mirror of
https://github.com/l1ving/youtube-dl
synced 2025-01-28 03:03:22 +08:00
Merge branch 'master' of git://github.com/rg3/youtube-dl
This commit is contained in:
Gael Pasgrimaud
commit
106ddc0494
@ -1 +1 @@
|
||||
2012.02.27
|
||||
2012.10.09
|
||||
|
||||
55
Makefile
55
Makefile
@ -1,26 +1,47 @@
|
||||
default: update
|
||||
all: youtube-dl README.md youtube-dl.1 youtube-dl.bash-completion LATEST_VERSION
|
||||
# TODO: re-add youtube-dl.exe, and make sure it's 1. safe and 2. doesn't need sudo
|
||||
|
||||
update: compile update-readme update-latest
|
||||
clean:
|
||||
rm -f youtube-dl youtube-dl.exe youtube-dl.1 LATEST_VERSION
|
||||
|
||||
update-latest:
|
||||
./youtube-dl.dev --version > LATEST_VERSION
|
||||
PREFIX=/usr/local
|
||||
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
|
||||
install -m 755 --owner root --group root youtube-dl $(PREFIX)/bin/
|
||||
install -m 644 --owner root --group root youtube-dl.1 $(PREFIX)/man/man1
|
||||
install -m 644 --owner root --group root youtube-dl.bash-completion /etc/bash_completion.d/youtube-dl
|
||||
|
||||
update-readme:
|
||||
@options=$$(COLUMNS=80 ./youtube-dl.dev --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/### \1/') && \
|
||||
header=$$(sed -e '/.*## OPTIONS/,$$ d' README.md) && \
|
||||
footer=$$(sed -e '1,/.*## FAQ/ d' README.md) && \
|
||||
echo "$${header}" > README.md && \
|
||||
echo >> README.md && \
|
||||
echo '## OPTIONS' >> README.md && \
|
||||
echo "$${options}" >> README.md&& \
|
||||
echo >> README.md && \
|
||||
echo '## FAQ' >> README.md && \
|
||||
echo "$${footer}" >> README.md
|
||||
.PHONY: all clean install README.md youtube-dl.bash-completion
|
||||
# TODO un-phony README.md and youtube-dl.bash_completion by reading from .in files and generating from them
|
||||
|
||||
compile:
|
||||
youtube-dl: youtube_dl/*.py
|
||||
zip --quiet --junk-paths youtube-dl youtube_dl/*.py
|
||||
echo '#!/usr/bin/env python' > youtube-dl
|
||||
cat youtube-dl.zip >> youtube-dl
|
||||
rm youtube-dl.zip
|
||||
chmod a+x youtube-dl
|
||||
|
||||
.PHONY: default compile update update-latest update-readme
|
||||
youtube-dl.exe: youtube_dl/*.py
|
||||
bash devscripts/wine-py2exe.sh build_exe.py
|
||||
|
||||
README.md: youtube_dl/*.py
|
||||
@options=$$(COLUMNS=80 python -m youtube_dl --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/## \1/') && \
|
||||
header=$$(sed -e '/.*# OPTIONS/,$$ d' README.md) && \
|
||||
footer=$$(sed -e '1,/.*# FAQ/ d' README.md) && \
|
||||
echo "$${header}" > README.md && \
|
||||
echo >> README.md && \
|
||||
echo '# OPTIONS' >> README.md && \
|
||||
echo "$${options}" >> README.md&& \
|
||||
echo >> README.md && \
|
||||
echo '# FAQ' >> README.md && \
|
||||
echo "$${footer}" >> README.md
|
||||
|
||||
youtube-dl.1: README.md
|
||||
pandoc -s -w man README.md -o youtube-dl.1
|
||||
|
||||
youtube-dl.bash-completion: README.md
|
||||
@options=`egrep -o '(--[a-z-]+) ' README.md | sort -u | xargs echo` && \
|
||||
content=`sed "s/opts=\"[^\"]*\"/opts=\"$${options}\"/g" youtube-dl.bash-completion` && \
|
||||
echo "$${content}" > youtube-dl.bash-completion
|
||||
|
||||
LATEST_VERSION: youtube_dl/__init__.py
|
||||
python -m youtube_dl --version > LATEST_VERSION
|
||||
|
||||
73
README.md
73
README.md
@ -1,16 +1,19 @@
|
||||
# youtube-dl
|
||||
% youtube-dl(1)
|
||||
|
||||
## USAGE
|
||||
youtube-dl [options] url [url...]
|
||||
# NAME
|
||||
youtube-dl
|
||||
|
||||
## DESCRIPTION
|
||||
# SYNOPSIS
|
||||
**youtube-dl** [OPTIONS] URL [URL...]
|
||||
|
||||
# DESCRIPTION
|
||||
**youtube-dl** is a small command-line program to download videos from
|
||||
YouTube.com and a few more sites. It requires the Python interpreter, version
|
||||
2.x (x being at least 6), and it is not platform specific. It should work in
|
||||
your Unix box, in Windows or in Mac OS X. It is released to the public domain,
|
||||
which means you can modify it, redistribute it or use it however you like.
|
||||
|
||||
## OPTIONS
|
||||
# OPTIONS
|
||||
-h, --help print this help text and exit
|
||||
--version print program version and exit
|
||||
-U, --update update this program to latest version
|
||||
@ -18,10 +21,11 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
-r, --rate-limit LIMIT download rate limit (e.g. 50k or 44.6m)
|
||||
-R, --retries RETRIES number of retries (default is 10)
|
||||
--dump-user-agent display the current browser identification
|
||||
--user-agent UA specify a custom user agent
|
||||
--list-extractors List all supported extractors and the URLs they
|
||||
would handle
|
||||
|
||||
### Video Selection:
|
||||
## Video Selection:
|
||||
--playlist-start NUMBER playlist video to start at (default is 1)
|
||||
--playlist-end NUMBER playlist video to end at (default is last)
|
||||
--match-title REGEX download only matching titles (regex or caseless
|
||||
@ -30,7 +34,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
caseless sub-string)
|
||||
--max-downloads NUMBER Abort after downloading NUMBER files
|
||||
|
||||
### Filesystem Options:
|
||||
## Filesystem Options:
|
||||
-t, --title use title in file name
|
||||
-l, --literal use literal title in file name
|
||||
-A, --auto-number number downloaded files starting from 00000
|
||||
@ -38,9 +42,10 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
title, %(uploader)s for the uploader name,
|
||||
%(autonumber)s to get an automatically incremented
|
||||
number, %(ext)s for the filename extension,
|
||||
%(upload_date)s for the upload date (YYYYMMDD), and
|
||||
%% for a literal percent. Use - to output to
|
||||
stdout.
|
||||
%(upload_date)s for the upload date (YYYYMMDD),
|
||||
%(extractor)s for the provider (youtube, metacafe,
|
||||
etc), %(id)s for the video id and %% for a literal
|
||||
percent. Use - to output to stdout.
|
||||
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
|
||||
-w, --no-overwrites do not overwrite files
|
||||
-c, --continue resume partially downloaded files
|
||||
@ -53,7 +58,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--write-description write video description to a .description file
|
||||
--write-info-json write video metadata to a .info.json file
|
||||
|
||||
### Verbosity / Simulation Options:
|
||||
## Verbosity / Simulation Options:
|
||||
-q, --quiet activates quiet mode
|
||||
-s, --simulate do not download the video and do not write anything
|
||||
to disk
|
||||
@ -68,7 +73,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--console-title display progress in console titlebar
|
||||
-v, --verbose print various debugging information
|
||||
|
||||
### Video Format Options:
|
||||
## Video Format Options:
|
||||
-f, --format FORMAT video format code
|
||||
--all-formats download all available video formats
|
||||
--prefer-free-formats prefer free video formats unless a specific one is
|
||||
@ -80,22 +85,23 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--srt-lang LANG language of the closed captions to download
|
||||
(optional) use IETF language tags like 'en'
|
||||
|
||||
### Authentication Options:
|
||||
## Authentication Options:
|
||||
-u, --username USERNAME account username
|
||||
-p, --password PASSWORD account password
|
||||
-n, --netrc use .netrc authentication data
|
||||
|
||||
### Post-processing Options:
|
||||
## Post-processing Options:
|
||||
--extract-audio convert video files to audio-only files (requires
|
||||
ffmpeg or avconv and ffprobe or avprobe)
|
||||
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", or "wav";
|
||||
best by default
|
||||
--audio-quality QUALITY ffmpeg/avconv audio bitrate specification, 128k by
|
||||
default
|
||||
--audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a
|
||||
value between 0 (better) and 9 (worse) for VBR or a
|
||||
specific bitrate like 128K (default 5)
|
||||
-k, --keep-video keeps the video file on disk after the post-
|
||||
processing; the video is erased by default
|
||||
|
||||
## FAQ
|
||||
# FAQ
|
||||
|
||||
### Can you please put the -b option back?
|
||||
|
||||
@ -117,13 +123,42 @@ The URLs youtube-dl outputs require the downloader to have the correct cookies.
|
||||
|
||||
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`.
|
||||
|
||||
## COPYRIGHT
|
||||
### 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`.
|
||||
|
||||
### SyntaxError: Non-ASCII character ###
|
||||
|
||||
The error
|
||||
|
||||
File "youtube-dl", line 2
|
||||
SyntaxError: Non-ASCII character '\x93' ...
|
||||
|
||||
means you're using an outdated version of Python. Please update to Python 2.6 or 2.7.
|
||||
|
||||
To run youtube-dl under Python 2.5, you'll have to manually check it out like this:
|
||||
|
||||
git clone git://github.com/rg3/youtube-dl.git
|
||||
cd youtube-dl
|
||||
python -m youtube_dl --help
|
||||
|
||||
Please note that Python 2.5 is not supported anymore.
|
||||
|
||||
### What is this binary file? Where has the code gone?
|
||||
|
||||
Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repo to see the code. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make compile`.
|
||||
|
||||
### The exe throws a *Runtime error from Visual C++*
|
||||
|
||||
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).
|
||||
|
||||
# COPYRIGHT
|
||||
|
||||
youtube-dl is released into the public domain by the copyright holders.
|
||||
|
||||
This README file was originally written by Daniel Bolton (<https://github.com/dbbolton>) and is likewise released into the public domain.
|
||||
|
||||
## BUGS
|
||||
# BUGS
|
||||
|
||||
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues>
|
||||
|
||||
|
||||
0
devscripts/posix-locale.sh
Normal file → Executable file
0
devscripts/posix-locale.sh
Normal file → Executable file
11
devscripts/release.sh
Executable file
11
devscripts/release.sh
Executable file
@ -0,0 +1,11 @@
|
||||
#!/bin/sh
|
||||
|
||||
if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
|
||||
version="$1"
|
||||
if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
|
||||
if [ ! -z "`git status --porcelain`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
|
||||
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/__init__.py
|
||||
make all
|
||||
git add -A
|
||||
git commit -m "release $version"
|
||||
git tag -m "Release $version" "$version"
|
||||
0
devscripts/wine-py2exe.sh
Normal file → Executable file
0
devscripts/wine-py2exe.sh
Normal file → Executable file
BIN
test/testvideo-original.mp4
Normal file
BIN
test/testvideo-original.mp4
Normal file
Binary file not shown.
BIN
youtube-dl
BIN
youtube-dl
Binary file not shown.
239
youtube-dl.1
Normal file
239
youtube-dl.1
Normal file
@ -0,0 +1,239 @@
|
||||
.TH youtube-dl 1 ""
|
||||
.SH NAME
|
||||
.PP
|
||||
youtube-dl
|
||||
.SH SYNOPSIS
|
||||
.PP
|
||||
\f[B]youtube-dl\f[] [OPTIONS] URL [URL...]
|
||||
.SH DESCRIPTION
|
||||
.PP
|
||||
\f[B]youtube-dl\f[] is a small command-line program to download videos
|
||||
from YouTube.com and a few more sites.
|
||||
It requires the Python interpreter, version 2.x (x being at least 6),
|
||||
and it is not platform specific.
|
||||
It should work in your Unix box, in Windows or in Mac OS X.
|
||||
It is released to the public domain, which means you can modify it,
|
||||
redistribute it or use it however you like.
|
||||
.SH OPTIONS
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
-h,\ --help\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ this\ help\ text\ and\ exit
|
||||
--version\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ program\ version\ and\ exit
|
||||
-U,\ --update\ \ \ \ \ \ \ \ \ \ \ \ \ update\ this\ program\ to\ latest\ version
|
||||
-i,\ --ignore-errors\ \ \ \ \ \ continue\ on\ download\ errors
|
||||
-r,\ --rate-limit\ LIMIT\ \ \ download\ rate\ limit\ (e.g.\ 50k\ or\ 44.6m)
|
||||
-R,\ --retries\ RETRIES\ \ \ \ number\ of\ retries\ (default\ is\ 10)
|
||||
--dump-user-agent\ \ \ \ \ \ \ \ display\ the\ current\ browser\ identification
|
||||
--user-agent\ UA\ \ \ \ \ \ \ \ \ \ specify\ a\ custom\ user\ agent
|
||||
--list-extractors\ \ \ \ \ \ \ \ List\ all\ supported\ extractors\ and\ the\ URLs\ they
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ would\ handle
|
||||
\f[]
|
||||
.fi
|
||||
.SS Video Selection:
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
--playlist-start\ NUMBER\ \ playlist\ video\ to\ start\ at\ (default\ is\ 1)
|
||||
--playlist-end\ NUMBER\ \ \ \ playlist\ video\ to\ end\ at\ (default\ is\ last)
|
||||
--match-title\ REGEX\ \ \ \ \ \ download\ only\ matching\ titles\ (regex\ or\ caseless
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ sub-string)
|
||||
--reject-title\ REGEX\ \ \ \ \ skip\ download\ for\ matching\ titles\ (regex\ or
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ caseless\ sub-string)
|
||||
--max-downloads\ NUMBER\ \ \ Abort\ after\ downloading\ NUMBER\ files
|
||||
\f[]
|
||||
.fi
|
||||
.SS Filesystem Options:
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
-t,\ --title\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ title\ in\ file\ name
|
||||
-l,\ --literal\ \ \ \ \ \ \ \ \ \ \ \ use\ literal\ title\ in\ file\ name
|
||||
-A,\ --auto-number\ \ \ \ \ \ \ \ number\ downloaded\ files\ starting\ from\ 00000
|
||||
-o,\ --output\ TEMPLATE\ \ \ \ output\ filename\ template.\ Use\ %(stitle)s\ to\ get\ the
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ title,\ %(uploader)s\ for\ the\ uploader\ name,
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(autonumber)s\ to\ get\ an\ automatically\ incremented
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ number,\ %(ext)s\ for\ the\ filename\ extension,
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(upload_date)s\ for\ the\ upload\ date\ (YYYYMMDD),
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(extractor)s\ for\ the\ provider\ (youtube,\ metacafe,
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ etc),\ %(id)s\ for\ the\ video\ id\ and\ %%\ for\ a\ literal
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ percent.\ Use\ -\ to\ output\ to\ stdout.
|
||||
-a,\ --batch-file\ FILE\ \ \ \ file\ containing\ URLs\ to\ download\ (\[aq]-\[aq]\ for\ stdin)
|
||||
-w,\ --no-overwrites\ \ \ \ \ \ do\ not\ overwrite\ files
|
||||
-c,\ --continue\ \ \ \ \ \ \ \ \ \ \ resume\ partially\ downloaded\ files
|
||||
--no-continue\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ resume\ partially\ downloaded\ files\ (restart
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ from\ beginning)
|
||||
--cookies\ FILE\ \ \ \ \ \ \ \ \ \ \ file\ to\ read\ cookies\ from\ and\ dump\ cookie\ jar\ in
|
||||
--no-part\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ .part\ files
|
||||
--no-mtime\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ the\ Last-modified\ header\ to\ set\ the\ file
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ modification\ time
|
||||
--write-description\ \ \ \ \ \ write\ video\ description\ to\ a\ .description\ file
|
||||
--write-info-json\ \ \ \ \ \ \ \ write\ video\ metadata\ to\ a\ .info.json\ file
|
||||
\f[]
|
||||
.fi
|
||||
.SS Verbosity / Simulation Options:
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
-q,\ --quiet\ \ \ \ \ \ \ \ \ \ \ \ \ \ activates\ quiet\ mode
|
||||
-s,\ --simulate\ \ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video\ and\ do\ not\ write\ anything
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ to\ disk
|
||||
--skip-download\ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video
|
||||
-g,\ --get-url\ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ URL
|
||||
-e,\ --get-title\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ title
|
||||
--get-thumbnail\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ thumbnail\ URL
|
||||
--get-description\ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ video\ description
|
||||
--get-filename\ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ filename
|
||||
--get-format\ \ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ format
|
||||
--no-progress\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ print\ progress\ bar
|
||||
--console-title\ \ \ \ \ \ \ \ \ \ display\ progress\ in\ console\ titlebar
|
||||
-v,\ --verbose\ \ \ \ \ \ \ \ \ \ \ \ print\ various\ debugging\ information
|
||||
\f[]
|
||||
.fi
|
||||
.SS Video Format Options:
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
-f,\ --format\ FORMAT\ \ \ \ \ \ video\ format\ code
|
||||
--all-formats\ \ \ \ \ \ \ \ \ \ \ \ download\ all\ available\ video\ formats
|
||||
--prefer-free-formats\ \ \ \ prefer\ free\ video\ formats\ unless\ a\ specific\ one\ is
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ requested
|
||||
--max-quality\ FORMAT\ \ \ \ \ highest\ quality\ format\ to\ download
|
||||
-F,\ --list-formats\ \ \ \ \ \ \ list\ all\ available\ formats\ (currently\ youtube\ only)
|
||||
--write-srt\ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ video\ closed\ captions\ to\ a\ .srt\ file
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (currently\ youtube\ only)
|
||||
--srt-lang\ LANG\ \ \ \ \ \ \ \ \ \ language\ of\ the\ closed\ captions\ to\ download
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (optional)\ use\ IETF\ language\ tags\ like\ \[aq]en\[aq]
|
||||
\f[]
|
||||
.fi
|
||||
.SS Authentication Options:
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
-u,\ --username\ USERNAME\ \ account\ username
|
||||
-p,\ --password\ PASSWORD\ \ account\ password
|
||||
-n,\ --netrc\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ .netrc\ authentication\ data
|
||||
\f[]
|
||||
.fi
|
||||
.SS Post-processing Options:
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
--extract-audio\ \ \ \ \ \ \ \ \ \ convert\ video\ files\ to\ audio-only\ files\ (requires
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ ffmpeg\ or\ avconv\ and\ ffprobe\ or\ avprobe)
|
||||
--audio-format\ FORMAT\ \ \ \ "best",\ "aac",\ "vorbis",\ "mp3",\ "m4a",\ or\ "wav";
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ best\ by\ default
|
||||
--audio-quality\ QUALITY\ \ ffmpeg/avconv\ audio\ quality\ specification,\ insert\ a
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ value\ between\ 0\ (better)\ and\ 9\ (worse)\ for\ VBR\ or\ a
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ specific\ bitrate\ like\ 128K\ (default\ 5)
|
||||
-k,\ --keep-video\ \ \ \ \ \ \ \ \ keeps\ the\ video\ file\ on\ disk\ after\ the\ post-
|
||||
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ processing;\ the\ video\ is\ erased\ by\ default
|
||||
\f[]
|
||||
.fi
|
||||
.SH FAQ
|
||||
.SS Can you please put the -b option back?
|
||||
.PP
|
||||
Most people asking this question are not aware that youtube-dl now
|
||||
defaults to downloading the highest available quality as reported by
|
||||
YouTube, which will be 1080p or 720p in some cases, so you no longer
|
||||
need the -b option.
|
||||
For some specific videos, maybe YouTube does not report them to be
|
||||
available in a specific high quality format you\[aq]\[aq]re interested
|
||||
in.
|
||||
In that case, simply request it with the -f option and youtube-dl will
|
||||
try to download it.
|
||||
.SS I get HTTP error 402 when trying to download a video. What\[aq]s
|
||||
this?
|
||||
.PP
|
||||
Apparently YouTube requires you to pass a CAPTCHA test if you download
|
||||
too much.
|
||||
We\[aq]\[aq]re considering to provide a way to let you solve the
|
||||
CAPTCHA (https://github.com/rg3/youtube-dl/issues/154), but at the
|
||||
moment, your best course of action is pointing a webbrowser to the
|
||||
youtube URL, solving the CAPTCHA, and restart youtube-dl.
|
||||
.SS I have downloaded a video but how can I play it?
|
||||
.PP
|
||||
Once the video is fully downloaded, use any video player, such as
|
||||
vlc (http://www.videolan.org) or mplayer (http://www.mplayerhq.hu/).
|
||||
.SS The links provided by youtube-dl -g are not working anymore
|
||||
.PP
|
||||
The URLs youtube-dl outputs require the downloader to have the correct
|
||||
cookies.
|
||||
Use the \f[C]--cookies\f[] 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
|
||||
\f[C]--dump-user-agent\f[] to see the one in use by youtube-dl.
|
||||
.SS ERROR: no fmt_url_map or conn information found in video info
|
||||
.PP
|
||||
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 \f[C]sudo\ youtube-dl\ --update\f[].
|
||||
.SS ERROR: unable to download video
|
||||
.PP
|
||||
youtube requires an additional signature since September 2012 which is
|
||||
not supported by old versions of youtube-dl.
|
||||
You can update youtube-dl with \f[C]sudo\ youtube-dl\ --update\f[].
|
||||
.SS SyntaxError: Non-ASCII character
|
||||
.PP
|
||||
The error
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
File\ "youtube-dl",\ line\ 2
|
||||
SyntaxError:\ Non-ASCII\ character\ \[aq]\\x93\[aq]\ ...
|
||||
\f[]
|
||||
.fi
|
||||
.PP
|
||||
means you\[aq]re using an outdated version of Python.
|
||||
Please update to Python 2.6 or 2.7.
|
||||
.PP
|
||||
To run youtube-dl under Python 2.5, you\[aq]ll have to manually check it
|
||||
out like this:
|
||||
.IP
|
||||
.nf
|
||||
\f[C]
|
||||
git\ clone\ git://github.com/rg3/youtube-dl.git
|
||||
cd\ youtube-dl
|
||||
python\ -m\ youtube_dl\ --help
|
||||
\f[]
|
||||
.fi
|
||||
.PP
|
||||
Please note that Python 2.5 is not supported anymore.
|
||||
.SS What is this binary file? Where has the code gone?
|
||||
.PP
|
||||
Since June 2012 (#342) youtube-dl is packed as an executable zipfile,
|
||||
simply unzip it (might need renaming to \f[C]youtube-dl.zip\f[] first on
|
||||
some systems) or clone the git repo to see the code.
|
||||
If you modify the code, you can run it by executing the
|
||||
\f[C]__main__.py\f[] file.
|
||||
To recompile the executable, run \f[C]make\ compile\f[].
|
||||
.SS The exe throws a \f[I]Runtime error from Visual C++\f[]
|
||||
.PP
|
||||
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).
|
||||
.SH COPYRIGHT
|
||||
.PP
|
||||
youtube-dl is released into the public domain by the copyright holders.
|
||||
.PP
|
||||
This README file was originally written by Daniel Bolton
|
||||
(<https://github.com/dbbolton>) and is likewise released into the public
|
||||
domain.
|
||||
.SH BUGS
|
||||
.PP
|
||||
Bugs and suggestions should be reported at:
|
||||
<https://github.com/rg3/youtube-dl/issues>
|
||||
.PP
|
||||
Please include:
|
||||
.IP \[bu] 2
|
||||
Your exact command line, like
|
||||
\f[C]youtube-dl\ -t\ "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"\f[].
|
||||
A common mistake is not to escape the \f[C]&\f[].
|
||||
Putting URLs in quotes should solve this problem.
|
||||
.IP \[bu] 2
|
||||
The output of \f[C]youtube-dl\ --version\f[]
|
||||
.IP \[bu] 2
|
||||
The output of \f[C]python\ --version\f[]
|
||||
.IP \[bu] 2
|
||||
The name and version of your Operating System ("Ubuntu 11.04 x64" or
|
||||
"Windows 7 x64" is usually enough).
|
||||
14
youtube-dl.bash-completion
Normal file
14
youtube-dl.bash-completion
Normal file
@ -0,0 +1,14 @@
|
||||
__youtube-dl()
|
||||
{
|
||||
local cur prev opts
|
||||
COMPREPLY=()
|
||||
cur="${COMP_WORDS[COMP_CWORD]}"
|
||||
opts="--all-formats --audio-format --audio-quality --auto-number --batch-file --console-title --continue --cookies --dump-user-agent --extract-audio --format --get-description --get-filename --get-format --get-thumbnail --get-title --get-url --help --ignore-errors --keep-video --list-extractors --list-formats --literal --match-title --max-downloads --max-quality --netrc --no-continue --no-mtime --no-overwrites --no-part --no-progress --output --password --playlist-end --playlist-start --prefer-free-formats --quiet --rate-limit --reject-title --retries --simulate --skip-download --srt-lang --title --update --user-agent --username --verbose --version --write-description --write-info-json --write-srt"
|
||||
|
||||
if [[ ${cur} == * ]] ; then
|
||||
COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )
|
||||
return 0
|
||||
fi
|
||||
}
|
||||
|
||||
complete -F __youtube-dl youtube-dl
|
||||
@ -1,6 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import youtube_dl
|
||||
|
||||
youtube_dl.main()
|
||||
BIN
youtube-dl.exe
BIN
youtube-dl.exe
Binary file not shown.
@ -474,6 +474,7 @@ class FileDownloader(object):
|
||||
# Extract information from URL and process it
|
||||
videos = ie.extract(url)
|
||||
for video in videos or []:
|
||||
video['extractor'] = ie.IE_NAME
|
||||
try:
|
||||
self.increment_downloads()
|
||||
self.process_info(video)
|
||||
|
||||
@ -13,6 +13,8 @@ import urllib
|
||||
import urllib2
|
||||
import email.utils
|
||||
import xml.etree.ElementTree
|
||||
import random
|
||||
import math
|
||||
from urlparse import parse_qs
|
||||
|
||||
try:
|
||||
@ -95,7 +97,25 @@ class InfoExtractor(object):
|
||||
class YoutubeIE(InfoExtractor):
|
||||
"""Information extractor for youtube.com."""
|
||||
|
||||
_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
|
||||
_VALID_URL = r"""^
|
||||
(
|
||||
(?:https?://)? # http(s):// (optional)
|
||||
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
|
||||
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
|
||||
(?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
|
||||
(?: # the various things that can precede the ID:
|
||||
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|
||||
|(?: # or the v= param in all its forms
|
||||
(?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
|
||||
(?:\?|\#!?) # the params delimiter ? or # or #!
|
||||
(?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx)
|
||||
v=
|
||||
)
|
||||
)? # optional -> youtube.com/xxxx is OK
|
||||
)? # all until now is optional -> you can pass the naked ID
|
||||
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
|
||||
(?(1).+)? # if we found the ID, everything can follow
|
||||
$"""
|
||||
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
|
||||
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
|
||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
|
||||
@ -134,6 +154,10 @@ class YoutubeIE(InfoExtractor):
|
||||
}
|
||||
IE_NAME = u'youtube'
|
||||
|
||||
def suitable(self, url):
|
||||
"""Receives a URL and returns True if suitable for this IE."""
|
||||
return re.match(self._VALID_URL, url, re.VERBOSE) is not None
|
||||
|
||||
def report_lang(self):
|
||||
"""Report attempt to set language."""
|
||||
self._downloader.to_screen(u'[youtube] Setting language')
|
||||
@ -268,7 +292,7 @@ class YoutubeIE(InfoExtractor):
|
||||
url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
|
||||
|
||||
# Extract video id from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
@ -402,7 +426,7 @@ class YoutubeIE(InfoExtractor):
|
||||
url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
|
||||
url_data = [parse_qs(uds) for uds in url_data_strs]
|
||||
url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
|
||||
url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
|
||||
url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
|
||||
|
||||
format_limit = self._downloader.params.get('format_limit', None)
|
||||
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
|
||||
@ -592,7 +616,7 @@ class MetacafeIE(InfoExtractor):
|
||||
class DailymotionIE(InfoExtractor):
|
||||
"""Information Extractor for Dailymotion"""
|
||||
|
||||
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
|
||||
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
|
||||
IE_NAME = u'dailymotion'
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
@ -613,9 +637,9 @@ class DailymotionIE(InfoExtractor):
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
|
||||
video_id = mobj.group(1)
|
||||
video_id = mobj.group(1).split('_')[0].split('?')[0]
|
||||
|
||||
video_extension = 'flv'
|
||||
video_extension = 'mp4'
|
||||
|
||||
# Retrieve video webpage to extract further information
|
||||
request = urllib2.Request(url)
|
||||
@ -629,20 +653,29 @@ class DailymotionIE(InfoExtractor):
|
||||
|
||||
# Extract URL, uploader and title from webpage
|
||||
self.report_extraction(video_id)
|
||||
mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
|
||||
mobj = re.search(r'\s*var flashvars = (.*)', webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract media URL')
|
||||
return
|
||||
sequence = urllib.unquote(mobj.group(1))
|
||||
mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract media URL')
|
||||
flashvars = urllib.unquote(mobj.group(1))
|
||||
|
||||
for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
|
||||
if key in flashvars:
|
||||
max_quality = key
|
||||
self._downloader.to_screen(u'[dailymotion] Using %s' % key)
|
||||
break
|
||||
else:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video URL')
|
||||
return
|
||||
mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
|
||||
|
||||
# if needed add http://www.dailymotion.com/ if relative URL
|
||||
mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video URL')
|
||||
return
|
||||
|
||||
video_url = mediaURL
|
||||
video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/')
|
||||
|
||||
# TODO: support choosing qualities
|
||||
|
||||
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
|
||||
if mobj is None:
|
||||
@ -650,17 +683,23 @@ class DailymotionIE(InfoExtractor):
|
||||
return
|
||||
video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
|
||||
|
||||
video_uploader = u'NA'
|
||||
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
||||
return
|
||||
video_uploader = mobj.group(1)
|
||||
self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
|
||||
else:
|
||||
video_uploader = mobj.group(1)
|
||||
|
||||
video_upload_date = u'NA'
|
||||
mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
|
||||
if mobj is not None:
|
||||
video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
|
||||
|
||||
return [{
|
||||
'id': video_id.decode('utf-8'),
|
||||
'url': video_url.decode('utf-8'),
|
||||
'uploader': video_uploader.decode('utf-8'),
|
||||
'upload_date': u'NA',
|
||||
'upload_date': video_upload_date,
|
||||
'title': video_title,
|
||||
'ext': video_extension.decode('utf-8'),
|
||||
'format': u'NA',
|
||||
@ -1469,9 +1508,9 @@ class YahooSearchIE(InfoExtractor):
|
||||
class YoutubePlaylistIE(InfoExtractor):
|
||||
"""Information Extractor for YouTube playlists."""
|
||||
|
||||
_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
|
||||
_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
|
||||
_TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
|
||||
_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=(PL)?%s&'
|
||||
_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&([^&"]+&)*list=.*?%s'
|
||||
_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
|
||||
IE_NAME = u'youtube:playlist'
|
||||
|
||||
@ -1539,6 +1578,56 @@ class YoutubePlaylistIE(InfoExtractor):
|
||||
return
|
||||
|
||||
|
||||
class YoutubeChannelIE(InfoExtractor):
|
||||
"""Information Extractor for YouTube channels."""
|
||||
|
||||
_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
|
||||
_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
|
||||
_MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
|
||||
IE_NAME = u'youtube:channel'
|
||||
|
||||
def report_download_page(self, channel_id, pagenum):
|
||||
"""Report attempt to download channel page with given number."""
|
||||
self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract channel id
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
|
||||
return
|
||||
|
||||
# Download channel pages
|
||||
channel_id = mobj.group(1)
|
||||
video_ids = []
|
||||
pagenum = 1
|
||||
|
||||
while True:
|
||||
self.report_download_page(channel_id, pagenum)
|
||||
url = self._TEMPLATE_URL % (channel_id, pagenum)
|
||||
request = urllib2.Request(url)
|
||||
try:
|
||||
page = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
# Extract video identifiers
|
||||
ids_in_page = []
|
||||
for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
|
||||
if mobj.group(1) not in ids_in_page:
|
||||
ids_in_page.append(mobj.group(1))
|
||||
video_ids.extend(ids_in_page)
|
||||
|
||||
if re.search(self._MORE_PAGES_INDICATOR, page) is None:
|
||||
break
|
||||
pagenum = pagenum + 1
|
||||
|
||||
for id in video_ids:
|
||||
self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
|
||||
return
|
||||
|
||||
|
||||
class YoutubeUserIE(InfoExtractor):
|
||||
"""Information Extractor for YouTube users."""
|
||||
|
||||
@ -2955,3 +3044,314 @@ class MTVIE(InfoExtractor):
|
||||
}
|
||||
|
||||
return [info]
|
||||
|
||||
|
||||
class YoukuIE(InfoExtractor):
|
||||
|
||||
_VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
|
||||
IE_NAME = u'Youku'
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
InfoExtractor.__init__(self, downloader)
|
||||
|
||||
def report_download_webpage(self, file_id):
|
||||
"""Report webpage download."""
|
||||
self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id)
|
||||
|
||||
def report_extraction(self, file_id):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id)
|
||||
|
||||
def _gen_sid(self):
|
||||
nowTime = int(time.time() * 1000)
|
||||
random1 = random.randint(1000,1998)
|
||||
random2 = random.randint(1000,9999)
|
||||
|
||||
return "%d%d%d" %(nowTime,random1,random2)
|
||||
|
||||
def _get_file_ID_mix_string(self, seed):
|
||||
mixed = []
|
||||
source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
|
||||
seed = float(seed)
|
||||
for i in range(len(source)):
|
||||
seed = (seed * 211 + 30031 ) % 65536
|
||||
index = math.floor(seed / 65536 * len(source) )
|
||||
mixed.append(source[int(index)])
|
||||
source.remove(source[int(index)])
|
||||
#return ''.join(mixed)
|
||||
return mixed
|
||||
|
||||
def _get_file_id(self, fileId, seed):
|
||||
mixed = self._get_file_ID_mix_string(seed)
|
||||
ids = fileId.split('*')
|
||||
realId = []
|
||||
for ch in ids:
|
||||
if ch:
|
||||
realId.append(mixed[int(ch)])
|
||||
return ''.join(realId)
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
video_id = mobj.group('ID')
|
||||
|
||||
info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
|
||||
|
||||
request = urllib2.Request(info_url, None, std_headers)
|
||||
try:
|
||||
self.report_download_webpage(video_id)
|
||||
jsondata = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error) as err:
|
||||
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
self.report_extraction(video_id)
|
||||
try:
|
||||
config = json.loads(jsondata)
|
||||
|
||||
video_title = config['data'][0]['title']
|
||||
seed = config['data'][0]['seed']
|
||||
|
||||
format = self._downloader.params.get('format', None)
|
||||
supported_format = config['data'][0]['streamfileids'].keys()
|
||||
|
||||
if format is None or format == 'best':
|
||||
if 'hd2' in supported_format:
|
||||
format = 'hd2'
|
||||
else:
|
||||
format = 'flv'
|
||||
ext = u'flv'
|
||||
elif format == 'worst':
|
||||
format = 'mp4'
|
||||
ext = u'mp4'
|
||||
else:
|
||||
format = 'flv'
|
||||
ext = u'flv'
|
||||
|
||||
|
||||
fileid = config['data'][0]['streamfileids'][format]
|
||||
seg_number = len(config['data'][0]['segs'][format])
|
||||
|
||||
keys=[]
|
||||
for i in xrange(seg_number):
|
||||
keys.append(config['data'][0]['segs'][format][i]['k'])
|
||||
|
||||
#TODO check error
|
||||
#youku only could be viewed from mainland china
|
||||
except:
|
||||
self._downloader.trouble(u'ERROR: unable to extract info section')
|
||||
return
|
||||
|
||||
files_info=[]
|
||||
sid = self._gen_sid()
|
||||
fileid = self._get_file_id(fileid, seed)
|
||||
|
||||
#column 8,9 of fileid represent the segment number
|
||||
#fileid[7:9] should be changed
|
||||
for index, key in enumerate(keys):
|
||||
|
||||
temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
|
||||
download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
|
||||
|
||||
info = {
|
||||
'id': '%s_part%02d' % (video_id, index),
|
||||
'url': download_url,
|
||||
'uploader': None,
|
||||
'title': video_title,
|
||||
'ext': ext,
|
||||
'format': u'NA'
|
||||
}
|
||||
files_info.append(info)
|
||||
|
||||
return files_info
|
||||
|
||||
|
||||
class XNXXIE(InfoExtractor):
|
||||
"""Information extractor for xnxx.com"""
|
||||
|
||||
_VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
|
||||
IE_NAME = u'xnxx'
|
||||
VIDEO_URL_RE = r'flv_url=(.*?)&'
|
||||
VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
|
||||
VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&'
|
||||
|
||||
def report_webpage(self, video_id):
|
||||
"""Report information extraction"""
|
||||
self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
|
||||
|
||||
def report_extraction(self, video_id):
|
||||
"""Report information extraction"""
|
||||
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
|
||||
return
|
||||
video_id = mobj.group(1).decode('utf-8')
|
||||
|
||||
self.report_webpage(video_id)
|
||||
|
||||
# Get webpage content
|
||||
try:
|
||||
webpage = urllib2.urlopen(url).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
|
||||
return
|
||||
|
||||
result = re.search(self.VIDEO_URL_RE, webpage)
|
||||
if result is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video url')
|
||||
return
|
||||
video_url = urllib.unquote(result.group(1).decode('utf-8'))
|
||||
|
||||
result = re.search(self.VIDEO_TITLE_RE, webpage)
|
||||
if result is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video title')
|
||||
return
|
||||
video_title = result.group(1).decode('utf-8')
|
||||
|
||||
result = re.search(self.VIDEO_THUMB_RE, webpage)
|
||||
if result is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
|
||||
return
|
||||
video_thumbnail = result.group(1).decode('utf-8')
|
||||
|
||||
info = {'id': video_id,
|
||||
'url': video_url,
|
||||
'uploader': None,
|
||||
'upload_date': None,
|
||||
'title': video_title,
|
||||
'ext': 'flv',
|
||||
'format': 'flv',
|
||||
'thumbnail': video_thumbnail,
|
||||
'description': None,
|
||||
'player_url': None}
|
||||
|
||||
return [info]
|
||||
|
||||
|
||||
class GooglePlusIE(InfoExtractor):
|
||||
"""Information extractor for plus.google.com."""
|
||||
|
||||
_VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)'
|
||||
IE_NAME = u'plus.google'
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
InfoExtractor.__init__(self, downloader)
|
||||
|
||||
def report_extract_entry(self, url):
|
||||
"""Report downloading extry"""
|
||||
self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8'))
|
||||
|
||||
def report_date(self, upload_date):
|
||||
"""Report downloading extry"""
|
||||
self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
|
||||
|
||||
def report_uploader(self, uploader):
|
||||
"""Report downloading extry"""
|
||||
self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8'))
|
||||
|
||||
def report_title(self, video_title):
|
||||
"""Report downloading extry"""
|
||||
self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8'))
|
||||
|
||||
def report_extract_vid_page(self, video_page):
|
||||
"""Report information extraction."""
|
||||
self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8'))
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract id from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
|
||||
return
|
||||
|
||||
post_url = mobj.group(0)
|
||||
video_id = mobj.group(2)
|
||||
|
||||
video_extension = 'flv'
|
||||
|
||||
# Step 1, Retrieve post webpage to extract further information
|
||||
self.report_extract_entry(post_url)
|
||||
request = urllib2.Request(post_url)
|
||||
try:
|
||||
webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % str(err))
|
||||
return
|
||||
|
||||
# Extract update date
|
||||
upload_date = u'NA'
|
||||
pattern = 'title="Timestamp">(.*?)</a>'
|
||||
mobj = re.search(pattern, webpage)
|
||||
if mobj:
|
||||
upload_date = mobj.group(1)
|
||||
# Convert timestring to a format suitable for filename
|
||||
upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
|
||||
upload_date = upload_date.strftime('%Y%m%d')
|
||||
self.report_date(upload_date)
|
||||
|
||||
# Extract uploader
|
||||
uploader = u'NA'
|
||||
pattern = r'rel\="author".*?>(.*?)</a>'
|
||||
mobj = re.search(pattern, webpage)
|
||||
if mobj:
|
||||
uploader = mobj.group(1)
|
||||
self.report_uploader(uploader)
|
||||
|
||||
# Extract title
|
||||
# Get the first line for title
|
||||
video_title = u'NA'
|
||||
pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
|
||||
mobj = re.search(pattern, webpage)
|
||||
if mobj:
|
||||
video_title = mobj.group(1)
|
||||
self.report_title(video_title)
|
||||
|
||||
# Step 2, Stimulate clicking the image box to launch video
|
||||
pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
|
||||
mobj = re.search(pattern, webpage)
|
||||
if mobj is None:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video page URL')
|
||||
|
||||
video_page = mobj.group(1)
|
||||
request = urllib2.Request(video_page)
|
||||
try:
|
||||
webpage = urllib2.urlopen(request).read()
|
||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
|
||||
return
|
||||
self.report_extract_vid_page(video_page)
|
||||
|
||||
|
||||
# Extract video links on video page
|
||||
"""Extract video links of all sizes"""
|
||||
pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
|
||||
mobj = re.findall(pattern, webpage)
|
||||
if len(mobj) == 0:
|
||||
self._downloader.trouble(u'ERROR: unable to extract video links')
|
||||
|
||||
# Sort in resolution
|
||||
links = sorted(mobj)
|
||||
|
||||
# Choose the lowest of the sort, i.e. highest resolution
|
||||
video_url = links[-1]
|
||||
# Only get the url. The resolution part in the tuple has no use anymore
|
||||
video_url = video_url[-1]
|
||||
# Treat escaped \u0026 style hex
|
||||
video_url = unicode(video_url, "unicode_escape")
|
||||
|
||||
|
||||
return [{
|
||||
'id': video_id.decode('utf-8'),
|
||||
'url': video_url,
|
||||
'uploader': uploader.decode('utf-8'),
|
||||
'upload_date': upload_date.decode('utf-8'),
|
||||
'title': video_title.decode('utf-8'),
|
||||
'ext': video_extension.decode('utf-8'),
|
||||
'format': u'NA',
|
||||
'player_url': None,
|
||||
}]
|
||||
|
||||
@ -71,13 +71,14 @@ class FFmpegExtractAudioPP(PostProcessor):
|
||||
|
||||
@staticmethod
|
||||
def detect_executables():
|
||||
available = {'avprobe' : False, 'avconv' : False, 'ffmpeg' : False, 'ffprobe' : False}
|
||||
for path in os.environ["PATH"].split(os.pathsep):
|
||||
for program in available.keys():
|
||||
exe_file = os.path.join(path, program)
|
||||
if os.path.isfile(exe_file) and os.access(exe_file, os.X_OK):
|
||||
available[program] = exe_file
|
||||
return available
|
||||
def executable(exe):
|
||||
try:
|
||||
subprocess.check_output([exe, '-version'])
|
||||
except OSError:
|
||||
return False
|
||||
return exe
|
||||
programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
|
||||
return dict((program, executable(program)) for program in programs)
|
||||
|
||||
def get_audio_codec(self, path):
|
||||
if not self._exes['ffprobe'] and not self._exes['avprobe']: return None
|
||||
@ -142,14 +143,20 @@ class FFmpegExtractAudioPP(PostProcessor):
|
||||
extension = 'mp3'
|
||||
more_opts = []
|
||||
if self._preferredquality is not None:
|
||||
more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality]
|
||||
if int(self._preferredquality) < 10:
|
||||
more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
|
||||
else:
|
||||
more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality]
|
||||
else:
|
||||
# We convert the audio (lossy)
|
||||
acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
|
||||
extension = self._preferredcodec
|
||||
more_opts = []
|
||||
if self._preferredquality is not None:
|
||||
more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality]
|
||||
if int(self._preferredquality) < 10:
|
||||
more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
|
||||
else:
|
||||
more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality]
|
||||
if self._preferredcodec == 'aac':
|
||||
more_opts += ['-f', 'adts']
|
||||
if self._preferredcodec == 'm4a':
|
||||
|
||||
@ -19,7 +19,7 @@ __authors__ = (
|
||||
)
|
||||
|
||||
__license__ = 'Public Domain'
|
||||
__version__ = '2012.02.27'
|
||||
__version__ = '2012.10.09'
|
||||
|
||||
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
|
||||
UPDATE_URL_VERSION = 'https://raw.github.com/rg3/youtube-dl/master/LATEST_VERSION'
|
||||
@ -186,16 +186,18 @@ def parseOpts():
|
||||
general.add_option('-r', '--rate-limit',
|
||||
dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
|
||||
general.add_option('-R', '--retries',
|
||||
dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
|
||||
dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10)
|
||||
general.add_option('--dump-user-agent',
|
||||
action='store_true', dest='dump_user_agent',
|
||||
help='display the current browser identification', default=False)
|
||||
general.add_option('--user-agent',
|
||||
dest='user_agent', help='specify a custom user agent', metavar='UA')
|
||||
general.add_option('--list-extractors',
|
||||
action='store_true', dest='list_extractors',
|
||||
help='List all supported extractors and the URLs they would handle', default=False)
|
||||
|
||||
selection.add_option('--playlist-start',
|
||||
dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
|
||||
dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is %default)', default=1)
|
||||
selection.add_option('--playlist-end',
|
||||
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
|
||||
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
|
||||
@ -267,7 +269,7 @@ def parseOpts():
|
||||
action='store_true', dest='autonumber',
|
||||
help='number downloaded files starting from 00000', default=False)
|
||||
filesystem.add_option('-o', '--output',
|
||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.')
|
||||
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout.')
|
||||
filesystem.add_option('-a', '--batch-file',
|
||||
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
|
||||
filesystem.add_option('-w', '--no-overwrites',
|
||||
@ -296,8 +298,8 @@ def parseOpts():
|
||||
help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
|
||||
postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
||||
help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default')
|
||||
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
|
||||
help='ffmpeg/avconv audio bitrate specification, 128k by default')
|
||||
postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5',
|
||||
help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)')
|
||||
postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
|
||||
help='keeps the video file on disk after the post-processing; the video is erased by default')
|
||||
|
||||
@ -326,6 +328,7 @@ def gen_extractors():
|
||||
"""
|
||||
return [
|
||||
YoutubePlaylistIE(),
|
||||
YoutubeChannelIE(),
|
||||
YoutubeUserIE(),
|
||||
YoutubeSearchIE(),
|
||||
YoutubeIE(),
|
||||
@ -351,6 +354,9 @@ def gen_extractors():
|
||||
MixcloudIE(),
|
||||
StanfordOpenClassroomIE(),
|
||||
MTVIE(),
|
||||
YoukuIE(),
|
||||
XNXXIE(),
|
||||
GooglePlusIE(),
|
||||
|
||||
GenericIE()
|
||||
]
|
||||
@ -368,6 +374,9 @@ def _real_main():
|
||||
jar.load()
|
||||
except (IOError, OSError), err:
|
||||
sys.exit(u'ERROR: unable to open cookie file')
|
||||
# Set user agent
|
||||
if opts.user_agent is not None:
|
||||
std_headers['User-Agent'] = opts.user_agent
|
||||
|
||||
# Dump user agent
|
||||
if opts.dump_user_agent:
|
||||
@ -444,6 +453,10 @@ def _real_main():
|
||||
if opts.extractaudio:
|
||||
if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a', 'wav']:
|
||||
parser.error(u'invalid audio format specified')
|
||||
if opts.audioquality:
|
||||
opts.audioquality = opts.audioquality.strip('k').strip('K')
|
||||
if not opts.audioquality.isdigit():
|
||||
parser.error(u'invalid audio quality specified')
|
||||
|
||||
# File downloader
|
||||
fd = FileDownloader({
|
||||
|
||||
@ -19,7 +19,7 @@ except ImportError:
|
||||
import StringIO
|
||||
|
||||
std_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
|
||||
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
|
||||
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
|
||||
'Accept-Encoding': 'gzip, deflate',
|
||||
|
||||
Loading…
Reference in New Issue
Block a user