file':\s*'([^']+)'",
webpage, 'URL base')
video_id = url_basename(video_url)
video_id = video_id.split('_')[0]
r'<source src="([^"]+)"', webpage, 'video URL')
video_id = url_basename(video_url).split('_')[0]
upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': self._og_search_title(webpage),
'display_id': display_id,
'url': video_url,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
'upload_date': upload_date,

107
youtube_dl/extractor/bet.py Normal file
View File

@ -0,0 +1,107 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import (
xpath_text,
xpath_with_ns,
int_or_none,
parse_iso8601,
)
class BetIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
_TESTS = [
{
'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
'info_dict': {
'id': '740ab250-bb94-4a8a-8787-fe0de7c74471',
'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
'ext': 'flv',
'title': 'BET News Presents: A Conversation With President Obama',
'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6',
'duration': 1534,
'timestamp': 1418075340,
'upload_date': '20141208',
'uploader': 'admin',
'thumbnail': 're:(?i)^https?://.*\.jpg$',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
'info_dict': {
'id': 'bcd1b1df-673a-42cf-8d01-b282db608f2d',
'display_id': 'justice-for-ferguson-a-community-reacts',
'ext': 'flv',
'title': 'Justice for Ferguson: A Community Reacts',
'description': 'A BET News special.',
'duration': 1696,
'timestamp': 1416942360,
'upload_date': '20141125',
'uploader': 'admin',
'thumbnail': 're:(?i)^https?://.*\.jpg$',
},
'params': {
# rtmp download
'skip_download': True,
},
}
]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
media_url = compat_urllib_parse.unquote(self._search_regex(
[r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
webpage, 'media URL'))
mrss = self._download_xml(media_url, display_id)
item = mrss.find('./channel/item')
NS_MAP = {
'dc': 'http://purl.org/dc/elements/1.1/',
'media': 'http://search.yahoo.com/mrss/',
'ka': 'http://kickapps.com/karss',
}
title = xpath_text(item, './title', 'title')
description = xpath_text(
item, './description', 'description', fatal=False)
video_id = xpath_text(item, './guid', 'video id', fatal=False)
timestamp = parse_iso8601(xpath_text(
item, xpath_with_ns('./dc:date', NS_MAP),
'upload date', fatal=False))
uploader = xpath_text(
item, xpath_with_ns('./dc:creator', NS_MAP),
'uploader', fatal=False)
media_content = item.find(
xpath_with_ns('./media:content', NS_MAP))
duration = int_or_none(media_content.get('duration'))
smil_url = media_content.get('url')
thumbnail = media_content.find(
xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
formats = self._extract_smil_formats(smil_url, display_id)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'duration': duration,
'formats': formats,
}

View File

@ -5,8 +5,6 @@ import re
from .common import InfoExtractor
from ..utils import (
compat_parse_qs,
ExtractorError,
int_or_none,
unified_strdate,
)
@ -29,10 +27,9 @@ class BiliBiliIE(InfoExtractor):
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_code = self._search_regex(
r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
@ -55,45 +52,38 @@ class BiliBiliIE(InfoExtractor):
thumbnail = self._html_search_meta(
'thumbnailUrl', video_code, 'thumbnail', fatal=False)
player_params = compat_parse_qs(self._html_search_regex(
r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
webpage, 'player params'))
cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
if 'cid' in player_params:
cid = player_params['cid'][0]
lq_doc = self._download_xml(
'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
video_id,
note='Downloading LQ video info'
)
lq_durl = lq_doc.find('./durl')
formats = [{
'format_id': 'lq',
'quality': 1,
'url': lq_durl.find('./url').text,
'filesize': int_or_none(
lq_durl.find('./size'), get_attr='text'),
}]
lq_doc = self._download_xml(
'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
video_id,
note='Downloading LQ video info'
)
lq_durl = lq_doc.find('.//durl')
formats = [{
'format_id': 'lq',
'quality': 1,
'url': lq_durl.find('./url').text,
hq_doc = self._download_xml(
'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
video_id,
note='Downloading HQ video info',
fatal=False,
)
if hq_doc is not False:
hq_durl = hq_doc.find('./durl')
formats.append({
'format_id': 'hq',
'quality': 2,
'ext': 'flv',
'url': hq_durl.find('./url').text,
'filesize': int_or_none(
lq_durl.find('./size'), get_attr='text'),
}]
hq_doc = self._download_xml(
'http://interface.bilibili.cn/playurl?cid=%s' % cid,
video_id,
note='Downloading HQ video info',
fatal=False,
)
if hq_doc is not False:
hq_durl = hq_doc.find('.//durl')
formats.append({
'format_id': 'hq',
'quality': 2,
'ext': 'flv',
'url': hq_durl.find('./url').text,
'filesize': int_or_none(
hq_durl.find('./size'), get_attr='text'),
})
else:
raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
hq_durl.find('./size'), get_attr='text'),
})
self._sort_formats(formats)
return {

View File

@ -1,40 +1,35 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import remove_start
from ..utils import (
remove_start,
int_or_none,
)
class BlinkxIE(InfoExtractor):
_VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
_VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
IE_NAME = 'blinkx'
_TEST = {
'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
'md5': '2e9a07364af40163a908edbf10bb2492',
'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ',
'md5': '337cf7a344663ec79bf93a526a2e06c7',
'info_dict': {
'id': '8aQUy7GV',
'id': 'Da0Gw3xc',
'ext': 'mp4',
'title': 'Police Car Rolls Away',
'uploader': 'stupidvideos.com',
'upload_date': '20131215',
'timestamp': 1387068000,
'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
'duration': 14.886,
'thumbnails': [{
'width': 100,
'height': 76,
'resolution': '100x76',
'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
}],
'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News',
'uploader': 'IGN News',
'upload_date': '20150217',
'timestamp': 1424215740,
'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.',
'duration': 47.743333,
},
}
def _real_extract(self, rl):
m = re.match(self._VALID_URL, rl)
video_id = m.group('id')
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = video_id[:8]
api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
@ -60,18 +55,20 @@ class BlinkxIE(InfoExtractor):
elif m['type'] in ('flv', 'mp4'):
vcodec = remove_start(m['vcodec'], 'ff')
acodec = remove_start(m['acodec'], 'ff')
tbr = (int(m['vbr']) + int(m['abr'])) // 1000
vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000)
abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000)
tbr = vbr + abr if vbr and abr else None
format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
formats.append({
'format_id': format_id,
'url': m['link'],
'vcodec': vcodec,
'acodec': acodec,
'abr': int(m['abr']) // 1000,
'vbr': int(m['vbr']) // 1000,
'abr': abr,
'vbr': vbr,
'tbr': tbr,
'width': int(m['w']),
'height': int(m['h']),
'width': int_or_none(m.get('w')),
'height': int_or_none(m.get('h')),
})
self._sort_formats(formats)

View File

@ -4,13 +4,17 @@ import re
from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
compat_urllib_request,
unescapeHTML,
parse_iso8601,
compat_urlparse,
clean_html,
from ..compat import (
compat_str,
compat_urllib_request,
compat_urlparse,
)
from ..utils import (
clean_html,
int_or_none,
parse_iso8601,
unescapeHTML,
)
@ -78,7 +82,25 @@ class BlipTVIE(SubtitlesInfoExtractor):
'uploader': 'NostalgiaCritic',
'uploader_id': '246467',
}
}
},
{
# https://github.com/rg3/youtube-dl/pull/4404
'note': 'Audio only',
'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982',
'md5': '76c0a56f24e769ceaab21fbb6416a351',
'info_dict': {
'id': '7103299',
'ext': 'flv',
'title': 'Weekly Manga Recap: Kingdom',
'description': 'And then Shin breaks the enemy line, and he&apos;s all like HWAH! And then he slices a guy and it&apos;s all like FWASHING! And... it&apos;s really hard to describe the best parts of this series without breaking down into sound effects, okay?',
'timestamp': 1417660321,
'upload_date': '20141204',
'uploader': 'The Rollo T',
'uploader_id': '407429',
'duration': 7251,
'vcodec': 'none',
}
},
]
def _real_extract(self, url):
@ -145,11 +167,11 @@ class BlipTVIE(SubtitlesInfoExtractor):
'url': real_url,
'format_id': role,
'format_note': media_type,
'vcodec': media_content.get(blip('vcodec')),
'vcodec': media_content.get(blip('vcodec')) or 'none',
'acodec': media_content.get(blip('acodec')),
'filesize': media_content.get('filesize'),
'width': int(media_content.get('width')),
'height': int(media_content.get('height')),
'width': int_or_none(media_content.get('width')),
'height': int_or_none(media_content.get('height')),
})
self._sort_formats(formats)
@ -177,7 +199,7 @@ class BlipTVIE(SubtitlesInfoExtractor):
# For some weird reason, blip.tv serves a video instead of subtitles
# when we request with a common UA
req = compat_urllib_request.Request(url)
req.add_header('Youtubedl-user-agent', 'youtube-dl')
req.add_header('User-Agent', 'youtube-dl')
return self._download_webpage(req, None, note=False)

View File

@ -14,7 +14,6 @@ class BreakIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'md5': '33aa4ff477ecd124d18d7b5d23b87ce5',
'info_dict': {
'id': '2468056',
'ext': 'mp4',

View File

@ -6,25 +6,26 @@ import json
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
find_xpath_attr,
fix_xml_ampersands,
compat_urlparse,
compat_str,
compat_urllib_request,
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse,
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urlparse,
)
from ..utils import (
determine_ext,
ExtractorError,
unsmuggle_url,
find_xpath_attr,
fix_xml_ampersands,
unescapeHTML,
unsmuggle_url,
)
class BrightcoveIE(InfoExtractor):
_VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*?\?(?P<query>.*)'
_VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
_FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
_TESTS = [
@ -94,6 +95,7 @@ class BrightcoveIE(InfoExtractor):
'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=3550052898001&playerKey=AQ%7E%7E%2CAAABmA9XpXk%7E%2C-Kp7jNgisre1fG5OdqpAFUTcs0lP_ZoL',
'info_dict': {
'title': 'Sealife',
'id': '3550319591001',
},
'playlist_mincount': 7,
},
@ -107,7 +109,7 @@ class BrightcoveIE(InfoExtractor):
"""
# Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>',
object_str = re.sub(r'(<param(?:\s+[a-zA-Z0-9_]+="[^"]*")*)>',
lambda m: m.group(1) + '/>', object_str)
# Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
object_str = object_str.replace('<--', '<!--')
@ -246,7 +248,7 @@ class BrightcoveIE(InfoExtractor):
playlist_info = json_data['videoList']
videos = [self._extract_video_info(video_info) for video_info in playlist_info['mediaCollectionDTO']['videoDTOs']]
return self.playlist_result(videos, playlist_id=playlist_info['id'],
return self.playlist_result(videos, playlist_id='%s' % playlist_info['id'],
playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
def _extract_video_info(self, video_info):
@ -265,6 +267,7 @@ class BrightcoveIE(InfoExtractor):
url = rend['defaultURL']
if not url:
continue
ext = None
if rend['remote']:
url_comp = compat_urllib_parse_urlparse(url)
if url_comp.path.endswith('.m3u8'):
@ -276,7 +279,7 @@ class BrightcoveIE(InfoExtractor):
# akamaihd.net, but they don't use f4m manifests
url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
ext = 'flv'
else:
if ext is None:
ext = determine_ext(url)
size = rend.get('size')
formats.append({

View File

@ -33,7 +33,8 @@ class BuzzFeedIE(InfoExtractor):
'skip_download': True, # Got enough YouTube download tests
},
'info_dict': {
'description': 'Munchkin the Teddy Bear is back !',
'id': 'look-at-this-cute-dog-omg',
'description': 're:Munchkin the Teddy Bear is back ?!',
'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
},
'playlist': [{
@ -42,9 +43,9 @@ class BuzzFeedIE(InfoExtractor):
'ext': 'mp4',
'upload_date': '20141124',
'uploader_id': 'CindysMunchkin',
'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
'uploader': 'Munchkin the Shih Tzu',
'title': 'Munchkin the Teddy Bear gets her exercise',
'description': 're:© 2014 Munchkin the',
'uploader': 're:^Munchkin the',
'title': 're:Munchkin the Teddy Bear gets her exercise',
},
}]
}]

View File

@ -0,0 +1,153 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
parse_iso8601,
str_to_int,
)
class CamdemyIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
_TESTS = [{
# single file
'url': 'http://www.camdemy.com/media/5181/',
'md5': '5a5562b6a98b37873119102e052e311b',
'info_dict': {
'id': '5181',
'ext': 'mp4',
'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
'thumbnail': 're:^https?://.*\.jpg$',
'description': '',
'creator': 'ss11spring',
'upload_date': '20130114',
'timestamp': 1358154556,
'view_count': int,
}
}, {
# With non-empty description
'url': 'http://www.camdemy.com/media/13885',
'md5': '4576a3bb2581f86c61044822adbd1249',
'info_dict': {
'id': '13885',
'ext': 'mp4',
'title': 'EverCam + Camdemy QuickStart',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
'creator': 'evercam',
'upload_date': '20140620',
'timestamp': 1403271569,
}
}, {
# External source
'url': 'http://www.camdemy.com/media/14842',
'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7',
'info_dict': {
'id': '2vsYQzNIsJo',
'ext': 'mp4',
'upload_date': '20130211',
'uploader': 'Hun Kim',
'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
'uploader_id': 'hunkimtutorials',
'title': 'Excel 2013 Tutorial - How to add Password Protection',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(url, video_id)
src_from = self._html_search_regex(
r"<div class='srcFrom'>Source: <a title='([^']+)'", page,
'external source', default=None)
if src_from:
return self.url_result(src_from)
oembed_obj = self._download_json(
'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
thumb_url = oembed_obj['thumbnail_url']
video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
file_list_doc = self._download_xml(
compat_urlparse.urljoin(video_folder, 'fileList.xml'),
video_id, 'Filelist XML')
file_name = file_list_doc.find('./video/item/fileName').text
video_url = compat_urlparse.urljoin(video_folder, file_name)
timestamp = parse_iso8601(self._html_search_regex(
r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<",
page, 'creation time', fatal=False),
delimiter=' ', timezone=datetime.timedelta(hours=8))
view_count = str_to_int(self._html_search_regex(
r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<",
page, 'view count', fatal=False))
return {
'id': video_id,
'url': video_url,
'title': oembed_obj['title'],
'thumbnail': thumb_url,
'description': self._html_search_meta('description', page),
'creator': oembed_obj['author_name'],
'duration': oembed_obj['duration'],
'timestamp': timestamp,
'view_count': view_count,
}
class CamdemyFolderIE(InfoExtractor):
_VALID_URL = r'http://www.camdemy.com/folder/(?P<id>\d+)'
_TESTS = [{
# links with trailing slash
'url': 'http://www.camdemy.com/folder/450',
'info_dict': {
'id': '450',
'title': '信號與系統 2012 & 2011 (Signals and Systems)',
},
'playlist_mincount': 145
}, {
# links without trailing slash
# and multi-page
'url': 'http://www.camdemy.com/folder/853',
'info_dict': {
'id': '853',
'title': '科學計算 - 使用 Matlab'
},
'playlist_mincount': 20
}, {
# with displayMode parameter. For testing the codes to add parameters
'url': 'http://www.camdemy.com/folder/853/?displayMode=defaultOrderByOrg',
'info_dict': {
'id': '853',
'title': '科學計算 - 使用 Matlab'
},
'playlist_mincount': 20
}]
def _real_extract(self, url):
folder_id = self._match_id(url)
# Add displayMode=list so that all links are displayed in a single page
parsed_url = list(compat_urlparse.urlparse(url))
query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
query.update({'displayMode': 'list'})
parsed_url[4] = compat_urllib_parse.urlencode(query)
final_url = compat_urlparse.urlunparse(parsed_url)
page = self._download_webpage(final_url, folder_id)
matches = re.findall(r"href='(/media/\d+/?)'", page)
entries = [self.url_result('http://www.camdemy.com' + media_path)
for media_path in matches]
folder_title = self._html_search_meta('keywords', page)
return self.playlist_result(entries, folder_id, folder_title)

View File

@ -5,6 +5,8 @@ import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
HEADRequest,
unified_strdate,
url_basename,
qualities,
@ -13,12 +15,13 @@ from ..utils import (
class CanalplusIE(InfoExtractor):
IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
_VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
_VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
_SITE_ID_MAP = {
'canalplus.fr': 'cplus',
'piwiplus.fr': 'teletoon',
'd8.tv': 'd8',
'itele.fr': 'itele',
}
_TESTS = [{
@ -51,6 +54,16 @@ class CanalplusIE(InfoExtractor):
'upload_date': '20131108',
},
'skip': 'videos get deleted after a while',
}, {
'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
'md5': '65aa83ad62fe107ce29e564bb8712580',
'info_dict': {
'id': '1213714',
'ext': 'flv',
'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
'description': 'md5:8216206ec53426ea6321321f3b3c16db',
'upload_date': '20150211',
},
}]
def _real_extract(self, url):
@ -76,6 +89,16 @@ class CanalplusIE(InfoExtractor):
preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
fmt_url = next(iter(media.find('VIDEOS'))).text
if '/geo' in fmt_url.lower():
response = self._request_webpage(
HEADRequest(fmt_url), video_id,
'Checking if the video is georestricted')
if '/blocage' in response.geturl():
raise ExtractorError(
'The video is not available in your country',
expected=True)
formats = []
for fmt in media.find('VIDEOS'):
format_url = fmt.text

View File

@ -1,7 +1,5 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
@ -39,8 +37,7 @@ class CBSIE(InfoExtractor):
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
real_id = self._search_regex(
r"video\.settings\.pid\s*=\s*'([^']+)';",

View File

@ -0,0 +1,30 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class CBSSportsIE(InfoExtractor):
_VALID_URL = r'http://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s',
'info_dict': {
'id': '_d5_GbO8p1sT',
'ext': 'flv',
'title': 'US Open flashbacks: 1990s',
'description': 'Bill Macatee relives the best moments in US Open history from the 1990s.',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
section = mobj.group('section')
video_id = mobj.group('id')
all_videos = self._download_json(
'http://www.cbssports.com/data/video/player/getVideos/%s?as=json' % section,
video_id)
# The json file contains the info of all the videos in the section
video_info = next(v for v in all_videos if v['pcid'] == video_id)
return self.url_result('theplatform:%s' % video_info['pid'], 'ThePlatform')

View File

@ -0,0 +1,99 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
qualities,
unified_strdate,
)
class CCCIE(InfoExtractor):
IE_NAME = 'media.ccc.de'
_VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/[^?#]+/[^?#/]*?_(?P<id>[0-9]{8,})._[^?#/]*\.html'
_TEST = {
'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video',
'md5': '205a365d0d57c0b1e43a12c9ffe8f9be',
'info_dict': {
'id': '20131228183',
'ext': 'mp4',
'title': 'Introduction to Processor Design',
'description': 'md5:5ddbf8c734800267f2cee4eab187bc1b',
'thumbnail': 're:^https?://.*\.jpg$',
'view_count': int,
'upload_date': '20131229',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if self._downloader.params.get('prefer_free_formats'):
preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd'])
else:
preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd'])
title = self._html_search_regex(
r'(?s)<h1>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex(
r"(?s)<p class='description'>(.*?)</p>",
webpage, 'description', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r"(?s)<span class='[^']*fa-calendar-o'></span>(.*?)</li>",
webpage, 'upload date', fatal=False))
view_count = int_or_none(self._html_search_regex(
r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
webpage, 'view count', fatal=False))
matches = re.finditer(r'''(?xs)
<(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s*
<a\s+href='(?P<http_url>[^']+)'>\s*
(?:
.*?
<a\s+href='(?P<torrent_url>[^']+\.torrent)'
)?''', webpage)
formats = []
for m in matches:
format = m.group('format')
format_id = self._search_regex(
r'.*/([a-z0-9_-]+)/[^/]*$',
m.group('http_url'), 'format id', default=None)
vcodec = 'h264' if 'h264' in format_id else (
'none' if format_id in ('mp3', 'opus') else None
)
formats.append({
'format_id': format_id,
'format': format,
'url': m.group('http_url'),
'vcodec': vcodec,
'preference': preference(format_id),
})
if m.group('torrent_url'):
formats.append({
'format_id': 'torrent-%s' % (format if format_id is None else format_id),
'format': '%s (torrent)' % format,
'proto': 'torrent',
'format_note': '(unsupported; will just download the .torrent file)',
'vcodec': vcodec,
'preference': -100 + preference(format_id),
'url': m.group('torrent_url'),
})
self._sort_formats(formats)
thumbnail = self._html_search_regex(
r"<video.*?poster='([^']+)'", webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'view_count': view_count,
'upload_date': upload_date,
'formats': formats,
}

View File

@ -3,55 +3,50 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
from .subtitles import SubtitlesInfoExtractor
from ..compat import (
compat_urllib_request,
compat_urllib_parse,
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
float_or_none,
)
class CeskaTelevizeIE(InfoExtractor):
class CeskaTelevizeIE(SubtitlesInfoExtractor):
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
_TESTS = [
{
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
'info_dict': {
'id': '213512120230004',
'ext': 'flv',
'title': 'První republika: Španělská chřipka',
'duration': 3107.4,
'id': '214411058091220',
'ext': 'mp4',
'title': 'Hyde Park Civilizace',
'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 3350,
},
'params': {
'skip_download': True, # requires rtmpdump
# m3u8 download
'skip_download': True,
},
'skip': 'Works only from Czech Republic.',
},
{
'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
'info_dict': {
'id': '20138143440',
'ext': 'flv',
'title': 'Tsatsiki, maminka a policajt',
'duration': 6754.1,
},
'params': {
'skip_download': True, # requires rtmpdump
},
'skip': 'Works only from Czech Republic.',
},
{
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
'info_dict': {
'id': '14716',
'ext': 'flv',
'ext': 'mp4',
'title': 'První republika: Zpěvačka z Dupárny Bobina',
'duration': 90,
'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 88.4,
},
'params': {
'skip_download': True, # requires rtmpdump
# m3u8 download
'skip_download': True,
},
},
]
@ -78,8 +73,9 @@ class CeskaTelevizeIE(InfoExtractor):
'requestSource': 'iVysilani',
}
req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
data=compat_urllib_parse.urlencode(data))
req = compat_urllib_request.Request(
'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
data=compat_urllib_parse.urlencode(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
req.add_header('x-addr', '127.0.0.1')
@ -88,39 +84,72 @@ class CeskaTelevizeIE(InfoExtractor):
playlistpage = self._download_json(req, video_id)
req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
playlist_url = playlistpage['url']
if playlist_url == 'error_region':
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url))
req.add_header('Referer', url)
playlist = self._download_xml(req, video_id)
playlist = self._download_json(req, video_id)
item = playlist['playlist'][0]
formats = []
for i in playlist.find('smilRoot/body'):
if 'AD' not in i.attrib['id']:
base_url = i.attrib['base']
parsedurl = compat_urllib_parse_urlparse(base_url)
duration = i.attrib['duration']
for video in i.findall('video'):
if video.attrib['label'] != 'AD':
format_id = video.attrib['label']
play_path = video.attrib['src']
vbr = int(video.attrib['system-bitrate'])
formats.append({
'format_id': format_id,
'url': base_url,
'vbr': vbr,
'play_path': play_path,
'app': parsedurl.path[1:] + '?' + parsedurl.query,
'rtmp_live': True,
'ext': 'flv',
})
for format_id, stream_url in item['streamUrls'].items():
formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4'))
self._sort_formats(formats)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
duration = float_or_none(item.get('duration'))
thumbnail = item.get('previewImageUrl')
subtitles = {}
subs = item.get('subtitles')
if subs:
subtitles['cs'] = subs[0]['url']
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id, subtitles)
return
subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles))
return {
'id': episode_id,
'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
'duration': float(duration),
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}
@staticmethod
def _fix_subtitles(subtitles):
""" Convert millisecond-based subtitles to SRT """
if subtitles is None:
return subtitles # subtitles not requested
def _msectotimecode(msec):
""" Helper utility to convert milliseconds to timecode """
components = []
for divider in [1000, 60, 60, 100]:
components.append(msec % divider)
msec //= divider
return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
def _fix_subtitle(subtitle):
for line in subtitle.splitlines():
m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
if m:
yield m.group(1)
start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
yield "{0} --> {1}".format(start, stop)
else:
yield line
fixed_subtitles = {}
for k, v in subtitles.items():
fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v))
return fixed_subtitles

View File

@ -236,16 +236,17 @@ class Channel9IE(InfoExtractor):
if contents is None:
return contents
session_meta = {'session_code': self._extract_session_code(html),
'session_day': self._extract_session_day(html),
'session_room': self._extract_session_room(html),
'session_speakers': self._extract_session_speakers(html),
}
session_meta = {
'session_code': self._extract_session_code(html),
'session_day': self._extract_session_day(html),
'session_room': self._extract_session_room(html),
'session_speakers': self._extract_session_speakers(html),
}
for content in contents:
content.update(session_meta)
return contents
return self.playlist_result(contents)
def _extract_list(self, content_path):
rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')

View File

@ -0,0 +1,50 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
unified_strdate,
xpath_text,
)
class CinchcastIE(InfoExtractor):
_VALID_URL = r'https?://player\.cinchcast\.com/.*?assetId=(?P<id>[0-9]+)'
_TEST = {
# Actual test is run in generic, look for undergroundwellness
'url': 'http://player.cinchcast.com/?platformId=1&#038;assetType=single&#038;assetId=7141703',
'only_matching': True,
}
def _real_extract(self, url):
video_id = self._match_id(url)
doc = self._download_xml(
'http://www.blogtalkradio.com/playerasset/mrss?assetType=single&assetId=%s' % video_id,
video_id)
item = doc.find('.//item')
title = xpath_text(item, './title', fatal=True)
date_str = xpath_text(
item, './{http://developer.longtailvideo.com/trac/}date')
upload_date = unified_strdate(date_str, day_first=False)
# duration is present but wrong
formats = [{
'format_id': 'main',
'url': item.find('./{http://search.yahoo.com/mrss/}content').attrib['url'],
}]
backup_url = xpath_text(
item, './{http://developer.longtailvideo.com/trac/}backupContent')
if backup_url:
formats.append({
'preference': 2, # seems to be more reliable
'format_id': 'backup',
'url': backup_url,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'upload_date': upload_date,
'formats': formats,
}

View File

@ -1,9 +1,7 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import determine_ext
_translation_table = {
@ -27,10 +25,10 @@ class CliphunterIE(InfoExtractor):
'''
_TEST = {
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
'md5': 'a2ba71eebf523859fe527a61018f723e',
'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
'info_dict': {
'id': '1012420',
'ext': 'mp4',
'ext': 'flv',
'title': 'Fun Jynx Maze solo',
'thumbnail': 're:^https?://.*\.jpg$',
'age_limit': 18,
@ -44,39 +42,31 @@ class CliphunterIE(InfoExtractor):
video_title = self._search_regex(
r'mediaTitle = "([^"]+)"', webpage, 'title')
pl_fiji = self._search_regex(
r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
pl_c_qual = self._search_regex(
r'pl_c_qual = "(.)"', webpage, 'video quality')
video_url = _decode(pl_fiji)
formats = [{
'url': video_url,
'format_id': 'default-%s' % pl_c_qual,
}]
fmts = {}
for fmt in ('mp4', 'flv'):
fmt_list = self._parse_json(self._search_regex(
r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
for f in fmt_list:
fmts[f['fname']] = _decode(f['sUrl'])
qualities_json = self._search_regex(
r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
qualities_data = json.loads(qualities_json)
qualities = self._parse_json(self._search_regex(
r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
for i, t in enumerate(
re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
quality_id, crypted_url = t
video_url = _decode(crypted_url)
formats = []
for fname, url in fmts.items():
f = {
'format_id': quality_id,
'url': video_url,
'quality': i,
'url': url,
}
if quality_id in qualities_data:
qd = qualities_data[quality_id]
m = re.match(
r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
\s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
if m:
f['width'] = int(m.group('width'))
f['height'] = int(m.group('height'))
f['tbr'] = int(m.group('tbr'))
if fname in qualities:
qual = qualities[fname]
f.update({
'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
'width': qual['w'],
'height': qual['h'],
'tbr': qual['br'],
})
formats.append(f)
self._sort_formats(formats)
thumbnail = self._search_regex(

View File

@ -2,12 +2,10 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
)
@ -15,23 +13,24 @@ class CNETIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
_TEST = {
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
'md5': '041233212a0d06b179c87cbcca1577b8',
'info_dict': {
'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
'ext': 'mp4',
'ext': 'flv',
'title': 'Hands-on with Microsoft Windows 8.1 Update',
'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
'thumbnail': 're:^http://.*/flmswindows8.jpg$',
'uploader_id': 'sarah.mitroff@cbsinteractive.com',
'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
'uploader': 'Sarah Mitroff',
},
'params': {
'skip_download': 'requires rtmpdump',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
data_json = self._html_search_regex(
r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
webpage, 'data json')
@ -42,37 +41,31 @@ class CNETIE(InfoExtractor):
if not vdata:
raise ExtractorError('Cannot find video data')
mpx_account = data['config']['players']['default']['mpx_account']
vid = vdata['files']['rtmp']
tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
video_id = vdata['id']
title = vdata.get('headline')
if title is None:
title = vdata.get('title')
if title is None:
raise ExtractorError('Cannot find title!')
description = vdata.get('dek')
thumbnail = vdata.get('image', {}).get('path')
author = vdata.get('author')
if author:
uploader = '%s %s' % (author['firstName'], author['lastName'])
uploader_id = author.get('email')
uploader_id = author.get('id')
else:
uploader = None
uploader_id = None
formats = [{
'format_id': '%s-%s-%s' % (
f['type'], f['format'],
int_or_none(f.get('bitrate'), 1000, default='')),
'url': f['uri'],
'tbr': int_or_none(f.get('bitrate'), 1000),
} for f in vdata['files']['data']]
self._sort_formats(formats)
return {
'_type': 'url_transparent',
'url': tp_link,
'id': video_id,
'display_id': display_id,
'title': title,
'formats': formats,
'description': description,
'uploader': uploader,
'uploader_id': uploader_id,
'thumbnail': thumbnail,

View File

@ -11,14 +11,14 @@ from ..utils import (
class CNNIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))'''
_VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''
_TESTS = [{
'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
'md5': '3e6121ea48df7e2259fe73a0628605c4',
'info_dict': {
'id': 'sports_2013_06_09_nadal-1-on-1.cnn',
'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
'ext': 'mp4',
'title': 'Nadal wins 8th French Open title',
'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
@ -35,13 +35,23 @@ class CNNIE(InfoExtractor):
"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
"upload_date": "20130821",
}
}, {
'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
'md5': 'f14d02ebd264df951feb2400e2c25a1b',
'info_dict': {
'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
'ext': 'mp4',
'title': 'Nashville Ep. 1: Hand crafted skateboards',
'description': 'md5:e7223a503315c9f150acac52e76de086',
'upload_date': '20141222',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
path = mobj.group('path')
page_title = mobj.group('title')
info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path
info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path
info = self._download_xml(info_url, page_title)
formats = []
@ -127,3 +137,28 @@ class CNNBlogsIE(InfoExtractor):
'url': cnn_url,
'ie_key': CNNIE.ie_key(),
}
class CNNArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
_TEST = {
'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
'info_dict': {
'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
'ext': 'mp4',
'title': 'Obama: Cyberattack not an act of war',
'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
'upload_date': '20141221',
},
'add_ie': ['CNN'],
}
def _real_extract(self, url):
webpage = self._download_webpage(url, url_basename(url))
cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
return {
'_type': 'url',
'url': 'http://cnn.com/video/?/video/' + cnn_url,
'ie_key': CNNIE.ie_key(),
}

View File

@ -0,0 +1,92 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
float_or_none,
int_or_none,
)
class CollegeRamaIE(InfoExtractor):
_VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P<id>[\da-f]+)'
_TESTS = [
{
'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d',
'md5': '481fda1c11f67588c0d9d8fbdced4e39',
'info_dict': {
'id': '585a43626e544bdd97aeb71a0ec907a01d',
'ext': 'mp4',
'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
'description': '',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 7713.088,
'timestamp': 1413309600,
'upload_date': '20141014',
},
},
{
'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4',
'md5': 'ef1fdded95bdf19b12c5999949419c92',
'info_dict': {
'id': '86a9ea9f53e149079fbdb4202b521ed21d',
'ext': 'wmv',
'title': '64ste Vakantiecursus: Afvalwater',
'description': 'md5:7fd774865cc69d972f542b157c328305',
'duration': 10853,
'timestamp': 1326446400,
'upload_date': '20120113',
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
player_options_request = {
"getPlayerOptionsRequest": {
"ResourceId": video_id,
"QueryString": "",
}
}
request = compat_urllib_request.Request(
'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
json.dumps(player_options_request))
request.add_header('Content-Type', 'application/json')
player_options = self._download_json(request, video_id)
presentation = player_options['d']['Presentation']
title = presentation['Title']
description = presentation.get('Description')
thumbnail = None
duration = float_or_none(presentation.get('Duration'), 1000)
timestamp = int_or_none(presentation.get('UnixTime'), 1000)
formats = []
for stream in presentation['Streams']:
for video in stream['VideoUrls']:
thumbnail_url = stream.get('ThumbnailUrl')
if thumbnail_url:
thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url
format_id = video['MediaType']
if format_id == 'SS':
continue
formats.append({
'url': video['Location'],
'format_id': format_id,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
}

View File

@ -0,0 +1,57 @@
# encoding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import parse_iso8601
class ComCarCoffIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
_TESTS = [{
'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
'info_dict': {
'id': 'miranda-sings-happy-thanksgiving-miranda',
'ext': 'mp4',
'upload_date': '20141127',
'timestamp': 1417107600,
'title': 'Happy Thanksgiving Miranda',
'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',
},
'params': {
'skip_download': 'requires ffmpeg',
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
if not display_id:
display_id = 'comediansincarsgettingcoffee.com'
webpage = self._download_webpage(url, display_id)
full_data = json.loads(self._search_regex(
r'<script type="application/json" id="videoData">(?P<json>.+?)</script>',
webpage, 'full data json'))
video_id = full_data['activeVideo']['video']
video_data = full_data['videos'][video_id]
thumbnails = [{
'url': video_data['images']['thumb'],
}, {
'url': video_data['images']['poster'],
}]
formats = self._extract_m3u8_formats(
video_data['mediaUrl'], video_id, ext='mp4')
return {
'id': video_id,
'display_id': display_id,
'title': video_data['title'],
'description': video_data.get('description'),
'timestamp': parse_iso8601(video_data.get('pubDate')),
'thumbnails': thumbnails,
'formats': formats,
'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
}

View File

@ -3,9 +3,11 @@ from __future__ import unicode_literals
import re
from .mtv import MTVServicesInfoExtractor
from ..utils import (
from ..compat import (
compat_str,
compat_urllib_parse,
)
from ..utils import (
ExtractorError,
float_or_none,
unified_strdate,
@ -32,12 +34,12 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
class ComedyCentralShowsIE(MTVServicesInfoExtractor):
IE_DESC = 'The Daily Show / The Colbert Report'
# urls can be abbreviations like :thedailyshow or :colbert
# urls can be abbreviations like :thedailyshow
# urls for episodes like:
# or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
# or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
# or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
|https?://(:www\.)?
(?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
@ -47,8 +49,10 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
)|
(?P<interview>
extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
(?:[?#].*|$)'''
extended-interviews/(?P<interID>[0-9a-z]+)/
(?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
(?:/[^/?#]?|[?#]|$))))
'''
_TESTS = [{
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
@ -60,6 +64,38 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
'uploader': 'thedailyshow',
'title': 'thedailyshow kristen-stewart part 1',
}
}, {
'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
'info_dict': {
'id': 'sarah-chayes-extended-interview',
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
'title': 'thedailyshow Sarah Chayes Extended Interview',
},
'playlist': [
{
'info_dict': {
'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
'ext': 'mp4',
'upload_date': '20150129',
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
'uploader': 'thedailyshow',
'title': 'thedailyshow sarah-chayes-extended-interview part 1',
},
},
{
'info_dict': {
'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
'ext': 'mp4',
'upload_date': '20150129',
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
'uploader': 'thedailyshow',
'title': 'thedailyshow sarah-chayes-extended-interview part 2',
},
},
],
'params': {
'skip_download': True,
},
}, {
'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
'only_matching': True,
@ -81,6 +117,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
}, {
'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
'only_matching': True,
@ -234,6 +273,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
return {
'_type': 'playlist',
'id': epTitle,
'entries': entries,
'title': playlist_title,
'description': description,

View File

@ -15,6 +15,7 @@ import xml.etree.ElementTree
from ..compat import (
compat_cookiejar,
compat_HTTPError,
compat_http_client,
compat_urllib_error,
compat_urllib_parse_urlparse,
@ -22,6 +23,7 @@ from ..compat import (
compat_str,
)
from ..utils import (
age_restricted,
clean_html,
compiled_regex_type,
ExtractorError,
@ -41,7 +43,7 @@ class InfoExtractor(object):
information about the video (or videos) the URL refers to. This
information includes the real video URL, the video title, author and
others. The information is stored in a dictionary which is then
passed to the FileDownloader. The FileDownloader processes this
passed to the YoutubeDL. The YoutubeDL processes this
information possibly downloading the video to the file system, among
other possible outcomes.
@ -87,12 +89,15 @@ class InfoExtractor(object):
* player_url SWF Player URL (used for rtmpdump).
* protocol The protocol that will be used for the actual
download, lower-case.
"http", "https", "rtsp", "rtmp", "m3u8" or so.
"http", "https", "rtsp", "rtmp", "rtmpe",
"m3u8", or "m3u8_native".
* preference Order number of this format. If this field is
present and not None, the formats get sorted
by this field, regardless of all other values.
-1 for default (order by other properties),
-2 or smaller for less than default.
< -1000 to hide the format (if there is
another one which is strictly better)
* language_preference Is this in the correct requested
language?
10 if it's what the URL is about,
@ -106,12 +111,17 @@ class InfoExtractor(object):
(quality takes higher priority)
-1 for default (order by other properties),
-2 or smaller for less than default.
* http_referer HTTP Referer header value to set.
* http_method HTTP method to use for the download.
* http_headers A dictionary of additional HTTP headers
to add to the request.
* http_post_data Additional data to send with a POST
request.
* stretched_ratio If given and not 1, indicates that the
video's pixels are not square.
width : height ratio as float.
* no_resume The server does not support resuming the
(HTTP or RTMP) download. Boolean.
url: Final video URL.
ext: Video filename extension.
format: The video format, defaults to ext (used for --get-format)
@ -119,19 +129,23 @@ class InfoExtractor(object):
The following fields are optional:
alt_title: A secondary title of the video.
display_id An alternative identifier for the video, not necessarily
unique, but available before title. Typically, id is
something like "4234987", title "Dancing naked mole rats",
and display_id "dancing-naked-mole-rats"
thumbnails: A list of dictionaries, with the following entries:
* "id" (optional, string) - Thumbnail format ID
* "url"
* "preference" (optional, int) - quality of the image
* "width" (optional, int)
* "height" (optional, int)
* "resolution" (optional, string "{width}x{height"},
deprecated)
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
description: Full video description.
uploader: Full name of the video uploader.
creator: The main artist who created the video.
timestamp: UNIX timestamp of the moment the video became available.
upload_date: Video upload date (YYYYMMDD).
If not explicitly set, calculated from timestamp.
@ -143,7 +157,19 @@ class InfoExtractor(object):
view_count: How many users have watched the video on the platform.
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
average_rating: Average rating give by users, the scale used depends on the webpage
comment_count: Number of comments on the video
comments: A list of comments, each with one or more of the following
properties (all but one of text or html optional):
* "author" - human-readable name of the comment author
* "author_id" - user ID of the comment author
* "id" - Comment ID
* "html" - Comment as HTML
* "text" - Plain text of the comment
* "timestamp" - UNIX timestamp of comment
* "parent" - ID of the comment this one is replying to.
Set to "root" to indicate that this is a
comment to the original video.
parts: A list of info_dicts for each of the parts of the video,
it must include the url field, if it's a rtmp download it
can contain additional fields for rtmpdump.
@ -162,8 +188,8 @@ class InfoExtractor(object):
_type "playlist" indicates multiple videos.
There must be a key "entries", which is a list or a PagedList object, each
element of which is a valid dictionary under this specfication.
There must be a key "entries", which is a list, an iterable, or a PagedList
object, each element of which is a valid dictionary by this specification.
Additionally, playlists can have "title" and "id" attributes with the same
semantics as videos (see above).
@ -178,9 +204,10 @@ class InfoExtractor(object):
_type "url" indicates that the video must be extracted from another
location, possibly by a different extractor. Its only required key is:
"url" - the next URL to extract.
Additionally, it may have properties believed to be identical to the
resolved entity, for example "title" if the title of the referred video is
The key "ie_key" can be set to the class name (minus the trailing "IE",
e.g. "Youtube") if the extractor class is known in advance.
Additionally, the dictionary may have any properties of the resolved entity
known in advance, for example "title" if the title of the referred video is
known ahead of time.
@ -241,8 +268,15 @@ class InfoExtractor(object):
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
self.initialize()
return self._real_extract(url)
try:
self.initialize()
return self._real_extract(url)
except ExtractorError:
raise
except compat_http_client.IncompleteRead as e:
raise ExtractorError('A network error has occured.', cause=e, expected=True)
except (KeyError, StopIteration) as e:
raise ExtractorError('An extractor error has occured.', cause=e)
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""
@ -364,9 +398,19 @@ class InfoExtractor(object):
return content
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
""" Returns the data of the page as a string """
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
success = False
try_count = 0
while success is False:
try:
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
success = True
except compat_http_client.IncompleteRead as e:
try_count += 1
if try_count >= tries:
raise e
self._sleep(timeout, video_id)
if res is False:
return res
else:
@ -394,6 +438,10 @@ class InfoExtractor(object):
url_or_request, video_id, note, errnote, fatal=fatal)
if (not fatal) and json_string is False:
return None
return self._parse_json(
json_string, video_id, transform_source=transform_source, fatal=fatal)
def _parse_json(self, json_string, video_id, transform_source=None, fatal=True):
if transform_source:
json_string = transform_source(json_string)
try:
@ -443,7 +491,7 @@ class InfoExtractor(object):
return video_info
@staticmethod
def playlist_result(entries, playlist_id=None, playlist_title=None):
def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None):
"""Returns a playlist"""
video_info = {'_type': 'playlist',
'entries': entries}
@ -451,6 +499,8 @@ class InfoExtractor(object):
video_info['id'] = playlist_id
if playlist_title:
video_info['title'] = playlist_title
if playlist_description:
video_info['description'] = playlist_description
return video_info
def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
@ -468,7 +518,7 @@ class InfoExtractor(object):
if mobj:
break
if os.name != 'nt' and sys.stderr.isatty():
if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty():
_name = '\033[0;34m%s\033[0m' % name
else:
_name = name
@ -585,9 +635,9 @@ class InfoExtractor(object):
if display_name is None:
display_name = name
return self._html_search_regex(
r'''(?ix)<meta
r'''(?isx)<meta
(?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
[^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
[^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
html, display_name, fatal=fatal, group='content', **kwargs)
def _dc_search_uploader(self, html):
@ -617,6 +667,21 @@ class InfoExtractor(object):
}
return RATING_TABLE.get(rating.lower(), None)
def _family_friendly_search(self, html):
# See http://schema.org/VideoObject
family_friendly = self._html_search_meta('isFamilyFriendly', html)
if not family_friendly:
return None
RATING_TABLE = {
'1': 0,
'true': 0,
'0': 18,
'false': 18,
}
return RATING_TABLE.get(family_friendly.lower(), None)
def _twitter_search_player(self, html):
return self._html_search_meta('twitter:player', html,
'twitter card player')
@ -666,21 +731,40 @@ class InfoExtractor(object):
preference,
f.get('language_preference') if f.get('language_preference') is not None else -1,
f.get('quality') if f.get('quality') is not None else -1,
f.get('tbr') if f.get('tbr') is not None else -1,
f.get('filesize') if f.get('filesize') is not None else -1,
f.get('vbr') if f.get('vbr') is not None else -1,
f.get('height') if f.get('height') is not None else -1,
f.get('width') if f.get('width') is not None else -1,
ext_preference,
f.get('tbr') if f.get('tbr') is not None else -1,
f.get('vbr') if f.get('vbr') is not None else -1,
f.get('abr') if f.get('abr') is not None else -1,
audio_ext_preference,
f.get('fps') if f.get('fps') is not None else -1,
f.get('filesize') if f.get('filesize') is not None else -1,
f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
f.get('source_preference') if f.get('source_preference') is not None else -1,
f.get('format_id'),
)
formats.sort(key=_formats_key)
def _check_formats(self, formats, video_id):
if formats:
formats[:] = filter(
lambda f: self._is_valid_url(
f['url'], video_id,
item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
formats)
def _is_valid_url(self, url, video_id, item='video'):
try:
self._request_webpage(url, video_id, 'Checking %s URL' % item)
return True
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
self.report_warning(
'%s URL is invalid, skipping' % item, video_id)
return False
raise
def http_scheme(self):
""" Either "http:" or "https:", depending on the user's preferences """
return (
@ -728,33 +812,41 @@ class InfoExtractor(object):
self._sort_formats(formats)
return formats
def _extract_f4m_formats(self, manifest_url, video_id):
def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
manifest = self._download_xml(
manifest_url, video_id, 'Downloading f4m manifest',
'Unable to download f4m manifest')
formats = []
manifest_version = '1.0'
media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
if not media_nodes:
manifest_version = '2.0'
media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
for i, media_el in enumerate(media_nodes):
if manifest_version == '2.0':
manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/'
+ (media_el.attrib.get('href') or media_el.attrib.get('url')))
tbr = int_or_none(media_el.attrib.get('bitrate'))
format_id = 'f4m-%d' % (i if tbr is None else tbr)
formats.append({
'format_id': format_id,
'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
'url': manifest_url,
'ext': 'flv',
'tbr': tbr,
'width': int_or_none(media_el.attrib.get('width')),
'height': int_or_none(media_el.attrib.get('height')),
'preference': preference,
})
self._sort_formats(formats)
return formats
def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
entry_protocol='m3u8', preference=None):
entry_protocol='m3u8', preference=None,
m3u8_id=None):
formats = [{
'format_id': 'm3u8-meta',
'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
'url': m3u8_url,
'ext': ext,
'protocol': 'm3u8',
@ -773,6 +865,7 @@ class InfoExtractor(object):
note='Downloading m3u8 information',
errnote='Failed to download m3u8 information')
last_info = None
last_media = None
kv_rex = re.compile(
r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
for line in m3u8_doc.splitlines():
@ -783,6 +876,13 @@ class InfoExtractor(object):
if v.startswith('"'):
v = v[1:-1]
last_info[m.group('key')] = v
elif line.startswith('#EXT-X-MEDIA:'):
last_media = {}
for m in kv_rex.finditer(line):
v = m.group('val')
if v.startswith('"'):
v = v[1:-1]
last_media[m.group('key')] = v
elif line.startswith('#') or not line.strip():
continue
else:
@ -790,9 +890,8 @@ class InfoExtractor(object):
formats.append({'url': format_url(line)})
continue
tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
f = {
'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
'url': format_url(line.strip()),
'tbr': tbr,
'ext': ext,
@ -812,11 +911,60 @@ class InfoExtractor(object):
width_str, height_str = resolution.split('x')
f['width'] = int(width_str)
f['height'] = int(height_str)
if last_media is not None:
f['m3u8_media'] = last_media
last_media = None
formats.append(f)
last_info = {}
self._sort_formats(formats)
return formats
# TODO: improve extraction
def _extract_smil_formats(self, smil_url, video_id, fatal=True):
smil = self._download_xml(
smil_url, video_id, 'Downloading SMIL file',
'Unable to download SMIL file', fatal=fatal)
if smil is False:
assert not fatal
return []
base = smil.find('./head/meta').get('base')
formats = []
rtmp_count = 0
for video in smil.findall('./body/switch/video'):
src = video.get('src')
if not src:
continue
bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
width = int_or_none(video.get('width'))
height = int_or_none(video.get('height'))
proto = video.get('proto')
if not proto:
if base:
if base.startswith('rtmp'):
proto = 'rtmp'
elif base.startswith('http'):
proto = 'http'
ext = video.get('ext')
if proto == 'm3u8':
formats.extend(self._extract_m3u8_formats(src, video_id, ext))
elif proto == 'rtmp':
rtmp_count += 1
streamer = video.get('streamer') or base
formats.append({
'url': streamer,
'play_path': src,
'ext': 'flv',
'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
'tbr': bitrate,
'width': width,
'height': height,
})
self._sort_formats(formats)
return formats
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()
@ -846,10 +994,40 @@ class InfoExtractor(object):
return res
def _set_cookie(self, domain, name, value, expire_time=None):
cookie = compat_cookiejar.Cookie(0, name, value, None, None, domain, None,
cookie = compat_cookiejar.Cookie(
0, name, value, None, None, domain, None,
None, '/', True, False, expire_time, '', None, None, None)
self._downloader.cookiejar.set_cookie(cookie)
def get_testcases(self, include_onlymatching=False):
t = getattr(self, '_TEST', None)
if t:
assert not hasattr(self, '_TESTS'), \
'%s has _TEST and _TESTS' % type(self).__name__
tests = [t]
else:
tests = getattr(self, '_TESTS', [])
for t in tests:
if not include_onlymatching and t.get('only_matching', False):
continue
t['name'] = type(self).__name__[:-len('IE')]
yield t
def is_suitable(self, age_limit):
""" Test whether the extractor is generally suitable for the given
age limit (i.e. pornographic sites are not, all others usually are) """
any_restricted = False
for tc in self.get_testcases(include_onlymatching=False):
if 'playlist' in tc:
tc = tc['playlist'][0]
is_restricted = age_restricted(
tc.get('info_dict', {}).get('age_limit'), age_limit)
if not is_restricted:
return True
any_restricted = any_restricted or is_restricted
return not any_restricted
class SearchInfoExtractor(InfoExtractor):
"""

View File

@ -0,0 +1,46 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import ExtractorError
class CommonMistakesIE(InfoExtractor):
IE_DESC = False # Do not list
_VALID_URL = r'''(?x)
(?:url|URL)
'''
_TESTS = [{
'url': 'url',
'only_matching': True,
}, {
'url': 'URL',
'only_matching': True,
}]
def _real_extract(self, url):
msg = (
'You\'ve asked youtube-dl to download the URL "%s". '
'That doesn\'t make any sense. '
'Simply remove the parameter in your command or configuration.'
) % url
if not self._downloader.params.get('verbose'):
msg += ' Add -v to the command line to see what arguments and configuration youtube-dl got.'
raise ExtractorError(msg, expected=True)
class UnicodeBOMIE(InfoExtractor):
IE_DESC = False
_VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
_TESTS = [{
'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
'only_matching': True,
}]
def _real_extract(self, url):
real_url = self._match_id(url)
self.report_warning(
'Your URL starts with a Byte Order Mark (BOM). '
'Removing the BOM and looking for "%s" ...' % real_url)
return self.url_result(real_url)

View File

@ -5,12 +5,14 @@ import re
import json
from .common import InfoExtractor
from ..utils import (
from ..compat import (
compat_urllib_parse,
orderedSet,
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
orderedSet,
)
class CondeNastIE(InfoExtractor):

View File

@ -10,10 +10,12 @@ import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
ExtractorError,
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
bytes_to_intlist,
intlist_to_bytes,
unified_strdate,
@ -27,10 +29,9 @@ from .common import InfoExtractor
class CrunchyrollIE(SubtitlesInfoExtractor):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_TEST = {
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
#'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
'info_dict': {
'id': '645513',
'ext': 'flv',
@ -45,7 +46,10 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
# rtmp
'skip_download': True,
},
}
}, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True,
}]
_FORMAT_IDS = {
'360': ('60', '106'),
@ -224,7 +228,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
formats = []
for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage):
for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
stream_quality, stream_format = self._FORMAT_IDS[fmt]
video_format = fmt + 'p'
streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/')

View File

@ -27,7 +27,6 @@ class CSpanIE(InfoExtractor):
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
# For whatever reason, the served video alternates between
# two different ones
#'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c',
'info_dict': {
'id': '340723',
'ext': 'mp4',

View File

@ -0,0 +1,93 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import parse_iso8601, ExtractorError
class CtsNewsIE(InfoExtractor):
# https connection failed (Connection reset)
_VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
_TESTS = [{
'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
'md5': 'a9875cb790252b08431186d741beaabe',
'info_dict': {
'id': '201501291578109',
'ext': 'mp4',
'title': '以色列.真主黨交火 3人死亡',
'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
'timestamp': 1422528540,
'upload_date': '20150129',
}
}, {
# News count not appear on page but still available in database
'url': 'http://news.cts.com.tw/cts/international/201309/201309031304098.html',
'md5': '3aee7e0df7cdff94e43581f54c22619e',
'info_dict': {
'id': '201309031304098',
'ext': 'mp4',
'title': '韓國31歲童顏男 貌如十多歲小孩',
'description': 'md5:f183feeba3752b683827aab71adad584',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1378205880,
'upload_date': '20130903',
}
}, {
# With Youtube embedded video
'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
'add_ie': ['Youtube'],
'info_dict': {
'id': 'OVbfO7d0_hQ',
'ext': 'mp4',
'title': 'iPhone6熱銷 蘋果財報亮眼',
'description': 'md5:f395d4f485487bb0f992ed2c4b07aa7d',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20150128',
'uploader_id': 'TBSCTS',
'uploader': '中華電視公司',
}
}]
def _real_extract(self, url):
news_id = self._match_id(url)
page = self._download_webpage(url, news_id)
if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
feed_url = self._html_search_regex(
r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
page, 'feed url')
video_url = self._download_webpage(
feed_url, news_id, note='Fetching feed')
else:
self.to_screen('Not CTSPlayer video, trying Youtube...')
youtube_url = self._search_regex(
r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
default=None)
if not youtube_url:
raise ExtractorError('The news includes no videos!', expected=True)
return {
'_type': 'url',
'url': youtube_url,
'ie_key': 'Youtube',
}
description = self._html_search_meta('description', page)
title = self._html_search_meta('title', page)
thumbnail = self._html_search_meta('image', page)
datetime_str = self._html_search_regex(
r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
# Transform into ISO 8601 format with timezone info
datetime_str = datetime_str.replace('/', '-') + ':00+0800'
timestamp = parse_iso8601(datetime_str, delimiter=' ')
return {
'id': news_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
}

View File

@ -8,13 +8,15 @@ import itertools
from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
compat_urllib_request,
from ..compat import (
compat_str,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
int_or_none,
orderedSet,
str_to_int,
int_or_none,
ExtractorError,
unescapeHTML,
)
@ -192,6 +194,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
'info_dict': {
'title': 'SPORT',
'id': 'xv4bw_nqtv_sport',
},
'playlist_mincount': 20,
}]

View File

@ -5,7 +5,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
from ..compat import (
compat_urllib_parse,
)
@ -38,7 +38,7 @@ class DaumIE(InfoExtractor):
canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
webpage = self._download_webpage(canonical_url, video_id)
full_id = self._search_regex(
r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
r'src=["\']http://videofarm\.daum\.net/controller/video/viewer/Video\.html\?.*?vid=(.+?)[&"\']',
webpage, 'full id')
query = compat_urllib_parse.urlencode({'vid': full_id})
info = self._download_xml(

View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
int_or_none,
@ -61,7 +62,7 @@ class DBTVIE(InfoExtractor):
self._sort_formats(formats)
return {
'id': video['id'],
'id': compat_str(video['id']),
'display_id': display_id,
'title': video['title'],
'description': clean_html(video['desc']),

View File

@ -0,0 +1,61 @@
# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
class DctpTvIE(InfoExtractor):
_VALID_URL = r'http://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
_TEST = {
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
'info_dict': {
'id': '1324',
'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
'ext': 'flv',
'title': 'Videoinstallation für eine Kaufhausfassade'
},
'params': {
# rtmp download
'skip_download': True,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
base_url = 'http://dctp-ivms2-restapi.s3.amazonaws.com/'
version_json = self._download_json(
base_url + 'version.json',
video_id, note='Determining file version')
version = version_json['version_name']
info_json = self._download_json(
'{0}{1}/restapi/slugs/{2}.json'.format(base_url, version, video_id),
video_id, note='Fetching object ID')
object_id = compat_str(info_json['object_id'])
meta_json = self._download_json(
'{0}{1}/restapi/media/{2}.json'.format(base_url, version, object_id),
video_id, note='Downloading metadata')
uuid = meta_json['uuid']
title = meta_json['title']
wide = meta_json['is_wide']
if wide:
ratio = '16x9'
else:
ratio = '4x3'
play_path = 'mp4:{0}_dctp_0500_{1}.m4v'.format(uuid, ratio)
servers_json = self._download_json(
'http://www.dctp.tv/streaming_servers/',
video_id, note='Downloading server list')
url = servers_json[0]['endpoint']
return {
'id': object_id,
'title': title,
'format': 'rtmp',
'url': url,
'play_path': play_path,
'rtmp_real_time': True,
'ext': 'flv',
'display_id': video_id
}

View File

@ -1,40 +1,38 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
class DefenseGouvFrIE(InfoExtractor):
IE_NAME = 'defense.gouv.fr'
_VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
r'ligthboxvideo/base-de-medias/webtv/(.*)')
_VALID_URL = r'http://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
_TEST = {
'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
'file': '11213.mp4',
'md5': '75bba6124da7e63d2d60b5244ec9430c',
"info_dict": {
"title": "attaque-chimique-syrienne-du-21-aout-2013-1"
'info_dict': {
'id': '11213',
'ext': 'mp4',
'title': 'attaque-chimique-syrienne-du-21-aout-2013-1'
}
}
def _real_extract(self, url):
title = re.match(self._VALID_URL, url).group(1)
title = self._match_id(url)
webpage = self._download_webpage(url, title)
video_id = self._search_regex(
r"flashvars.pvg_id=\"(\d+)\";",
webpage, 'ID')
json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
+ video_id)
info = self._download_webpage(json_url, title,
'Downloading JSON config')
video_url = json.loads(info)['renditions'][0]['url']
info = self._download_json(json_url, title, 'Downloading JSON config')
video_url = info['renditions'][0]['url']
return {'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
}
return {
'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
}

View File

@ -1,47 +1,45 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
int_or_none,
)
class DiscoveryIE(InfoExtractor):
_VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
_VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
_TEST = {
'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
'md5': 'e12614f9ee303a6ccef415cb0793eba2',
'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
'info_dict': {
'id': '614784',
'ext': 'mp4',
'title': 'MythBusters: Mission Impossible Outtakes',
'id': 'mission-impossible-outtakes',
'ext': 'flv',
'title': 'Mission Impossible Outtakes',
'description': ('Watch Jamie Hyneman and Adam Savage practice being'
' each other -- to the point of confusing Jamie\'s dog -- and '
'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
' back.'),
'duration': 156,
'timestamp': 1303099200,
'upload_date': '20110418',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_list_json = self._search_regex(r'var videoListJSON = ({.*?});',
webpage, 'video list', flags=re.DOTALL)
video_list = json.loads(video_list_json)
info = video_list['clips'][0]
formats = []
for f in info['mp4']:
formats.append(
{'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
info = self._parse_json(self._search_regex(
r'(?s)<script type="application/ld\+json">(.*?)</script>',
webpage, 'video info'), video_id)
return {
'id': info['contentId'],
'title': video_list['name'],
'formats': formats,
'description': info['videoCaption'],
'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'),
'duration': info['duration'],
'id': video_id,
'title': info['name'],
'url': info['contentURL'],
'description': info.get('description'),
'thumbnail': info.get('thumbnailUrl'),
'timestamp': parse_iso8601(info.get('uploadDate')),
'duration': int_or_none(info.get('duration')),
}

View File

@ -1,13 +1,14 @@
from __future__ import unicode_literals
import re
import time
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
)
class DotsubIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
_TEST = {
'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
'md5': '0914d4d69605090f623b7ac329fea66e',
@ -15,28 +16,37 @@ class DotsubIE(InfoExtractor):
'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
'ext': 'flv',
'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
'description': 'md5:699a0f7f50aeec6042cb3b1db2d0d074',
'thumbnail': 're:^https?://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
'duration': 3169,
'uploader': '4v4l0n42',
'description': 'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
'thumbnail': 'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
'timestamp': 1292248482.625,
'upload_date': '20101213',
'view_count': int,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info_url = "https://dotsub.com/api/media/%s/metadata" % video_id
info = self._download_json(info_url, video_id)
date = time.gmtime(info['dateCreated'] / 1000) # The timestamp is in miliseconds
video_id = self._match_id(url)
info = self._download_json(
'https://dotsub.com/api/media/%s/metadata' % video_id, video_id)
video_url = info.get('mediaURI')
if not video_url:
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'"file"\s*:\s*\'([^\']+)', webpage, 'video url')
return {
'id': video_id,
'url': info['mediaURI'],
'url': video_url,
'ext': 'flv',
'title': info['title'],
'thumbnail': info['screenshotURI'],
'description': info['description'],
'uploader': info['user'],
'view_count': info['numberOfViews'],
'upload_date': '%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
'description': info.get('description'),
'thumbnail': info.get('screenshotURI'),
'duration': int_or_none(info.get('duration'), 1000),
'uploader': info.get('user'),
'timestamp': float_or_none(info.get('dateCreated'), 1000),
'view_count': int_or_none(info.get('numberOfViews')),
}

View File

@ -0,0 +1,131 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
)
class DRBonanzaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
_TESTS = [{
'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
'md5': 'fe330252ddea607635cf2eb2c99a0af3',
'info_dict': {
'id': '65517',
'ext': 'mp4',
'title': 'Talkshowet - Leonard Cohen',
'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
'timestamp': 1295537932,
'upload_date': '20110120',
'duration': 3664,
},
}, {
'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
'md5': '6dfe039417e76795fb783c52da3de11d',
'info_dict': {
'id': '59410',
'ext': 'mp3',
'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
'description': 'md5:501e5a195749480552e214fbbed16c4e',
'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
'timestamp': 1223274900,
'upload_date': '20081006',
'duration': 7369,
},
}]
def _real_extract(self, url):
url_id = self._match_id(url)
webpage = self._download_webpage(url, url_id)
if url_id:
info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
else:
# Just fetch the first video on that page
info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
asset_id = str(info['AssetId'])
title = info['Title'].rstrip(' \'\"-,.:;!?')
duration = int_or_none(info.get('Duration'), scale=1000)
# First published online. "FirstPublished" contains the date for original airing.
timestamp = parse_iso8601(
re.sub(r'\.\d+$', '', info['Created']))
def parse_filename_info(url):
match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
if match:
return {
'width': int(match.group('width')),
'height': int(match.group('height')),
'vbr': int(match.group('bitrate')),
'ext': match.group('ext')
}
match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
if match:
return {
'vbr': int(match.group('bitrate')),
'ext': match.group(2)
}
return {}
video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
preferencemap = {
'VideoHigh': -1,
'VideoMid': -2,
'VideoLow': -3,
'Audio': -4,
}
formats = []
for file in info['Files']:
if info['Type'] == "Video":
if file['Type'] in video_types:
format = parse_filename_info(file['Location'])
format.update({
'url': file['Location'],
'format_id': file['Type'].replace('Video', ''),
'preference': preferencemap.get(file['Type'], -10),
})
formats.append(format)
elif file['Type'] == "Thumb":
thumbnail = file['Location']
elif info['Type'] == "Audio":
if file['Type'] == "Audio":
format = parse_filename_info(file['Location'])
format.update({
'url': file['Location'],
'format_id': file['Type'],
'vcodec': 'none',
})
formats.append(format)
elif file['Type'] == "Thumb":
thumbnail = file['Location']
description = '%s\n%s\n%s\n' % (
info['Description'], info['Actors'], info['Colophon'])
for f in formats:
f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
self._sort_formats(formats)
display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
display_id = re.sub(r'-+', '-', display_id)
return {
'id': asset_id,
'display_id': display_id,
'title': title,
'formats': formats,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
}

Some files were not shown because too many files have changed in this diff Show More