Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-13 23:37:24 +08:00
Code Issues Releases Wiki Activity

Merge remote-tracking branch 'rg3/master' into universalmusicfrance

Browse Source
This commit is contained in:
dabiboo 2015-09-20 09:32:25 +02:00
commit 80f8fbba67
84 changed files with 1855 additions and 804 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
AUTHORS
View File

@ -140,3 +140,6 @@ Behrouz Abbasi
ngld
nyuszika7h
Shaun Walbridge
Lee Jenkins
Anssi Hannula
Lukáš Lalinský

2
CONTRIBUTING.md
View File

@ -125,7 +125,7 @@ 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 and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
7. Have a look at [`youtube_dl/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 and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). 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:

13
README.md
View File

@ -9,6 +9,7 @@ youtube-dl - download videos from youtube.com or other video platforms
- [VIDEO SELECTION](#video-selection)
- [FAQ](#faq)
- [DEVELOPER INSTRUCTIONS](#developer-instructions)
- [EMBEDDING YOUTUBE-DL](#embedding-youtube-dl)
- [BUGS](#bugs)
- [COPYRIGHT](#copyright)
@ -34,7 +35,7 @@ You can also use pip:
sudo pip install youtube-dl
Alternatively, refer to the developer instructions below for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see https://rg3.github.io/youtube-dl/download.html .
# DESCRIPTION
**youtube-dl** is a small command-line program to download videos from
@ -207,7 +208,7 @@ which means you can modify it, redistribute it or use it however you like.
-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)
--video-password PASSWORD Video password (vimeo, smotri, youku)
## Post-processing Options:
-x, --extract-audio Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
@ -261,7 +262,7 @@ For example:
machine youtube login myaccount@gmail.com password my_youtube_password
machine twitch login my_twitch_account_name password my_twitch_password
```
To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or to place it in [configuration file](#configuration).
To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or place it in [configuration file](#configuration).
On Windows you may also need to setup `%HOME%` environment variable manually.
@ -277,8 +278,8 @@ The `-o` option allows users to indicate a template for the output file names. T
- `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
- `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
- `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
- `playlist`: The name or the id of the playlist that contains the video.
- `playlist_index`: The index of the video in the playlist, a five-digit number.
- `playlist`: The sequence will be replaced by the name or the id of the playlist that contains the video.
- `playlist_index`: The sequence will be replaced by the index of the video in the playlist padded with leading zeros according to the total length of the playlist.
- `format_id`: The sequence will be replaced by the format code specified by `--format`.
The current default template is `%(title)s-%(id)s.%(ext)s`.
@ -552,7 +553,7 @@ 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 and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
7. Have a look at [`youtube_dl/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 and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). 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:

10
docs/supportedsites.md
View File

@ -166,7 +166,7 @@
- **Folketinget**: Folketinget (ft.dk; Danish parliament)
- **FootyRoom**
- **Foxgay**
- **FoxNews**
- **FoxNews**: Fox News and Fox Business Video
- **FoxSports**
- **france2.fr:generation-quoi**
- **FranceCulture**
@ -195,7 +195,7 @@
- **GodTube**
- **GoldenMoustache**
- **Golem**
- **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net
- **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com
- **Goshgay**
- **Groupon**
- **Hark**
@ -220,6 +220,7 @@
- **imdb**: Internet Movie Database trailers
- **imdb:list**: Internet Movie Database lists
- **Imgur**
- **ImgurAlbum**
- **Ina**
- **Indavideo**
- **IndavideoEmbed**
@ -303,11 +304,11 @@
- **MPORA**
- **MSNBC**
- **MTV**
- **mtv.de**
- **mtviggy.com**
- **mtvservices:embedded**
- **MuenchenTV**: münchen.tv
- **MusicPlayOn**
- **MusicVault**
- **muzu.tv**
- **Mwave**
- **MySpace**
@ -465,7 +466,7 @@
- **Sexu**
- **SexyKarma**: Sexy Karma and Watch Indian Porn
- **Shahid**
- **Shared**
- **Shared**: shared.sx and vivo.sx
- **ShareSix**
- **Sina**
- **Slideshare**
@ -631,6 +632,7 @@
- **vine:user**
- **vk**: VK
- **vk:uservideos**: VK - User's Videos
- **vlive**
- **Vodlocker**
- **VoiceRepublic**
- **Vporn**

4
test/test_compat.py
View File

@ -14,6 +14,7 @@ from youtube_dl.utils import get_filesystem_encoding
from youtube_dl.compat import (
compat_getenv,
compat_expanduser,
compat_shlex_split,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
@ -67,5 +68,8 @@ class TestCompat(unittest.TestCase):
self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
def test_compat_shlex_split(self):
self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
if __name__ == '__main__':
unittest.main()

76
test/test_utils.py
View File

@ -57,11 +57,16 @@ from youtube_dl.utils import (
urlencode_postdata,
version_tuple,
xpath_with_ns,
xpath_element,
xpath_text,
xpath_attr,
render_table,
match_str,
parse_dfxp_time_expr,
dfxp2srt,
cli_option,
cli_valueless_option,
cli_bool_option,
)
@ -264,6 +269,16 @@ class TestUtil(unittest.TestCase):
self.assertEqual(find('media:song/media:author').text, 'The Author')
self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
def test_xpath_element(self):
doc = xml.etree.ElementTree.Element('root')
div = xml.etree.ElementTree.SubElement(doc, 'div')
p = xml.etree.ElementTree.SubElement(div, 'p')
p.text = 'Foo'
self.assertEqual(xpath_element(doc, 'div/p'), p)
self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
self.assertTrue(xpath_element(doc, 'div/bar') is None)
self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
def test_xpath_text(self):
testxml = '''<root>
<div>
@ -272,9 +287,25 @@ class TestUtil(unittest.TestCase):
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
self.assertTrue(xpath_text(doc, 'div/bar') is None)
self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
def test_xpath_attr(self):
testxml = '''<root>
<div>
<p x="a">Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
def test_smuggle_url(self):
data = {"ö": "ö", "abc": [3]}
url = 'https://foo.bar/baz?x=y#a'
@ -646,6 +677,51 @@ The first line
'''
self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
def test_cli_option(self):
self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
def test_cli_valueless_option(self):
self.assertEqual(cli_valueless_option(
{'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
self.assertEqual(cli_valueless_option(
{'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
self.assertEqual(cli_valueless_option(
{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
self.assertEqual(cli_valueless_option(
{'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
self.assertEqual(cli_valueless_option(
{'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
self.assertEqual(cli_valueless_option(
{'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
def test_cli_bool_option(self):
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
['--no-check-certificate', 'true'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
['--no-check-certificate=true'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
['--check-certificate', 'false'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
['--check-certificate=false'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
['--check-certificate', 'true'])
self.assertEqual(
cli_bool_option(
{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
['--check-certificate=true'])
if __name__ == '__main__':
unittest.main()

2
test/test_write_annotations.py
View File

@ -33,7 +33,7 @@ params = get_params({
TEST_ID = 'gr51aVj-mLg'
ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
ANNOTATIONS_FILE = TEST_ID + '.annotations.xml'
EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']

12
youtube_dl/YoutubeDL.py
View File

@ -69,6 +69,7 @@ from .utils import (
version_tuple,
write_json_file,
write_string,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
prepend_extension,
replace_extension,
@ -284,7 +285,11 @@ class YoutubeDL(object):
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self._err_file = sys.stderr
self.params = params
self.params = {
# Default parameters
'nocheckcertificate': False,
}
self.params.update(params)
self.cache = Cache(self)
if params.get('bidi_workaround', False):
@ -1939,8 +1944,7 @@ class YoutubeDL(object):
if os.access(opts_cookiefile, os.R_OK):
self.cookiejar.load()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(
self.cookiejar)
cookie_processor = YoutubeDLCookieProcessor(self.cookiejar)
if opts_proxy is not None:
if opts_proxy == '':
proxies = {}
@ -2009,7 +2013,7 @@ class YoutubeDL(object):
(info_dict['extractor'], info_dict['id'], thumb_display_id))
try:
uf = self.urlopen(t['url'])
with open(thumb_filename, 'wb') as thumbf:
with open(encodeFilename(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))

6
youtube_dl/__init__.py
View File

@ -9,7 +9,6 @@ import codecs
import io
import os
import random
import shlex
import sys
@ -20,6 +19,7 @@ from .compat import (
compat_expanduser,
compat_getpass,
compat_print,
compat_shlex_split,
workaround_optparse_bug9161,
)
from .utils import (
@ -262,10 +262,10 @@ def _real_main(argv=None):
parser.error('setting filesize xattr requested but python-xattr is not available')
external_downloader_args = None
if opts.external_downloader_args:
external_downloader_args = shlex.split(opts.external_downloader_args)
external_downloader_args = compat_shlex_split(opts.external_downloader_args)
postprocessor_args = None
if opts.postprocessor_args:
postprocessor_args = shlex.split(opts.postprocessor_args)
postprocessor_args = compat_shlex_split(opts.postprocessor_args)
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))

25
youtube_dl/compat.py
View File

@ -5,6 +5,7 @@ import getpass
import optparse
import os
import re
import shlex
import shutil
import socket
import subprocess
@ -79,6 +80,11 @@ try:
except ImportError:
import BaseHTTPServer as compat_http_server
try:
compat_str = unicode # Python 2
except NameError:
compat_str = str
try:
from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
from urllib.parse import unquote as compat_urllib_parse_unquote
@ -99,7 +105,7 @@ except ImportError: # Python 2
# Is it a string-like object?
string.split
return b''
if isinstance(string, unicode):
if isinstance(string, compat_str):
string = string.encode('utf-8')
bits = string.split(b'%')
if len(bits) == 1:
@ -149,11 +155,6 @@ except ImportError: # Python 2
string = string.replace('+', ' ')
return compat_urllib_parse_unquote(string, encoding, errors)
try:
compat_str = unicode # Python 2
except NameError:
compat_str = str
try:
compat_basestring = basestring # Python 2
except NameError:
@ -227,6 +228,17 @@ except ImportError: # Python < 3.3
return "'" + s.replace("'", "'\"'\"'") + "'"
if sys.version_info >= (2, 7, 3):
compat_shlex_split = shlex.split
else:
# Working around shlex issue with unicode strings on some python 2
# versions (see http://bugs.python.org/issue1548891)
def compat_shlex_split(s, comments=False, posix=True):
if isinstance(s, compat_str):
s = s.encode('utf-8')
return shlex.split(s, comments, posix)
def compat_ord(c):
if type(c) is int:
return c
@ -459,6 +471,7 @@ __all__ = [
'compat_ord',
'compat_parse_qs',
'compat_print',
'compat_shlex_split',
'compat_socket_create_connection',
'compat_str',
'compat_subprocess_get_DEVNULL',

28
youtube_dl/downloader/external.py
View File

@ -5,6 +5,10 @@ import subprocess
from .common import FileDownloader
from ..utils import (
cli_option,
cli_valueless_option,
cli_bool_option,
cli_configuration_args,
encodeFilename,
encodeArgument,
)
@ -46,19 +50,16 @@ class ExternalFD(FileDownloader):
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
def _option(self, command_option, param):
param = self.params.get(param)
if param is None:
return []
if isinstance(param, bool):
return [command_option]
return [command_option, param]
return cli_option(self.params, command_option, param)
def _bool_option(self, command_option, param, true_value='true', false_value='false', separator=None):
return cli_bool_option(self.params, command_option, param, true_value, false_value, separator)
def _valueless_option(self, command_option, param, expected_value=True):
return cli_valueless_option(self.params, command_option, param, expected_value)
def _configuration_args(self, default=[]):
ex_args = self.params.get('external_downloader_args')
if ex_args is None:
return default
assert isinstance(ex_args, list)
return ex_args
return cli_configuration_args(self.params, 'external_downloader_args', default)
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
@ -80,6 +81,8 @@ class CurlFD(ExternalFD):
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--interface', 'source_address')
cmd += self._option('--proxy', 'proxy')
cmd += self._valueless_option('--insecure', 'nocheckcertificate')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
@ -102,7 +105,7 @@ class WgetFD(ExternalFD):
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--bind-address', 'source_address')
cmd += self._option('--proxy', 'proxy')
cmd += self._option('--no-check-certificate', 'nocheckcertificate')
cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
@ -121,6 +124,7 @@ class Aria2cFD(ExternalFD):
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--interface', 'source_address')
cmd += self._option('--all-proxy', 'proxy')
cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
cmd += ['--', info_dict['url']]
return cmd

25
youtube_dl/downloader/f4m.py
View File

@ -13,6 +13,8 @@ from ..compat import (
compat_urllib_error,
)
from ..utils import (
encodeFilename,
sanitize_open,
struct_pack,
struct_unpack,
xpath_text,
@ -343,18 +345,19 @@ class F4mFD(FragmentFD):
success = ctx['dl'].download(frag_filename, {'url': url})
if not success:
return False
with open(frag_filename, 'rb') as down:
down_data = down.read()
reader = FlvReader(down_data)
while True:
_, box_type, box_data = reader.read_box_info()
if box_type == b'mdat':
dest_stream.write(box_data)
break
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')
down_data = down.read()
down.close()
reader = FlvReader(down_data)
while True:
_, box_type, box_data = reader.read_box_info()
if box_type == b'mdat':
dest_stream.write(box_data)
break
if live:
os.remove(frag_filename)
os.remove(encodeFilename(frag_sanitized))
else:
frags_filenames.append(frag_filename)
frags_filenames.append(frag_sanitized)
except (compat_urllib_error.HTTPError, ) as err:
if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue
@ -375,6 +378,6 @@ class F4mFD(FragmentFD):
self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(frag_file)
os.remove(encodeFilename(frag_file))
return True

12
youtube_dl/downloader/hls.py
View File

@ -12,6 +12,7 @@ from ..postprocessor.ffmpeg import FFmpegPostProcessor
from ..utils import (
encodeArgument,
encodeFilename,
sanitize_open,
)
@ -30,7 +31,7 @@ class HlsFD(FileDownloader):
args = [
encodeArgument(opt)
for opt in (ffpp.executable, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
args.append(encodeFilename(tmpfilename, True))
args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
self._debug_cmd(args)
@ -89,13 +90,14 @@ class NativeHlsFD(FragmentFD):
success = ctx['dl'].download(frag_filename, {'url': frag_url})
if not success:
return False
with open(frag_filename, 'rb') as down:
ctx['dest_stream'].write(down.read())
frags_filenames.append(frag_filename)
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
ctx['dest_stream'].write(down.read())
down.close()
frags_filenames.append(frag_sanitized)
self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(frag_file)
os.remove(encodeFilename(frag_file))
return True

21
youtube_dl/extractor/__init__.py
View File

@ -138,7 +138,6 @@ from .dump import DumpIE
from .dumpert import DumpertIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .divxstage import DivxStageIE
from .dropbox import DropboxIE
from .eagleplatform import EaglePlatformIE
from .ebaumsworld import EbaumsWorldIE
@ -241,7 +240,10 @@ from .imdb import (
ImdbIE,
ImdbListIE
)
from .imgur import ImgurIE
from .imgur import (
ImgurIE,
ImgurAlbumIE,
)
from .ina import InaIE
from .indavideo import (
IndavideoIE,
@ -340,10 +342,10 @@ from .mtv import (
MTVIE,
MTVServicesEmbeddedIE,
MTVIggyIE,
MTVDEIE,
)
from .muenchentv import MuenchenTVIE
from .musicplayon import MusicPlayOnIE
from .musicvault import MusicVaultIE
from .muzu import MuzuTVIE
from .mwave import MwaveIE
from .myspace import MySpaceIE, MySpaceAlbumIE
@ -364,6 +366,9 @@ from .nbc import (
from .ndr import (
NDRIE,
NJoyIE,
NDREmbedBaseIE,
NDREmbedIE,
NJoyEmbedIE,
)
from .ndtv import NDTVIE
from .netzkino import NetzkinoIE
@ -399,7 +404,11 @@ from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE
from .nova import NovaIE
from .novamov import NovaMovIE
from .nowness import NownessIE
from .nowness import (
NownessIE,
NownessPlaylistIE,
NownessSeriesIE,
)
from .nowtv import NowTVIE
from .nowvideo import NowVideoIE
from .npo import (
@ -429,7 +438,6 @@ from .ooyala import (
OoyalaIE,
OoyalaExternalIE,
)
from .openfilm import OpenFilmIE
from .orf import (
ORFTVthekIE,
ORFOE1IE,
@ -740,6 +748,7 @@ from .vk import (
VKIE,
VKUserVideosIE,
)
from .vlive import VLiveIE
from .vodlocker import VodlockerIE
from .voicerepublic import VoiceRepublicIE
from .vporn import VpornIE
@ -800,7 +809,7 @@ from .youtube import (
YoutubeIE,
YoutubeChannelIE,
YoutubeFavouritesIE,
YoutubeHistoryIE,
#YoutubeHistoryIE,
YoutubePlaylistIE,
YoutubeRecommendedIE,
YoutubeSearchDateIE,

51
youtube_dl/extractor/abc.py
View File

@ -1,16 +1,20 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
js_to_json,
int_or_none,
)
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
'md5': 'cb3dd03b18455a661071ee1e28344d9f',
'info_dict': {
@ -19,22 +23,47 @@ class ABCIE(InfoExtractor):
'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
},
}
}, {
'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
'md5': 'db2a5369238b51f9811ad815b69dc086',
'info_dict': {
'id': 'NvqvPeNZsHU',
'ext': 'mp4',
'upload_date': '20150816',
'uploader': 'ABC News (Australia)',
'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
'uploader_id': 'NewsOnABC',
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
urls_info_json = self._search_regex(
r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls',
flags=re.DOTALL)
urls_info = json.loads(urls_info_json.replace('\'', '"'))
mobj = re.search(
r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
if not isinstance(urls_info, list):
urls_info = [urls_info]
if mobj.group('type') == 'YouTube':
return self.playlist_result([
self.url_result(url_info['url']) for url_info in urls_info])
formats = [{
'url': url_info['url'],
'width': int(url_info['width']),
'height': int(url_info['height']),
'tbr': int(url_info['bitrate']),
'filesize': int(url_info['filesize']),
'width': int_or_none(url_info.get('width')),
'height': int_or_none(url_info.get('height')),
'tbr': int_or_none(url_info.get('bitrate')),
'filesize': int_or_none(url_info.get('filesize')),
} for url_info in urls_info]
self._sort_formats(formats)

2
youtube_dl/extractor/academicearth.py
View File

@ -15,7 +15,7 @@ class AcademicEarthCourseIE(InfoExtractor):
'title': 'Laws of Nature',
'description': 'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.',
},
'playlist_count': 4,
'playlist_count': 3,
}
def _real_extract(self, url):

2
youtube_dl/extractor/adultswim.py
View File

@ -156,7 +156,7 @@ class AdultSwimIE(InfoExtractor):
xpath_text(idoc, './/trt', 'segment duration').strip())
formats = []
file_els = idoc.findall('.//files/file')
file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
for file_el in file_els:
bitrate = file_el.attrib.get('bitrate')

4
youtube_dl/extractor/airmozilla.py
View File

@ -20,14 +20,14 @@ class AirMozillaIE(InfoExtractor):
'id': '6x4q2w',
'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
'thumbnail': 're:https?://vid\.ly/(?P<id>[0-9a-z-]+)/poster',
'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
'timestamp': 1422487800,
'upload_date': '20150128',
'location': 'SFO Commons',
'duration': 3780,
'view_count': int,
'categories': ['Main'],
'categories': ['Main', 'Privacy'],
}
}

1
youtube_dl/extractor/aljazeera.py
View File

@ -16,6 +16,7 @@ class AlJazeeraIE(InfoExtractor):
'uploader': 'Al Jazeera English',
},
'add_ie': ['Brightcove'],
'skip': 'Not accessible from Travis CI server',
}
def _real_extract(self, url):

12
youtube_dl/extractor/arte.py
View File

@ -4,6 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
find_xpath_attr,
unified_strdate,
@ -77,7 +81,13 @@ class ArteTVPlus7IE(InfoExtractor):
def _extract_from_webpage(self, webpage, video_id, lang):
json_url = self._html_search_regex(
[r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'],
webpage, 'json vp url')
webpage, 'json vp url', default=None)
if not json_url:
iframe_url = self._html_search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
webpage, 'iframe url', group='url')
json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
return self._extract_from_json_url(json_url, video_id, lang)
def _extract_from_json_url(self, json_url, video_id, lang):

7
youtube_dl/extractor/bbc.py
View File

@ -21,6 +21,7 @@ class BBCCoUkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
_MEDIASELECTOR_URLS = [
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
]
@ -189,6 +190,12 @@ class BBCCoUkIE(InfoExtractor):
# Skip DASH until supported
elif transfer_format == 'dash':
pass
elif transfer_format == 'hls':
m3u8_formats = self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=supplier, fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
# Direct link
else:
formats.append({

156
youtube_dl/extractor/ceskatelevize.py
View File

@ -17,55 +17,81 @@ from ..utils import (
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
_TESTS = [
{
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
'info_dict': {
'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': {
# m3u8 download
'skip_download': True,
},
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
_TESTS = [{
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
'info_dict': {
'id': '61924494876951776',
'ext': 'mp4',
'title': 'Hyde Park Civilizace',
'description': 'md5:fe93f6eda372d150759d11644ebbfb4a',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 3350,
},
{
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
'info_dict': {
'id': '14716',
'ext': 'mp4',
'title': 'První republika: Zpěvačka z Dupárny Bobina',
'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 88.4,
},
'params': {
# m3u8 download
'skip_download': True,
},
'params': {
# m3u8 download
'skip_download': True,
},
]
}, {
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
'info_dict': {
'id': '61924494876844374',
'ext': 'mp4',
'title': 'První republika: Zpěvačka z Dupárny Bobina',
'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 88.4,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Queer: Bogotart',
'description': 'Alternativní průvodce současným queer světem',
},
'playlist': [{
'info_dict': {
'id': '61924494876844842',
'ext': 'mp4',
'title': 'Queer: Bogotart (Varování 18+)',
'duration': 10.2,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Queer: Bogotart (Queer)',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
playlist_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, playlist_id)
NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
typ = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
episode_id = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
data = {
'playlist[0][type]': typ,
@ -83,7 +109,7 @@ class CeskaTelevizeIE(InfoExtractor):
req.add_header('X-Requested-With', 'XMLHttpRequest')
req.add_header('Referer', url)
playlistpage = self._download_json(req, video_id)
playlistpage = self._download_json(req, playlist_id)
playlist_url = playlistpage['url']
if playlist_url == 'error_region':
@ -92,33 +118,43 @@ class CeskaTelevizeIE(InfoExtractor):
req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url)
playlist = self._download_json(req, video_id)
playlist_title = self._og_search_title(webpage)
playlist_description = self._og_search_description(webpage)
item = playlist['playlist'][0]
formats = []
for format_id, stream_url in item['streamUrls'].items():
formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4'))
self._sort_formats(formats)
playlist = self._download_json(req, playlist_id)['playlist']
playlist_len = len(playlist)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
duration = float_or_none(item.get('duration'))
thumbnail = item.get('previewImageUrl')
entries = []
for item in playlist:
formats = []
for format_id, stream_url in item['streamUrls'].items():
formats.extend(self._extract_m3u8_formats(
stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
self._sort_formats(formats)
subtitles = {}
subs = item.get('subtitles')
if subs:
subtitles = self.extract_subtitles(episode_id, subs)
item_id = item.get('id') or item['assetId']
title = item['title']
return {
'id': episode_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}
duration = float_or_none(item.get('duration'))
thumbnail = item.get('previewImageUrl')
subtitles = {}
if item.get('type') == 'VOD':
subs = item.get('subtitles')
if subs:
subtitles = self.extract_subtitles(episode_id, subs)
entries.append({
'id': item_id,
'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title),
'description': playlist_description if playlist_len == 1 else None,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
})
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
def _get_subtitles(self, episode_id, subs):
original_subtitles = self._download_webpage(

7
youtube_dl/extractor/cinemassacre.py
View File

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor
from ..utils import ExtractorError
from .bliptv import BlipTVIE
from .screenwavemedia import ScreenwaveMediaIE
class CinemassacreIE(InfoExtractor):
@ -83,10 +84,10 @@ class CinemassacreIE(InfoExtractor):
playerdata_url = self._search_regex(
[
r'src="(http://(?:player2\.screenwavemedia\.com|player\.screenwavemedia\.com/play)/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
ScreenwaveMediaIE.EMBED_PATTERN,
r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
],
webpage, 'player data URL', default=None)
webpage, 'player data URL', default=None, group='url')
if not playerdata_url:
playerdata_url = BlipTVIE._extract_url(webpage)
if not playerdata_url:

9
youtube_dl/extractor/clubic.py
View File

@ -12,9 +12,9 @@ from ..utils import (
class ClubicIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P<id>[0-9]+)\.html'
_VALID_URL = r'http://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
_TEST = {
_TESTS = [{
'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
'md5': '1592b694ba586036efac1776b0b43cd3',
'info_dict': {
@ -24,7 +24,10 @@ class ClubicIE(InfoExtractor):
'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
}
}
}, {
'url': 'http://www.clubic.com/video/video-clubic-week-2-0-apple-iphone-6s-et-plus-mais-surtout-le-pencil-469792.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

13
youtube_dl/extractor/common.py
View File

@ -510,6 +510,12 @@ class InfoExtractor(object):
"""Report attempt to log in."""
self.to_screen('Logging in')
@staticmethod
def raise_login_required(msg='This video is only available for registered users'):
raise ExtractorError(
'%s. Use --username and --password or --netrc to provide account credentials.' % msg,
expected=True)
# Methods for following #608
@staticmethod
def url_result(url, ie=None, video_id=None, video_title=None):
@ -725,9 +731,10 @@ class InfoExtractor(object):
@staticmethod
def _hidden_inputs(html):
html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
hidden_inputs = {}
for input in re.findall(r'<input([^>]+)>', html):
if not re.search(r'type=(["\'])hidden\1', input):
for input in re.findall(r'(?i)<input([^>]+)>', html):
if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
continue
name = re.search(r'name=(["\'])(?P<value>.+?)\1', input)
if not name:
@ -740,7 +747,7 @@ class InfoExtractor(object):
def _form_hidden_inputs(self, form_id, html):
form = self._search_regex(
r'(?s)<form[^>]+?id=(["\'])%s\1[^>]*>(?P<form>.+?)</form>' % form_id,
r'(?is)<form[^>]+?id=(["\'])%s\1[^>]*>(?P<form>.+?)</form>' % form_id,
html, '%s form' % form_id, group='form')
return self._hidden_inputs(form)

53
youtube_dl/extractor/crunchyroll.py
View File

@ -20,16 +20,34 @@ from ..utils import (
ExtractorError,
bytes_to_intlist,
intlist_to_bytes,
int_or_none,
remove_end,
unified_strdate,
urlencode_postdata,
xpath_text,
)
from ..aes import (
aes_cbc_decrypt,
)
class CrunchyrollIE(InfoExtractor):
class CrunchyrollBaseIE(InfoExtractor):
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else compat_urllib_request.Request(url_or_request))
# Accept-Language must be set explicitly to accept any language to avoid issues
# similar to https://github.com/rg3/youtube-dl/issues/6797.
# Along with IP address Crunchyroll uses Accept-Language to guess whether georestriction
# should be imposed or not (from what I can see it just takes the first language
# ignoring the priority and requires it to correspond the IP). By the way this causes
# Crunchyroll to not work in georestriction cases in some browsers that don't place
# the locale lang first in header. However allowing any language seems to workaround the issue.
request.add_header('Accept-Language', '*')
return super(CrunchyrollBaseIE, self)._download_webpage(
request, video_id, note, errnote, fatal, tries, timeout, encoding)
class CrunchyrollIE(CrunchyrollBaseIE):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_NETRC_MACHINE = 'crunchyroll'
_TESTS = [{
@ -237,7 +255,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
webpage_url = 'http://www.' + mobj.group('url')
webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, 'trailer-notice', default='')
note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='')
if note_m:
raise ExtractorError(note_m)
@ -247,15 +267,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
if msg.get('type') == 'error':
raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
if 'To view this, please log in to verify you are 18 or older.' in webpage:
self.raise_login_required()
video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
video_title = re.sub(r' {2,}', ' ', video_title)
video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
if not video_description:
video_description = None
video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
video_upload_date = self._html_search_regex(
[r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
if video_upload_date:
video_upload_date = unified_strdate(video_upload_date)
video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
video_uploader = self._html_search_regex(
r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
'video_uploader', fatal=False)
playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
playerdata_req = compat_urllib_request.Request(playerdata_url)
@ -281,6 +308,13 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
stream_info = streamdata.find('./{default}preload/stream_info')
video_url = stream_info.find('./host').text
video_play_path = stream_info.find('./file').text
metadata = stream_info.find('./metadata')
format_info = {
'format': video_format,
'format_id': video_format,
'height': int_or_none(xpath_text(metadata, './height')),
'width': int_or_none(xpath_text(metadata, './width')),
}
if '.fplive.net/' in video_url:
video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
@ -289,19 +323,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
netloc='v.lvlt.crcdn.net',
path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
if self._is_valid_url(direct_video_url, video_id, video_format):
formats.append({
format_info.update({
'url': direct_video_url,
'format_id': video_format,
})
formats.append(format_info)
continue
formats.append({
format_info.update({
'url': video_url,
'play_path': video_play_path,
'ext': 'flv',
'format': video_format,
'format_id': video_format,
})
formats.append(format_info)
subtitles = self.extract_subtitles(video_id, webpage)
@ -317,7 +350,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
}
class CrunchyrollShowPlaylistIE(InfoExtractor):
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
IE_NAME = "crunchyroll:playlist"
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'

4
youtube_dl/extractor/dcn.py
View File

@ -44,8 +44,8 @@ class DCNIE(InfoExtractor):
title = video.get('title_en') or video['title_ar']
webpage = self._download_webpage(
'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?'
+ compat_urllib_parse.urlencode({
'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
compat_urllib_parse.urlencode({
'id': video['id'],
'user_id': video['user_id'],
'signature': video['signature'],

27
youtube_dl/extractor/divxstage.py
View File

@ -1,27 +0,0 @@
from __future__ import unicode_literals
from .novamov import NovaMovIE
class DivxStageIE(NovaMovIE):
IE_NAME = 'divxstage'
IE_DESC = 'DivxStage'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag|to)'}
_HOST = 'www.divxstage.eu'
_FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
_TITLE_REGEX = r'<div class="video_det">\s*<strong>([^<]+)</strong>'
_DESCRIPTION_REGEX = r'<div class="video_det">\s*<strong>[^<]+</strong>\s*<p>([^<]+)</p>'
_TEST = {
'url': 'http://www.divxstage.eu/video/57f238e2e5e01',
'md5': '63969f6eb26533a1968c4d325be63e72',
'info_dict': {
'id': '57f238e2e5e01',
'ext': 'flv',
'title': 'youtubedl test video',
'description': 'This is a test video for youtubedl.',
}
}

10
youtube_dl/extractor/dumpert.py
View File

@ -9,8 +9,8 @@ from ..utils import qualities
class DumpertIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dumpert\.nl/mediabase/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
'info_dict': {
@ -20,11 +20,15 @@ class DumpertIE(InfoExtractor):
'description': 'Niet schrikken hoor',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
}, {
'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
url = 'https://www.dumpert.nl/mediabase/' + video_id
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'nsfw=1; cpc=10')
webpage = self._download_webpage(req, video_id)

2
youtube_dl/extractor/eagleplatform.py
View File

@ -79,7 +79,7 @@ class EaglePlatformIE(InfoExtractor):
age_limit = 0 if age_restriction == 'allow_all' else 18
m3u8_data = self._download_json(
media['sources']['secure_m3u8']['auto'],
self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:'),
video_id, 'Downloading m3u8 JSON')
formats = self._extract_m3u8_formats(

3
youtube_dl/extractor/eroprofile.py
View File

@ -71,8 +71,7 @@ class EroProfileIE(InfoExtractor):
m = re.search(r'You must be logged in to view this video\.', webpage)
if m:
raise ExtractorError(
'This video requires login. Please specify a username and password and try again.', expected=True)
self.raise_login_required('This video requires login')
video_id = self._search_regex(
[r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],

13
youtube_dl/extractor/fc2.py
View File

@ -10,12 +10,13 @@ from ..compat import (
compat_urlparse,
)
from ..utils import (
encode_dict,
ExtractorError,
)
class FC2IE(InfoExtractor):
_VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)'
_VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
IE_NAME = 'fc2'
_NETRC_MACHINE = 'fc2'
_TESTS = [{
@ -37,6 +38,9 @@ class FC2IE(InfoExtractor):
'password': '(snip)',
'skip': 'requires actual password'
}
}, {
'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF',
'only_matching': True,
}]
def _login(self):
@ -52,10 +56,7 @@ class FC2IE(InfoExtractor):
'Submit': ' Login ',
}
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8')
request = compat_urllib_request.Request(
'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
@ -80,7 +81,7 @@ class FC2IE(InfoExtractor):
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
refer = url.replace('/content/', '/a/content/')
refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url
mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()

15
youtube_dl/extractor/foxnews.py
View File

@ -1,5 +1,7 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
@ -8,7 +10,8 @@ from ..utils import (
class FoxNewsIE(InfoExtractor):
_VALID_URL = r'https?://video\.foxnews\.com/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
IE_DESC = 'Fox News and Fox Business Video'
_VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [
{
'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
@ -42,13 +45,19 @@ class FoxNewsIE(InfoExtractor):
'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
'only_matching': True,
},
{
'url': 'http://video.foxbusiness.com/v/4442309889001',
'only_matching': True,
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
host = mobj.group('host')
video = self._download_json(
'http://video.foxnews.com/v/feed/video/%s.js?template=fox' % video_id, video_id)
'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id)
item = video['channel']['item']
title = item['title']

21
youtube_dl/extractor/francetv.py
View File

@ -78,9 +78,14 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
})
self._sort_formats(formats)
title = info['titre']
subtitle = info.get('sous_titre')
if subtitle:
title += ' - %s' % subtitle
return {
'id': video_id,
'title': info['titre'],
'title': title,
'description': clean_html(info['synopsis']),
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
@ -214,15 +219,15 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
},
# france5
{
'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
'md5': '78f0f4064f9074438e660785bbf2c5d9',
'url': 'http://www.france5.fr/emissions/c-a-dire/videos/quels_sont_les_enjeux_de_cette_rentree_politique__31-08-2015_908948?onglet=tous&page=1',
'md5': 'f6c577df3806e26471b3d21631241fd0',
'info_dict': {
'id': '108961659',
'id': '123327454',
'ext': 'flv',
'title': 'C à dire ?!',
'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
'upload_date': '20140915',
'timestamp': 1410795000,
'title': 'C à dire ?! - Quels sont les enjeux de cette rentrée politique ?',
'description': 'md5:4a0d5cb5dce89d353522a84462bae5a4',
'upload_date': '20150831',
'timestamp': 1441035120,
},
},
# franceo

38
youtube_dl/extractor/generic.py
View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import os
import re
import sys
from .common import InfoExtractor
from .youtube import YoutubeIE
@ -48,6 +49,7 @@ from .vimeo import VimeoIE
from .dailymotion import DailymotionCloudIE
from .onionstudios import OnionStudiosIE
from .snagfilms import SnagFilmsEmbedIE
from .screenwavemedia import ScreenwaveMediaIE
class GenericIE(InfoExtractor):
@ -229,6 +231,22 @@ class GenericIE(InfoExtractor):
'skip_download': False,
}
},
{
# redirect in Refresh HTTP header
'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
'info_dict': {
'id': 'pO8h3EaFRdo',
'ext': 'mp4',
'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
'upload_date': '20150917',
'uploader_id': 'brtvofficial',
'uploader': 'Boiler Room',
},
'params': {
'skip_download': False,
},
},
{
'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
@ -1001,6 +1019,16 @@ class GenericIE(InfoExtractor):
'description': 'New experience with Acrobat DC',
'duration': 248.667,
},
},
# ScreenwaveMedia embed
{
'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
'md5': '24ace5baba0d35d55c6810b51f34e9e0',
'info_dict': {
'id': 'cinemasnob-55d26273809dd',
'ext': 'mp4',
'title': 'cinemasnob',
},
}
]
@ -1718,6 +1746,11 @@ class GenericIE(InfoExtractor):
if snagfilms_url:
return self.url_result(snagfilms_url)
# Look for ScreenwaveMedia embeds
mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
if mobj is not None:
return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
# Look for AdobeTVVideo embeds
mobj = re.search(
r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
@ -1781,7 +1814,7 @@ class GenericIE(InfoExtractor):
found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
if not found:
# HTML5 video
found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
if not found:
REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
found = re.search(
@ -1792,6 +1825,9 @@ class GenericIE(InfoExtractor):
# Look also in Refresh HTTP header
refresh_header = head_response.headers.get('Refresh')
if refresh_header:
# In python 2 response HTTP headers are bytestrings
if sys.version_info < (3, 0) and isinstance(refresh_header, str):
refresh_header = refresh_header.decode('iso-8859-1')
found = re.search(REDIRECT_REGEX, refresh_header)
if found:
new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))

11
youtube_dl/extractor/globo.py
View File

@ -13,6 +13,7 @@ from ..compat import (
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
)
@ -359,13 +360,8 @@ class GloboIE(InfoExtractor):
self._API_URL_TEMPLATE % video_id, video_id)['videos'][0]
title = video['title']
duration = float_or_none(video['duration'], 1000)
like_count = video['likes']
uploader = video['channel']
uploader_id = video['channel_id']
formats = []
for resource in video['resources']:
resource_id = resource.get('_id')
if not resource_id:
@ -407,6 +403,11 @@ class GloboIE(InfoExtractor):
self._sort_formats(formats)
duration = float_or_none(video.get('duration'), 1000)
like_count = int_or_none(video.get('likes'))
uploader = video.get('channel')
uploader_id = video.get('channel_id')
return {
'id': video_id,
'title': title,

20
youtube_dl/extractor/gorillavid.py
View File

@ -10,15 +10,16 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
encode_dict,
int_or_none,
)
class GorillaVidIE(InfoExtractor):
IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net'
IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com'
_VALID_URL = r'''(?x)
https?://(?P<host>(?:www\.)?
(?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net))/
(?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com))/
(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
'''
@ -67,13 +68,22 @@ class GorillaVidIE(InfoExtractor):
}, {
'url': 'http://movpod.in/0wguyyxi1yca',
'only_matching': True,
}, {
'url': 'http://filehoot.com/3ivfabn7573c.html',
'info_dict': {
'id': '3ivfabn7573c',
'ext': 'mp4',
'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
'thumbnail': 're:http://.*\.jpg',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id)
url = 'http://%s/%s' % (mobj.group('host'), video_id)
webpage = self._download_webpage(url, video_id)
if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
@ -87,7 +97,7 @@ class GorillaVidIE(InfoExtractor):
if countdown:
self._sleep(countdown, video_id)
post = compat_urllib_parse.urlencode(fields)
post = compat_urllib_parse.urlencode(encode_dict(fields))
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
@ -95,7 +105,7 @@ class GorillaVidIE(InfoExtractor):
webpage = self._download_webpage(req, video_id, 'Downloading video page')
title = self._search_regex(
[r'style="z-index: [0-9]+;">([^<]+)</span>', r'>Watch (.+) '],
[r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'>Watch (.+) '],
webpage, 'title', default=None) or self._og_search_title(webpage)
video_url = self._search_regex(
r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')

27
youtube_dl/extractor/imgur.py
View File

@ -13,7 +13,7 @@ from ..utils import (
class ImgurIE(InfoExtractor):
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!gallery)(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://i.imgur.com/A61SaA1.gifv',
@ -97,3 +97,28 @@ class ImgurIE(InfoExtractor):
'description': self._og_search_description(webpage),
'title': self._og_search_title(webpage),
}
class ImgurAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P<id>[a-zA-Z0-9]+)'
_TEST = {
'url': 'http://imgur.com/gallery/Q95ko',
'info_dict': {
'id': 'Q95ko',
},
'playlist_count': 25,
}
def _real_extract(self, url):
album_id = self._match_id(url)
album_images = self._download_json(
'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id,
album_id)['data']['images']
entries = [
self.url_result('http://imgur.com/%s' % image['hash'])
for image in album_images if image.get('hash')]
return self.playlist_result(entries, album_id)

34
youtube_dl/extractor/kaltura.py
View File

@ -13,12 +13,24 @@ from ..utils import (
class KalturaIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:kaltura:|
https?://(:?(?:www|cdnapisec)\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_
)(?P<partner_id>\d+)
(?::|
/(?:[^/]+/)*?entry_id/
)(?P<id>[0-9a-z_]+)'''
(?:
kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)|
https?://
(:?(?:www|cdnapisec)\.)?kaltura\.com/
(?:
(?:
# flash player
index\.php/kwidget/
(?:[^/]+/)*?wid/_(?P<partner_id>\d+)/
(?:[^/]+/)*?entry_id/(?P<id>[0-9a-z_]+)|
# html5 player
html5/html5lib/
(?:[^/]+/)*?entry_id/(?P<id_html5>[0-9a-z_]+)
.*\?.*\bwid=_(?P<partner_id_html5>\d+)
)
)
)
'''
_API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?'
_TESTS = [
{
@ -43,6 +55,10 @@ class KalturaIE(InfoExtractor):
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3',
'only_matching': True,
},
{
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
'only_matching': True,
}
]
def _kaltura_api_call(self, video_id, actions, *args, **kwargs):
@ -105,9 +121,9 @@ class KalturaIE(InfoExtractor):
video_id, actions, note='Downloading video info JSON')
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
partner_id, entry_id = mobj.group('partner_id'), mobj.group('id')
partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5')
entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5')
info, source_data = self._get_video_info(entry_id, partner_id)
@ -126,7 +142,7 @@ class KalturaIE(InfoExtractor):
self._sort_formats(formats)
return {
'id': video_id,
'id': entry_id,
'title': info['name'],
'formats': formats,
'description': info.get('description'),

3
youtube_dl/extractor/krasview.py
View File

@ -25,6 +25,9 @@ class KrasViewIE(InfoExtractor):
'duration': 27,
'thumbnail': 're:^https?://.*\.jpg',
},
'params': {
'skip_download': 'Not accessible from Travis CI server',
},
}
def _real_extract(self, url):

1
youtube_dl/extractor/kuwo.py
View File

@ -202,6 +202,7 @@ class KuwoSingerIE(InfoExtractor):
'title': 'Ali',
},
'playlist_mincount': 95,
'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
}]
def _real_extract(self, url):

4
youtube_dl/extractor/lynda.py
View File

@ -118,9 +118,7 @@ class LyndaIE(LyndaBaseIE):
'lynda returned error: %s' % video_json['Message'], expected=True)
if video_json['HasAccess'] is False:
raise ExtractorError(
'Video %s is only available for members. '
% video_id + self._ACCOUNT_CREDENTIALS_HINT, expected=True)
self.raise_login_required('Video %s is only available for members' % video_id)
video_id = compat_str(video_json['ID'])
duration = video_json['DurationInSeconds']

2
youtube_dl/extractor/mailru.py
View File

@ -25,6 +25,7 @@ class MailRuIE(InfoExtractor):
'uploader_id': 'sonypicturesrus@mail.ru',
'duration': 184,
},
'skip': 'Not accessible from Travis CI server',
},
{
'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
@ -39,6 +40,7 @@ class MailRuIE(InfoExtractor):
'uploader_id': 'hitech@corp.mail.ru',
'duration': 245,
},
'skip': 'Not accessible from Travis CI server',
},
]

10
youtube_dl/extractor/mit.py
View File

@ -18,12 +18,12 @@ class TechTVMITIE(InfoExtractor):
_TEST = {
'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
'md5': '00a3a27ee20d44bcaa0933ccec4a2cf7',
'info_dict': {
'id': '25418',
'ext': 'mp4',
'title': 'MIT DNA Learning Center Set',
'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
'title': 'MIT DNA and Protein Sets',
'description': 'md5:46f5c69ce434f0a97e7c628cc142802d',
},
}
@ -33,8 +33,8 @@ class TechTVMITIE(InfoExtractor):
'http://techtv.mit.edu/videos/%s' % video_id, video_id)
clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
base_url = self._search_regex(
r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
base_url = self._proto_relative_url(self._search_regex(
r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url'), 'http:')
formats_json = self._search_regex(
r'bitrates: (\[.+?\])', raw_page, 'video formats')
formats_mit = json.loads(formats_json)

107
youtube_dl/extractor/mitele.py
View File

@ -1,74 +1,85 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urlparse,
)
from ..compat import compat_urllib_parse
from ..utils import (
encode_dict,
get_element_by_attribute,
parse_duration,
strip_jsonp,
int_or_none,
)
class MiTeleIE(InfoExtractor):
IE_NAME = 'mitele.es'
IE_DESC = 'mitele.es'
_VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
'md5': 'ace7635b2a0b286aaa37d3ff192d2a8a',
'info_dict': {
'id': '0fce117d',
'ext': 'mp4',
'title': 'Programa 144 - Tor, la web invisible',
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
'id': '0NF1jJnxS1Wu3pHrmvFyw2',
'display_id': 'programa-144',
'ext': 'flv',
'title': 'Tor, la web invisible',
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
'thumbnail': 're:(?i)^https?://.*\.jpg$',
'duration': 2913,
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
episode = self._match_id(url)
webpage = self._download_webpage(url, episode)
embed_data_json = self._search_regex(
r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
).replace('\'', '"')
embed_data = json.loads(embed_data_json)
display_id = self._match_id(url)
domain = embed_data['mediaUrl']
if not domain.startswith('http'):
# only happens in telecinco.es videos
domain = 'http://' + domain
info_url = compat_urlparse.urljoin(
domain,
compat_urllib_parse_unquote(embed_data['flashvars']['host'])
)
info_el = self._download_xml(info_url, episode).find('./video/info')
webpage = self._download_webpage(url, display_id)
video_link = info_el.find('videoUrl/link').text
token_query = compat_urllib_parse.urlencode({'id': video_link})
token_info = self._download_json(
embed_data['flashvars']['ov_tk'] + '?' + token_query,
episode,
transform_source=strip_jsonp
)
formats = self._extract_m3u8_formats(
token_info['tokenizedUrl'], episode, ext='mp4')
config_url = self._search_regex(
r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
config = self._download_json(
config_url, display_id, 'Downloading config JSON')
mmc = self._download_json(
config['services']['mmc'], display_id, 'Downloading mmc JSON')
formats = []
for location in mmc['locations']:
gat = self._proto_relative_url(location.get('gat'), 'http:')
bas = location.get('bas')
loc = location.get('loc')
ogn = location.get('ogn')
if None in (gat, bas, loc, ogn):
continue
token_data = {
'bas': bas,
'icd': loc,
'ogn': ogn,
'sta': '0',
}
media = self._download_json(
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data)).encode('utf-8')),
display_id, 'Downloading %s JSON' % location['loc'])
file_ = media.get('file')
if not file_:
continue
formats.extend(self._extract_f4m_formats(
file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
display_id, f4m_id=loc))
title = self._search_regex(
r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title')
video_id = self._search_regex(
r'data-media-id\s*=\s*"([^"]+)"', webpage,
'data media id', default=None) or display_id
thumbnail = config.get('poster', {}).get('imageUrl')
duration = int_or_none(mmc.get('duration'))
return {
'id': embed_data['videoId'],
'display_id': episode,
'title': info_el.find('title').text,
'formats': formats,
'id': video_id,
'display_id': display_id,
'title': title,
'description': get_element_by_attribute('class', 'text', webpage),
'thumbnail': info_el.find('thumb').text,
'duration': parse_duration(info_el.find('duration').text),
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}

74
youtube_dl/extractor/mtv.py
View File

@ -67,7 +67,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
return [{'url': url, 'ext': 'mp4'}]
def _extract_video_formats(self, mdoc, mtvn_id):
if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None:
if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:
if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
self.to_screen('The normal version is not available from your '
'country, trying with the mobile version')
@ -114,7 +114,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
# Remove the templates, like &device={device}
mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
if 'acceptMethods' not in mediagen_url:
mediagen_url += '&acceptMethods=fms'
mediagen_url += '&' if '?' in mediagen_url else '?'
mediagen_url += 'acceptMethods=fms'
mediagen_doc = self._download_xml(mediagen_url, video_id,
'Downloading video urls')
@ -141,7 +142,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
if title_el is None:
title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
if title_el is None:
title_el = itemdoc.find('.//title')
title_el = itemdoc.find('.//title') or itemdoc.find('./title')
if title_el.text is None:
title_el = None
@ -174,8 +175,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
if self._LANG:
info_url += 'lang=%s&' % self._LANG
info_url += data
return self._get_videos_info_from_url(info_url, video_id)
def _get_videos_info_from_url(self, url, video_id):
idoc = self._download_xml(
info_url, video_id,
url, video_id,
'Downloading info', transform_source=fix_xml_ampersands)
return self.playlist_result(
[self._get_video_info(item) for item in idoc.findall('.//item')])
@ -288,3 +292,65 @@ class MTVIggyIE(MTVServicesInfoExtractor):
}
}
_FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'
class MTVDEIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv.de'
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
_TESTS = [{
'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
'info_dict': {
'id': 'music_video-a50bc5f0b3aa4b3190aa',
'ext': 'mp4',
'title': 'MusicVideo_cro-traum',
'description': 'Cro - Traum',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
# mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
'info_dict': {
'id': 'local_playlist-f5ae778b9832cc837189',
'ext': 'mp4',
'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
# single video in pagePlaylist with different id
'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
'info_dict': {
'id': 'local_playlist-4e760566473c4c8c5344',
'ext': 'mp4',
'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1',
'description': 'MTV Movies Supercut',
},
'params': {
# rtmp download
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist = self._parse_json(
self._search_regex(
r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
video_id)
# news pages contain single video in playlist with different id
if len(playlist) == 1:
return self._get_videos_info_from_url(playlist[0]['mrss'], video_id)
for item in playlist:
item_id = item.get('id')
if item_id and compat_str(item_id) == video_id:
return self._get_videos_info_from_url(item['mrss'], video_id)

63
youtube_dl/extractor/musicvault.py
View File

@ -1,63 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class MusicVaultIE(InfoExtractor):
_VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html'
_TEST = {
'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html',
'md5': '3adcbdb3dcc02d647539e53f284ba171',
'info_dict': {
'id': '1010863',
'ext': 'mp4',
'uploader_id': 'the-allman-brothers-band',
'title': 'Straight from the Heart',
'duration': 244,
'uploader': 'The Allman Brothers Band',
'thumbnail': 're:^https?://.*/thumbnail/.*',
'upload_date': '20131219',
'location': 'Capitol Theatre (Passaic, NJ)',
'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981',
'timestamp': int,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
thumbnail = self._search_regex(
r'<meta itemprop="thumbnail" content="([^"]+)"',
webpage, 'thumbnail', fatal=False)
data_div = self._search_regex(
r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields')
uploader = self._html_search_regex(
r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False)
title = self._html_search_regex(
r'<h2.*?>(.*?)</h2>', data_div, 'title')
location = self._html_search_regex(
r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False)
kaltura_id = self._search_regex(
r'<div id="video-detail-player" data-kaltura-id="([^"]+)"',
webpage, 'kaltura ID')
wid = self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid')
return {
'id': mobj.group('id'),
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (wid, kaltura_id),
'ie_key': 'Kaltura',
'display_id': display_id,
'uploader_id': mobj.group('uploader_id'),
'thumbnail': thumbnail,
'description': self._html_search_meta('description', webpage),
'location': location,
'title': title,
'uploader': uploader,
}

452
youtube_dl/extractor/ndr.py
View File

@ -1,130 +1,380 @@
# encoding: utf-8
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
parse_iso8601,
qualities,
parse_duration,
)
class NDRBaseIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page = self._download_webpage(url, video_id, 'Downloading page')
title = self._og_search_title(page).strip()
description = self._og_search_description(page)
if description:
description = description.strip()
duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', default=None))
if not duration:
duration = parse_duration(self._html_search_regex(
r'(<span class="min">\d+</span>:<span class="sec">\d+</span>)',
page, 'duration', default=None))
formats = []
mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
if mp3_url:
formats.append({
'url': mp3_url.group('audio'),
'format_id': 'mp3',
})
thumbnail = None
video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.(lo|hi|hq)\.mp4', type:"video/mp4"},''', page)
if video_url:
thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
if thumbnails:
quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
thumbnail = 'http://www.ndr.de' + largest[0]
for format_id in 'lo', 'hi', 'hq':
formats.append({
'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
'format_id': format_id,
})
if not formats:
raise ExtractorError('No media links available for %s' % video_id)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
return self._extract_embed(webpage, display_id)
class NDRIE(NDRBaseIE):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Mediathek'
_VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
_TESTS = [{
# httpVideo, same content id
'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
'md5': '6515bc255dc5c5f8c85bbc38e035a659',
'info_dict': {
'id': 'hafengeburtstag988',
'display_id': 'Party-Poette-und-Parade',
'ext': 'mp4',
'title': 'Party, Pötte und Parade',
'description': 'md5:ad14f9d2f91d3040b6930c697e5f6b4c',
'uploader': 'ndrtv',
'timestamp': 1431108900,
'upload_date': '20150510',
'duration': 3498,
},
'params': {
'skip_download': True,
},
}, {
# httpVideo, different content id
'url': 'http://www.ndr.de/sport/fussball/40-Osnabrueck-spielt-sich-in-einen-Rausch,osna270.html',
'md5': '1043ff203eab307f0c51702ec49e9a71',
'info_dict': {
'id': 'osna272',
'display_id': '40-Osnabrueck-spielt-sich-in-einen-Rausch',
'ext': 'mp4',
'title': 'Osnabrück - Wehen Wiesbaden: Die Highlights',
'description': 'md5:32e9b800b3d2d4008103752682d5dc01',
'uploader': 'ndrtv',
'timestamp': 1442059200,
'upload_date': '20150912',
'duration': 510,
},
'params': {
'skip_download': True,
},
}, {
# httpAudio, same content id
'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html',
'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
'info_dict': {
'id': 'audio51535',
'display_id': 'La-Valette-entgeht-der-Hinrichtung',
'ext': 'mp3',
'title': 'La Valette entgeht der Hinrichtung',
'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
'uploader': 'ndrinfo',
'timestamp': 1290626100,
'upload_date': '20140729',
'duration': 884,
},
'params': {
'skip_download': True,
},
}]
_TESTS = [
{
'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html',
'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c',
'note': 'Video file',
'info_dict': {
'id': '25866',
'ext': 'mp4',
'title': 'Kartoffeltage in der Lewitz',
'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8',
'duration': 166,
},
'skip': '404 Not found',
},
{
'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
'md5': 'dadc003c55ae12a5d2f6bd436cd73f59',
'info_dict': {
'id': '988',
'ext': 'mp4',
'title': 'Party, Pötte und Parade',
'description': 'Hunderttausende feiern zwischen Speicherstadt und St. Pauli den 826. Hafengeburtstag. Die NDR Sondersendung zeigt die schönsten und spektakulärsten Bilder vom Auftakt.',
'duration': 3498,
},
},
{
'url': 'http://www.ndr.de/info/audio51535.html',
'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
'note': 'Audio file',
'info_dict': {
'id': '51535',
'ext': 'mp3',
'title': 'La Valette entgeht der Hinrichtung',
'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
'duration': 884,
}
def _extract_embed(self, webpage, display_id):
embed_url = self._html_search_meta(
'embedURL', webpage, 'embed URL', fatal=True)
description = self._search_regex(
r'<p[^>]+itemprop="description">([^<]+)</p>',
webpage, 'description', fatal=False)
timestamp = parse_iso8601(
self._search_regex(
r'<span itemprop="datePublished" content="([^"]+)">',
webpage, 'upload date', fatal=False))
return {
'_type': 'url_transparent',
'url': embed_url,
'display_id': display_id,
'description': description,
'timestamp': timestamp,
}
]
class NJoyIE(NDRBaseIE):
IE_NAME = 'N-JOY'
_VALID_URL = r'https?://www\.n-joy\.de/.+?(?P<id>\d+)\.html'
_TEST = {
IE_NAME = 'njoy'
IE_DESC = 'N-JOY'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
_TESTS = [{
# httpVideo, same content id
'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
'md5': 'cb63be60cd6f9dd75218803146d8dc67',
'info_dict': {
'id': '2480',
'id': 'comedycontest2480',
'display_id': 'Benaissa-beim-NDR-Comedy-Contest',
'ext': 'mp4',
'title': 'Benaissa beim NDR Comedy Contest',
'description': 'Von seinem sehr "behaarten" Leben lässt sich Benaissa trotz aller Schwierigkeiten nicht unterkriegen.',
'description': 'md5:f057a6c4e1c728b10d33b5ffd36ddc39',
'uploader': 'ndrtv',
'upload_date': '20141129',
'duration': 654,
},
'params': {
'skip_download': True,
},
}, {
# httpVideo, different content id
'url': 'http://www.n-joy.de/musik/Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-,felixjaehn168.html',
'md5': '417660fffa90e6df2fda19f1b40a64d8',
'info_dict': {
'id': 'dockville882',
'display_id': 'Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-',
'ext': 'mp4',
'title': '"Ich hab noch nie" mit Felix Jaehn',
'description': 'md5:85dd312d53be1b99e1f998a16452a2f3',
'uploader': 'njoy',
'upload_date': '20150822',
'duration': 211,
},
'params': {
'skip_download': True,
},
}]
def _extract_embed(self, webpage, display_id):
video_id = self._search_regex(
r'<iframe[^>]+id="pp_([\da-z]+)"', webpage, 'embed id')
description = self._search_regex(
r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>',
webpage, 'description', fatal=False)
return {
'_type': 'url_transparent',
'ie_key': 'NDREmbedBase',
'url': 'ndr:%s' % video_id,
'display_id': display_id,
'description': description,
}
}
class NDREmbedBaseIE(InfoExtractor):
IE_NAME = 'ndr:embed:base'
_VALID_URL = r'(?:ndr:(?P<id_s>[\da-z]+)|https?://www\.ndr\.de/(?P<id>[\da-z]+)-ppjson\.json)'
_TESTS = [{
'url': 'ndr:soundcheck3366',
'only_matching': True,
}, {
'url': 'http://www.ndr.de/soundcheck3366-ppjson.json',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') or mobj.group('id_s')
ppjson = self._download_json(
'http://www.ndr.de/%s-ppjson.json' % video_id, video_id)
playlist = ppjson['playlist']
formats = []
quality_key = qualities(('xs', 's', 'm', 'l', 'xl'))
for format_id, f in playlist.items():
src = f.get('src')
if not src:
continue
ext = determine_ext(src, None)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, f4m_id='hds'))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
src, video_id, m3u8_id='hls', entry_protocol='m3u8_native'))
else:
quality = f.get('quality')
ff = {
'url': src,
'format_id': quality or format_id,
'quality': quality_key(quality),
}
type_ = f.get('type')
if type_ and type_.split('/')[0] == 'audio':
ff['vcodec'] = 'none'
ff['ext'] = ext or 'mp3'
formats.append(ff)
self._sort_formats(formats)
config = playlist['config']
live = playlist.get('config', {}).get('streamType') in ['httpVideoLive', 'httpAudioLive']
title = config['title']
if live:
title = self._live_title(title)
uploader = ppjson.get('config', {}).get('branding')
upload_date = ppjson.get('config', {}).get('publicationDate')
duration = int_or_none(config.get('duration'))
thumbnails = [{
'id': thumbnail.get('quality') or thumbnail_id,
'url': thumbnail['src'],
'preference': quality_key(thumbnail.get('quality')),
} for thumbnail_id, thumbnail in config.get('poster', {}).items() if thumbnail.get('src')]
return {
'id': video_id,
'title': title,
'is_live': live,
'uploader': uploader if uploader != '-' else None,
'upload_date': upload_date[0:8] if upload_date else None,
'duration': duration,
'thumbnails': thumbnails,
'formats': formats,
}
class NDREmbedIE(NDREmbedBaseIE):
IE_NAME = 'ndr:embed'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
_TESTS = [{
'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
'info_dict': {
'id': 'ndraktuell28488',
'ext': 'mp4',
'title': 'Norddeutschland begrüßt Flüchtlinge',
'is_live': False,
'uploader': 'ndrtv',
'upload_date': '20150907',
'duration': 132,
},
}, {
'url': 'http://www.ndr.de/ndr2/events/soundcheck/soundcheck3366-player.html',
'md5': '002085c44bae38802d94ae5802a36e78',
'info_dict': {
'id': 'soundcheck3366',
'ext': 'mp4',
'title': 'Ella Henderson braucht Vergleiche nicht zu scheuen',
'is_live': False,
'uploader': 'ndr2',
'upload_date': '20150912',
'duration': 3554,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.ndr.de/info/audio51535-player.html',
'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
'info_dict': {
'id': 'audio51535',
'ext': 'mp3',
'title': 'La Valette entgeht der Hinrichtung',
'is_live': False,
'uploader': 'ndrinfo',
'upload_date': '20140729',
'duration': 884,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.ndr.de/fernsehen/sendungen/visite/visite11010-externalPlayer.html',
'md5': 'ae57f80511c1e1f2fd0d0d3d31aeae7c',
'info_dict': {
'id': 'visite11010',
'ext': 'mp4',
'title': 'Visite - die ganze Sendung',
'is_live': False,
'uploader': 'ndrtv',
'upload_date': '20150902',
'duration': 3525,
},
'params': {
'skip_download': True,
},
}, {
# httpVideoLive
'url': 'http://www.ndr.de/fernsehen/livestream/livestream217-externalPlayer.html',
'info_dict': {
'id': 'livestream217',
'ext': 'flv',
'title': 're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
'upload_date': '20150910',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.ndr.de/ndrkultur/audio255020-player.html',
'only_matching': True,
}, {
'url': 'http://www.ndr.de/fernsehen/sendungen/nordtour/nordtour7124-player.html',
'only_matching': True,
}, {
'url': 'http://www.ndr.de/kultur/film/videos/videoimport10424-player.html',
'only_matching': True,
}, {
'url': 'http://www.ndr.de/fernsehen/sendungen/hamburg_journal/hamj43006-player.html',
'only_matching': True,
}, {
'url': 'http://www.ndr.de/fernsehen/sendungen/weltbilder/weltbilder4518-player.html',
'only_matching': True,
}, {
'url': 'http://www.ndr.de/fernsehen/doku952-player.html',
'only_matching': True,
}]
class NJoyEmbedIE(NDREmbedBaseIE):
IE_NAME = 'njoy:embed'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
_TESTS = [{
# httpVideo
'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',
'md5': '8483cbfe2320bd4d28a349d62d88bd74',
'info_dict': {
'id': 'doku948',
'ext': 'mp4',
'title': 'Zehn Jahre Reeperbahn Festival - die Doku',
'is_live': False,
'upload_date': '20150807',
'duration': 1011,
},
}, {
# httpAudio
'url': 'http://www.n-joy.de/news_wissen/stefanrichter100-player_image-d5e938b1-f21a-4b9a-86b8-aaba8bca3a13_theme-n-joy.html',
'md5': 'd989f80f28ac954430f7b8a48197188a',
'info_dict': {
'id': 'stefanrichter100',
'ext': 'mp3',
'title': 'Interview mit einem Augenzeugen',
'is_live': False,
'uploader': 'njoy',
'upload_date': '20150909',
'duration': 140,
},
'params': {
'skip_download': True,
},
}, {
# httpAudioLive, no explicit ext
'url': 'http://www.n-joy.de/news_wissen/webradioweltweit100-player_image-3fec0484-2244-4565-8fb8-ed25fd28b173_theme-n-joy.html',
'info_dict': {
'id': 'webradioweltweit100',
'ext': 'mp3',
'title': 're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
'uploader': 'njoy',
'upload_date': '20150810',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.n-joy.de/musik/dockville882-player_image-3905259e-0803-4764-ac72-8b7de077d80a_theme-n-joy.html',
'only_matching': True,
}, {
'url': 'http://www.n-joy.de/radio/sendungen/morningshow/urlaubsfotos190-player_image-066a5df1-5c95-49ec-a323-941d848718db_theme-n-joy.html',
'only_matching': True,
}, {
'url': 'http://www.n-joy.de/entertainment/comedy/krudetv290-player_image-ab261bfe-51bf-4bf3-87ba-c5122ee35b3d_theme-n-joy.html',
'only_matching': True,
}]

6
youtube_dl/extractor/niconico.py
View File

@ -12,6 +12,7 @@ from ..compat import (
compat_urlparse,
)
from ..utils import (
encode_dict,
ExtractorError,
int_or_none,
parse_duration,
@ -100,10 +101,7 @@ class NiconicoIE(InfoExtractor):
'mail': username,
'password': password,
}
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8')
request = compat_urllib_request.Request(
'https://secure.nicovideo.jp/secure/login', login_data)
login_results = self._download_webpage(

166
youtube_dl/extractor/nowness.py
View File

@ -1,64 +1,134 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .brightcove import BrightcoveIE
from .common import InfoExtractor
from ..utils import ExtractorError
from ..compat import (
compat_str,
compat_urllib_request,
)
class NownessIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])'
class NownessBaseIE(InfoExtractor):
def _extract_url_result(self, post):
if post['type'] == 'video':
for media in post['media']:
if media['type'] == 'video':
video_id = media['content']
source = media['source']
if source == 'brightcove':
player_code = self._download_webpage(
'http://www.nowness.com/iframe?id=%s' % video_id, video_id,
note='Downloading player JavaScript',
errnote='Unable to download player JavaScript')
bc_url = BrightcoveIE._extract_brightcove_url(player_code)
if bc_url is None:
raise ExtractorError('Could not find player definition')
return self.url_result(bc_url, 'Brightcove')
elif source == 'vimeo':
return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
elif source == 'youtube':
return self.url_result(video_id, 'Youtube')
elif source == 'cinematique':
# youtube-dl currently doesn't support cinematique
# return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique')
pass
_TESTS = [
{
'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
'md5': '068bc0202558c2e391924cb8cc470676',
'info_dict': {
'id': '2520295746001',
'ext': 'mp4',
'title': 'Candor: The Art of Gesticulation',
'description': 'Candor: The Art of Gesticulation',
'thumbnail': 're:^https?://.*\.jpg',
'uploader': 'Nowness',
}
def _api_request(self, url, request_path):
display_id = self._match_id(url)
request = compat_urllib_request.Request(
'http://api.nowness.com/api/' + request_path % display_id,
headers={
'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us',
})
return display_id, self._download_json(request, display_id)
class NownessIE(NownessBaseIE):
IE_NAME = 'nowness'
_VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P<id>[^/]+?)(?:$|[?#])'
_TESTS = [{
'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation',
'md5': '068bc0202558c2e391924cb8cc470676',
'info_dict': {
'id': '2520295746001',
'ext': 'mp4',
'title': 'Candor: The Art of Gesticulation',
'description': 'Candor: The Art of Gesticulation',
'thumbnail': 're:^https?://.*\.jpg',
'uploader': 'Nowness',
},
{
'url': 'http://cn.nowness.com/day/2014/8/7/4069/kasper-bj-rke-ft-jaakko-eino-kalevi--tnr',
'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
'info_dict': {
'id': '3716354522001',
'ext': 'mp4',
'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'thumbnail': 're:^https?://.*\.jpg',
'uploader': 'Nowness',
}
}, {
'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
'info_dict': {
'id': '3716354522001',
'ext': 'mp4',
'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'thumbnail': 're:^https?://.*\.jpg',
'uploader': 'Nowness',
},
]
}, {
# vimeo
'url': 'https://www.nowness.com/series/nowness-picks/jean-luc-godard-supercut',
'md5': '9a5a6a8edf806407e411296ab6bc2a49',
'info_dict': {
'id': '130020913',
'ext': 'mp4',
'title': 'Bleu, Blanc, Rouge - A Godard Supercut',
'description': 'md5:f0ea5f1857dffca02dbd37875d742cec',
'thumbnail': 're:^https?://.*\.jpg',
'upload_date': '20150607',
'uploader': 'Cinema Sem Lei',
'uploader_id': 'cinemasemlei',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('slug')
_, post = self._api_request(url, 'post/getBySlug/%s')
return self._extract_url_result(post)
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'"([^"]+/content/issue-[0-9.]+.js)"', webpage, 'player URL')
real_id = self._search_regex(
r'\sdata-videoId="([0-9]+)"', webpage, 'internal video ID')
player_code = self._download_webpage(
player_url, video_id,
note='Downloading player JavaScript',
errnote='Player download failed')
player_code = player_code.replace("'+d+'", real_id)
class NownessPlaylistIE(NownessBaseIE):
IE_NAME = 'nowness:playlist'
_VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)'
_TEST = {
'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues',
'info_dict': {
'id': '3286',
},
'playlist_mincount': 8,
}
bc_url = BrightcoveIE._extract_brightcove_url(player_code)
if bc_url is None:
raise ExtractorError('Could not find player definition')
return {
'_type': 'url',
'url': bc_url,
'ie_key': 'Brightcove',
}
def _real_extract(self, url):
playlist_id, playlist = self._api_request(url, 'post?PlaylistId=%s')
entries = [self._extract_url_result(item) for item in playlist['items']]
return self.playlist_result(entries, playlist_id)
class NownessSeriesIE(NownessBaseIE):
IE_NAME = 'nowness:series'
_VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])'
_TEST = {
'url': 'https://www.nowness.com/series/60-seconds',
'info_dict': {
'id': '60',
'title': '60 Seconds',
'description': 'One-minute wisdom in a new NOWNESS series',
},
'playlist_mincount': 4,
}
def _real_extract(self, url):
display_id, series = self._api_request(url, 'series/getBySlug/%s')
entries = [self._extract_url_result(post) for post in series['posts']]
series_title = None
series_description = None
translations = series.get('translations', [])
if translations:
series_title = translations[0].get('title') or translations[0]['seoTitle']
series_description = translations[0].get('seoDescription')
return self.playlist_result(
entries, compat_str(series['id']), series_title, series_description)

6
youtube_dl/extractor/nowtv.py
View File

@ -130,10 +130,16 @@ class NowTVIE(InfoExtractor):
}, {
'url': 'http://www.nowtv.at/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview?return=/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
'only_matching': True,
}, {
'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
display_id_split = display_id.split('/')
if len(display_id) > 2:
display_id = '/'.join((display_id_split[0], display_id_split[-1]))
info = self._download_json(
'https://api.nowtv.de/v3/movies/%s?fields=id,title,free,geoblocked,articleLong,articleShort,broadcastStartDate,seoUrl,duration,format,files' % display_id,

2
youtube_dl/extractor/nowvideo.py
View File

@ -7,7 +7,7 @@ class NowVideoIE(NovaMovIE):
IE_NAME = 'nowvideo'
IE_DESC = 'NowVideo'
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co|li)'}
_VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|ec|sx|eu|at|ag|co|li)'}
_HOST = 'www.nowvideo.ch'

63
youtube_dl/extractor/odnoklassniki.py
View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
ExtractorError,
unified_strdate,
int_or_none,
qualities,
@ -12,7 +13,7 @@ from ..utils import (
class OdnoklassnikiIE(InfoExtractor):
_VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_TESTS = [{
# metadata in JSON
'url': 'http://ok.ru/video/20079905452',
@ -28,6 +29,7 @@ class OdnoklassnikiIE(InfoExtractor):
'like_count': int,
'age_limit': 0,
},
'skip': 'Video has been blocked',
}, {
# metadataUrl
'url': 'http://ok.ru/video/63567059965189-0',
@ -43,9 +45,27 @@ class OdnoklassnikiIE(InfoExtractor):
'like_count': int,
'age_limit': 0,
},
}, {
# YouTube embed (metadataUrl, provider == USER_YOUTUBE)
'url': 'http://ok.ru/video/64211978996595-1',
'md5': '5d7475d428845cd2e13bae6f1a992278',
'info_dict': {
'id': '64211978996595-1',
'ext': 'mp4',
'title': 'Космическая среда от 26 августа 2015',
'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
'duration': 440,
'upload_date': '20150826',
'uploader_id': '750099571',
'uploader': 'Алина П',
'age_limit': 0,
},
}, {
'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
'only_matching': True,
}, {
'url': 'http://www.ok.ru/video/20648036891',
'only_matching': True,
}]
def _real_extract(self, url):
@ -54,9 +74,16 @@ class OdnoklassnikiIE(InfoExtractor):
webpage = self._download_webpage(
'http://ok.ru/video/%s' % video_id, video_id)
error = self._search_regex(
r'[^>]+class="vp_video_stub_txt"[^>]*>([^<]+)<',
webpage, 'error', default=None)
if error:
raise ExtractorError(error, expected=True)
player = self._parse_json(
unescapeHTML(self._search_regex(
r'data-attributes="([^"]+)"', webpage, 'player')),
r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id,
webpage, 'player', group='player')),
video_id)
flashvars = player['flashvars']
@ -89,16 +116,7 @@ class OdnoklassnikiIE(InfoExtractor):
like_count = int_or_none(metadata.get('likeCount'))
quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
formats = [{
'url': f['url'],
'ext': 'mp4',
'format_id': f['name'],
'quality': quality(f['name']),
} for f in metadata['videos']]
return {
info = {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
@ -108,5 +126,24 @@ class OdnoklassnikiIE(InfoExtractor):
'uploader_id': uploader_id,
'like_count': like_count,
'age_limit': age_limit,
'formats': formats,
}
if metadata.get('provider') == 'USER_YOUTUBE':
info.update({
'_type': 'url_transparent',
'url': movie['contentId'],
})
return info
quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
formats = [{
'url': f['url'],
'ext': 'mp4',
'format_id': f['name'],
'quality': quality(f['name']),
} for f in metadata['videos']]
self._sort_formats(formats)
info['formats'] = formats
return info

70
youtube_dl/extractor/openfilm.py
View File

@ -1,70 +0,0 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote_plus
from ..utils import (
parse_iso8601,
parse_age_limit,
int_or_none,
)
class OpenFilmIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)openfilm\.com/videos/(?P<id>.+)'
_TEST = {
'url': 'http://www.openfilm.com/videos/human-resources-remastered',
'md5': '42bcd88c2f3ec13b65edf0f8ad1cac37',
'info_dict': {
'id': '32736',
'display_id': 'human-resources-remastered',
'ext': 'mp4',
'title': 'Human Resources (Remastered)',
'description': 'Social Engineering in the 20th Century.',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 7164,
'timestamp': 1334756988,
'upload_date': '20120418',
'uploader_id': '41117',
'view_count': int,
'age_limit': 0,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player = compat_urllib_parse_unquote_plus(
self._og_search_video_url(webpage))
video = json.loads(self._search_regex(
r'\bp=({.+?})(?:&|$)', player, 'video JSON'))
video_url = '%s1.mp4' % video['location']
video_id = video.get('video_id')
display_id = video.get('alias') or display_id
title = video.get('title')
description = video.get('description')
thumbnail = video.get('main_thumb')
duration = int_or_none(video.get('duration'))
timestamp = parse_iso8601(video.get('dt_published'), ' ')
uploader_id = video.get('user_id')
view_count = int_or_none(video.get('views_count'))
age_limit = parse_age_limit(video.get('age_limit'))
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'uploader_id': uploader_id,
'view_count': view_count,
'age_limit': age_limit,
}

2
youtube_dl/extractor/playwire.py
View File

@ -19,7 +19,7 @@ class PlaywireIE(InfoExtractor):
'id': '3353705',
'ext': 'mp4',
'title': 'S04_RM_UCL_Rus',
'thumbnail': 're:^http://.*\.png$',
'thumbnail': 're:^https?://.*\.png$',
'duration': 145.94,
},
}, {

4
youtube_dl/extractor/pluralsight.py
View File

@ -41,9 +41,7 @@ class PluralsightIE(InfoExtractor):
def _login(self):
(username, password) = self._get_login_info()
if username is None:
raise ExtractorError(
'Pluralsight account is required, use --username and --password options to provide account credentials.',
expected=True)
self.raise_login_required('Pluralsight account is required')
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')

5
youtube_dl/extractor/pornhub.py
View File

@ -20,7 +20,7 @@ from ..aes import (
class PornHubIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
_VALID_URL = r'https?://(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
_TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': '882f488fa1f0026f023f33576004a2ed',
@ -34,6 +34,9 @@ class PornHubIE(InfoExtractor):
}, {
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
'only_matching': True,
}, {
'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
'only_matching': True,
}]
@classmethod

22
youtube_dl/extractor/rai.py
View File

@ -5,6 +5,7 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
parse_duration,
@ -72,6 +73,18 @@ class RaiIE(InfoExtractor):
'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!',
'uploader': 'RaiTre',
}
},
{
'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
'md5': '037104d2c14132887e5e4cf114569214',
'info_dict': {
'id': '0c7a664b-d0f4-4b2c-8835-3f82e46f433e',
'ext': 'flv',
'title': 'Il pacco',
'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
'uploader': 'RaiTre',
'upload_date': '20141221',
},
}
]
@ -90,11 +103,14 @@ class RaiIE(InfoExtractor):
relinker_url = self._extract_relinker_url(webpage)
if not relinker_url:
iframe_path = self._search_regex(
r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
iframe_url = self._search_regex(
[r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
r'drawMediaRaiTV\(["\'](.+?)["\']'],
webpage, 'iframe')
if not iframe_url.startswith('http'):
iframe_url = compat_urlparse.urljoin(url, iframe_url)
webpage = self._download_webpage(
'%s/%s' % (host, iframe_path), video_id)
iframe_url, video_id)
relinker_url = self._extract_relinker_url(webpage)
relinker = self._download_json(

6
youtube_dl/extractor/rtve.py
View File

@ -6,7 +6,7 @@ import re
import time
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..compat import compat_urllib_request, compat_urlparse
from ..utils import (
ExtractorError,
float_or_none,
@ -102,7 +102,9 @@ class RTVEALaCartaIE(InfoExtractor):
if info['state'] == 'DESPU':
raise ExtractorError('The video is no longer available', expected=True)
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
png = self._download_webpage(png_url, video_id, 'Downloading url information')
png_request = compat_urllib_request.Request(png_url)
png_request.add_header('Referer', url)
png = self._download_webpage(png_request, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
if not video_url.endswith('.f4m'):
auth_url = video_url.replace(

43
youtube_dl/extractor/ruutu.py
View File

@ -6,19 +6,19 @@ from ..compat import compat_urllib_parse_urlparse
from ..utils import (
determine_ext,
int_or_none,
xpath_attr,
xpath_text,
)
class RuutuIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?ruutu\.fi/ohjelmat/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?ruutu\.fi/video/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
'url': 'http://www.ruutu.fi/video/2058907',
'md5': 'ab2093f39be1ca8581963451b3c0234f',
'info_dict': {
'id': '2058907',
'display_id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi',
'ext': 'mp4',
'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
@ -28,14 +28,13 @@ class RuutuIE(InfoExtractor):
},
},
{
'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa',
'url': 'http://www.ruutu.fi/video/2057306',
'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
'info_dict': {
'id': '2057306',
'display_id': 'superpesis-katso-koko-kausi-ruudussa',
'ext': 'mp4',
'title': 'Superpesis: katso koko kausi Ruudussa',
'description': 'md5:44c44a99fdbe5b380ab74ebd75f0af77',
'description': 'md5:da2736052fef3b2bd5e0005e63c25eac',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 40,
'age_limit': 0,
@ -44,29 +43,10 @@ class RuutuIE(InfoExtractor):
]
def _real_extract(self, url):
display_id = self._match_id(url)
video_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-media-id="(\d+)"', webpage, 'media id')
video_xml_url = None
media_data = self._search_regex(
r'jQuery\.extend\([^,]+,\s*(.+?)\);', webpage,
'media data', default=None)
if media_data:
media_json = self._parse_json(media_data, display_id, fatal=False)
if media_json:
xml_url = media_json.get('ruutuplayer', {}).get('xmlUrl')
if xml_url:
video_xml_url = xml_url.replace('{ID}', video_id)
if not video_xml_url:
video_xml_url = 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id
video_xml = self._download_xml(video_xml_url, video_id)
video_xml = self._download_xml(
'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id)
formats = []
processed_urls = []
@ -109,10 +89,9 @@ class RuutuIE(InfoExtractor):
return {
'id': video_id,
'display_id': display_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
'formats': formats,

5
youtube_dl/extractor/safari.py
View File

@ -20,7 +20,6 @@ from ..utils import (
class SafariBaseIE(InfoExtractor):
_LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
_SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
_ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com'
_NETRC_MACHINE = 'safari'
_API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
@ -37,9 +36,7 @@ class SafariBaseIE(InfoExtractor):
def _login(self):
(username, password) = self._get_login_info()
if username is None:
raise ExtractorError(
self._ACCOUNT_CREDENTIALS_HINT,
expected=True)
self.raise_login_required('safaribooksonline.com account is required')
headers = std_headers
if 'Referer' not in headers:

7
youtube_dl/extractor/screenwavemedia.py
View File

@ -12,8 +12,8 @@ from ..utils import (
class ScreenwaveMediaIE(InfoExtractor):
_VALID_URL = r'http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'
_VALID_URL = r'https?://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=(?P<id>[A-Za-z0-9-]+)'
EMBED_PATTERN = r'src=(["\'])(?P<url>(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=.+?)\1'
_TESTS = [{
'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
'only_matching': True,
@ -33,7 +33,7 @@ class ScreenwaveMediaIE(InfoExtractor):
'http://player.screenwavemedia.com/player.js',
video_id, 'Downloading playerconfig webpage')
videoserver = self._search_regex(r"\[ipaddress\]\s*=>\s*([\d\.]+)", playerdata, 'videoserver')
videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver')
sources = self._parse_json(
js_to_json(
@ -56,6 +56,7 @@ class ScreenwaveMediaIE(InfoExtractor):
# Fallback to hardcoded sources if JS changes again
if not sources:
self.report_warning('Falling back to a hardcoded list of streams')
sources = [{
'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id),
'type': 'mp4',

4
youtube_dl/extractor/shahid.py
View File

@ -16,7 +16,7 @@ class ShahidIE(InfoExtractor):
'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html',
'info_dict': {
'id': '90574',
'ext': 'm3u8',
'ext': 'mp4',
'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
'duration': 2972,
@ -81,7 +81,7 @@ class ShahidIE(InfoExtractor):
compat_urllib_parse.urlencode({
'apiKey': 'sh@hid0nlin3',
'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
}).encode('utf-8')),
})),
video_id, 'Downloading video JSON')
video = video[api_vars['playerType']]

17
youtube_dl/extractor/shared.py
View File

@ -14,17 +14,28 @@ from ..utils import (
class SharedIE(InfoExtractor):
_VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})'
IE_DESC = 'shared.sx and vivo.sx'
_VALID_URL = r'http://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'
_TEST = {
_TESTS = [{
'url': 'http://shared.sx/0060718775',
'md5': '106fefed92a8a2adb8c98e6a0652f49b',
'info_dict': {
'id': '0060718775',
'ext': 'mp4',
'title': 'Bmp4',
'filesize': 1720110,
},
}
}, {
'url': 'http://vivo.sx/d7ddda0e78',
'md5': '15b3af41be0b4fe01f4df075c2678b2c',
'info_dict': {
'id': 'd7ddda0e78',
'ext': 'mp4',
'title': 'Chicken',
'filesize': 528031,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)

5
youtube_dl/extractor/smotri.py
View File

@ -330,10 +330,7 @@ class SmotriBroadcastIE(InfoExtractor):
(username, password) = self._get_login_info()
if username is None:
raise ExtractorError(
'Erotic broadcasts allowed only for registered users, '
'use --username and --password options to provide account credentials.',
expected=True)
self.raise_login_required('Erotic broadcasts allowed only for registered users')
login_form = {
'login-hint53': '1',

79
youtube_dl/extractor/telecinco.py
View File

@ -1,24 +1,51 @@
# coding: utf-8
from __future__ import unicode_literals
from .mitele import MiTeleIE
import json
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urlparse,
)
from ..utils import (
get_element_by_attribute,
parse_duration,
strip_jsonp,
)
class TelecincoIE(MiTeleIE):
IE_NAME = 'telecinco.es'
_VALID_URL = r'https?://www\.telecinco\.es/(?:[^/]+/)+(?P<id>.+?)\.html'
class TelecincoIE(InfoExtractor):
IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
_VALID_URL = r'https?://www\.(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
_TESTS = [{
'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
'md5': '5cbef3ad5ef17bf0d21570332d140729',
'info_dict': {
'id': 'MDSVID20141015_0058',
'ext': 'mp4',
'title': 'Con Martín Berasategui, hacer un bacalao al ...',
'duration': 662,
},
'params': {
# m3u8 download
'skip_download': True,
}, {
'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
'md5': '0a5b9f3cc8b074f50a0578f823a12694',
'info_dict': {
'id': 'MDSVID20150916_0128',
'ext': 'mp4',
'title': '¿Quién es este ex futbolista con el que hablan ...',
'duration': 79,
},
}, {
'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
'md5': 'ad1bfaaba922dd4a295724b05b68f86a',
'info_dict': {
'id': 'MDSVID20150513_0220',
'ext': 'mp4',
'title': '#DOYLACARA. Con la trata no hay trato',
'duration': 50,
},
}, {
'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
@ -27,3 +54,41 @@ class TelecincoIE(MiTeleIE):
'url': 'http://www.telecinco.es/espanasinirmaslejos/Espana-gran-destino-turistico_2_1240605043.html',
'only_matching': True,
}]
def _real_extract(self, url):
episode = self._match_id(url)
webpage = self._download_webpage(url, episode)
embed_data_json = self._search_regex(
r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
).replace('\'', '"')
embed_data = json.loads(embed_data_json)
domain = embed_data['mediaUrl']
if not domain.startswith('http'):
# only happens in telecinco.es videos
domain = 'http://' + domain
info_url = compat_urlparse.urljoin(
domain,
compat_urllib_parse_unquote(embed_data['flashvars']['host'])
)
info_el = self._download_xml(info_url, episode).find('./video/info')
video_link = info_el.find('videoUrl/link').text
token_query = compat_urllib_parse.urlencode({'id': video_link})
token_info = self._download_json(
embed_data['flashvars']['ov_tk'] + '?' + token_query,
episode,
transform_source=strip_jsonp
)
formats = self._extract_m3u8_formats(
token_info['tokenizedUrl'], episode, ext='mp4', entry_protocol='m3u8_native')
return {
'id': embed_data['videoId'],
'display_id': episode,
'title': info_el.find('title').text,
'formats': formats,
'description': get_element_by_attribute('class', 'text', webpage),
'thumbnail': info_el.find('thumb').text,
'duration': parse_duration(info_el.find('duration').text),
}

4
youtube_dl/extractor/tubitv.py
View File

@ -60,9 +60,7 @@ class TubiTvIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
if re.search(r"<(?:DIV|div) class='login-required-screen'>", webpage):
raise ExtractorError(
'This video requires login, use --username and --password '
'options to provide account credentials.', expected=True)
self.raise_login_required('This video requires login')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)

38
youtube_dl/extractor/tudou.py
View File

@ -2,14 +2,12 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..compat import compat_str
class TudouIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/.*?/(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])'
_VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/([^/]+/)*(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])'
_TESTS = [{
'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
'md5': '140a49ed444bd22f93330985d8475fcb',
@ -27,41 +25,41 @@ class TudouIE(InfoExtractor):
'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'url': 'http://www.tudou.com/albumplay/cJAHGih4yYg.html',
'only_matching': True,
}]
_PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
def _url_for_id(self, id, quality=None):
info_url = "http://v2.tudou.com/f?id=" + str(id)
def _url_for_id(self, video_id, quality=None):
info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id)
if quality:
info_url += '&hd' + quality
webpage = self._download_webpage(info_url, id, "Opening the info webpage")
final_url = self._html_search_regex('>(.+?)</f>', webpage, 'video url')
xml_data = self._download_xml(info_url, video_id, "Opening the info XML page")
final_url = xml_data.text
return final_url
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage)
if m and m.group(1):
return {
'_type': 'url',
'url': 'youku:' + m.group(1),
'ie_key': 'Youku'
}
youku_vcode = self._search_regex(
r'vcode\s*:\s*[\'"]([^\'"]*)[\'"]', webpage, 'youku vcode', default=None)
if youku_vcode:
return self.url_result('youku:' + youku_vcode, ie='Youku')
title = self._search_regex(
r",kw:\s*['\"](.+?)[\"']", webpage, 'title')
r',kw\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'title')
thumbnail_url = self._search_regex(
r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False)
r',pic\s*:\s*[\'"]([^\'"]+)[\'"]', webpage, 'thumbnail URL', fatal=False)
player_url = self._search_regex(
r"playerUrl\s*:\s*['\"](.+?\.swf)[\"']",
r'playerUrl\s*:\s*[\'"]([^\'"]+\.swf)[\'"]',
webpage, 'player URL', default=self._PLAYER_URL)
segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments')
segments = json.loads(segs_json)
segments = self._parse_json(self._search_regex(
r'segs: \'([^\']+)\'', webpage, 'segments'), video_id)
# It looks like the keys are the arguments that have to be passed as
# the hd field in the request url, we pick the higher
# Also, filter non-number qualities (see issue #3643).

4
youtube_dl/extractor/udemy.py
View File

@ -70,9 +70,7 @@ class UdemyIE(InfoExtractor):
def _login(self):
(username, password) = self._get_login_info()
if username is None:
raise ExtractorError(
'Udemy account is required, use --username and --password options to provide account credentials.',
expected=True)
self.raise_login_required('Udemy account is required')
login_popup = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login popup')

128
youtube_dl/extractor/vidme.py
View File

@ -1,10 +1,12 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
str_to_int,
parse_iso8601,
)
@ -12,18 +14,41 @@ class VidmeIE(InfoExtractor):
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'https://vid.me/QNB',
'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
'md5': 'c62f1156138dc3323902188c5b5a8bd6',
'info_dict': {
'id': 'QNB',
'ext': 'mp4',
'title': 'Fishing for piranha - the easy way',
'description': 'source: https://www.facebook.com/photo.php?v=312276045600871',
'duration': 119.92,
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1406313244,
'upload_date': '20140725',
'thumbnail': 're:^https?://.*\.jpg',
'age_limit': 0,
'duration': 119.92,
'view_count': int,
'like_count': int,
'comment_count': int,
},
}, {
'url': 'https://vid.me/Gc6M',
'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
'info_dict': {
'id': 'Gc6M',
'ext': 'mp4',
'title': 'O Mere Dil ke chain - Arnav and Khushi VM',
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1441211642,
'upload_date': '20150902',
'uploader': 'SunshineM',
'uploader_id': '3552827',
'age_limit': 0,
'duration': 223.72,
'view_count': int,
'like_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
}, {
# tests uploader field
@ -33,63 +58,94 @@ class VidmeIE(InfoExtractor):
'ext': 'mp4',
'title': 'The Carver',
'description': 'md5:e9c24870018ae8113be936645b93ba3c',
'duration': 97.859999999999999,
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1433203629,
'upload_date': '20150602',
'uploader': 'Thomas',
'thumbnail': 're:^https?://.*\.jpg',
'uploader_id': '109747',
'age_limit': 0,
'duration': 97.859999999999999,
'view_count': int,
'like_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
}, {
# From http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
# nsfw test from http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
'url': 'https://vid.me/e/Wmur',
'only_matching': True,
'info_dict': {
'id': 'Wmur',
'ext': 'mp4',
'title': 'naked smoking & stretching',
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1430931613,
'upload_date': '20150506',
'uploader': 'naked-yogi',
'uploader_id': '1638622',
'age_limit': 18,
'duration': 653.26999999999998,
'view_count': int,
'like_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
url = url.replace('vid.me/e/', 'vid.me/')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
try:
response = self._download_json(
'https://api.vid.me/videoByUrl/%s' % video_id, video_id)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
response = self._parse_json(e.cause.read(), video_id)
else:
raise
title = self._og_search_title(webpage)
description = self._og_search_description(webpage, default='')
thumbnail = self._og_search_thumbnail(webpage)
timestamp = int_or_none(self._og_search_property(
'updated_time', webpage, fatal=False))
width = int_or_none(self._og_search_property(
'video:width', webpage, fatal=False))
height = int_or_none(self._og_search_property(
'video:height', webpage, fatal=False))
duration = float_or_none(self._html_search_regex(
r'data-duration="([^"]+)"', webpage, 'duration', fatal=False))
view_count = str_to_int(self._html_search_regex(
r'<(?:li|span) class="video_views">\s*([\d,\.]+)\s*plays?',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._html_search_regex(
r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">',
webpage, 'like count', fatal=False))
uploader = self._html_search_regex(
'class="video_author_username"[^>]*>([^<]+)',
webpage, 'uploader', default=None)
error = response.get('error')
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
video = response['video']
formats = [{
'format_id': f.get('type'),
'url': f['uri'],
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
} for f in video.get('formats', []) if f.get('uri')]
self._sort_formats(formats)
title = video['title']
description = video.get('description')
thumbnail = video.get('thumbnail_url')
timestamp = parse_iso8601(video.get('date_created'), ' ')
uploader = video.get('user', {}).get('username')
uploader_id = video.get('user', {}).get('user_id')
age_limit = 18 if video.get('nsfw') is True else 0
duration = float_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
like_count = int_or_none(video.get('likes_count'))
comment_count = int_or_none(video.get('comment_count'))
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'age_limit': age_limit,
'timestamp': timestamp,
'width': width,
'height': height,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'uploader': uploader,
'comment_count': comment_count,
'formats': formats,
}

13
youtube_dl/extractor/vier.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
@ -91,31 +92,27 @@ class VierVideosIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
program = mobj.group('program')
webpage = self._download_webpage(url, program)
page_id = mobj.group('page')
if page_id:
page_id = int(page_id)
start_page = page_id
last_page = start_page + 1
playlist_id = '%s-page%d' % (program, page_id)
else:
start_page = 0
last_page = int(self._search_regex(
r'videos\?page=(\d+)">laatste</a>',
webpage, 'last page', default=0)) + 1
playlist_id = program
entries = []
for current_page_id in range(start_page, last_page):
for current_page_id in itertools.count(start_page):
current_page = self._download_webpage(
'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
program,
'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage
'Downloading page %d' % (current_page_id + 1))
page_entries = [
self.url_result('http://www.vier.be' + video_url, 'Vier')
for video_url in re.findall(
r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
entries.extend(page_entries)
if page_id or '>Meer<' not in current_page:
break
return self.playlist_result(entries, playlist_id)

86
youtube_dl/extractor/vlive.py Normal file
View File

@ -0,0 +1,86 @@
# coding: utf-8
from __future__ import unicode_literals
import hmac
from hashlib import sha1
from base64 import b64encode
from time import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext
)
from ..compat import compat_urllib_parse
class VLiveIE(InfoExtractor):
IE_NAME = 'vlive'
# www.vlive.tv/video/ links redirect to m.vlive.tv/video/ for mobile devices
_VALID_URL = r'https?://(?:(www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://m.vlive.tv/video/1326',
'md5': 'cc7314812855ce56de70a06a27314983',
'info_dict': {
'id': '1326',
'ext': 'mp4',
'title': '[V] Girl\'s Day\'s Broadcast',
'creator': 'Girl\'s Day',
},
}
_SECRET = 'rFkwZet6pqk1vQt6SxxUkAHX7YL3lmqzUMrU4IDusTo4jEBdtOhNfT4BYYAdArwH'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://m.vlive.tv/video/%s' % video_id,
video_id, note='Download video page')
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
creator = self._html_search_regex(
r'<span[^>]+class="name">([^<>]+)</span>', webpage, 'creator')
url = 'http://global.apis.naver.com/globalV/globalV/vod/%s/playinfo?' % video_id
msgpad = '%.0f' % (time() * 1000)
md = b64encode(
hmac.new(self._SECRET.encode('ascii'),
(url[:255] + msgpad).encode('ascii'), sha1).digest()
)
url += '&' + compat_urllib_parse.urlencode({'msgpad': msgpad, 'md': md})
playinfo = self._download_json(url, video_id, 'Downloading video json')
if playinfo.get('message', '') != 'success':
raise ExtractorError(playinfo.get('message', 'JSON request unsuccessful'))
if not playinfo.get('result'):
raise ExtractorError('No videos found.')
formats = []
for vid in playinfo['result'].get('videos', {}).get('list', []):
formats.append({
'url': vid['source'],
'ext': 'mp4',
'abr': vid.get('bitrate', {}).get('audio'),
'vbr': vid.get('bitrate', {}).get('video'),
'format_id': vid['encodingOption']['name'],
'height': vid.get('height'),
'width': vid.get('width'),
})
self._sort_formats(formats)
subtitles = {}
for caption in playinfo['result'].get('captions', {}).get('list', []):
subtitles[caption['language']] = [
{'ext': determine_ext(caption['source'], default_ext='vtt'),
'url': caption['source']}]
return {
'id': video_id,
'title': title,
'creator': creator,
'thumbnail': thumbnail,
'formats': formats,
'subtitles': subtitles,
}

8
youtube_dl/extractor/washingtonpost.py
View File

@ -19,25 +19,25 @@ class WashingtonPostIE(InfoExtractor):
'title': 'Sinkhole of bureaucracy',
},
'playlist': [{
'md5': '79132cc09ec5309fa590ae46e4cc31bc',
'md5': 'b9be794ceb56c7267d410a13f99d801a',
'info_dict': {
'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f',
'ext': 'mp4',
'title': 'Breaking Points: The Paper Mine',
'duration': 1287,
'duration': 1290,
'description': 'Overly complicated paper pushing is nothing new to government bureaucracy. But the way federal retirement applications are filed may be the most outdated. David Fahrenthold explains.',
'uploader': 'The Washington Post',
'timestamp': 1395527908,
'upload_date': '20140322',
},
}, {
'md5': 'e1d5734c06865cc504ad99dc2de0d443',
'md5': '1fff6a689d8770966df78c8cb6c8c17c',
'info_dict': {
'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f',
'ext': 'mp4',
'title': 'The town bureaucracy sustains',
'description': 'Underneath the friendly town of Boyers is a sea of government paperwork. In a disused limestone mine, hundreds of locals now track, file and process retirement applications for the federal government. We set out to find out what it\'s like to do paperwork 230 feet underground.',
'duration': 2217,
'duration': 2220,
'timestamp': 1395528005,
'upload_date': '20140322',
'uploader': 'The Washington Post',

23
youtube_dl/extractor/wimp.py
View File

@ -1,40 +1,33 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .youtube import YoutubeIE
class WimpIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/'
_VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)/'
_TESTS = [{
'url': 'http://www.wimp.com/maruexhausted/',
'md5': 'f1acced123ecb28d9bb79f2479f2b6a1',
'md5': 'ee21217ffd66d058e8b16be340b74883',
'info_dict': {
'id': 'maruexhausted',
'ext': 'flv',
'ext': 'mp4',
'title': 'Maru is exhausted.',
'description': 'md5:57e099e857c0a4ea312542b684a869b8',
}
}, {
# youtube video
'url': 'http://www.wimp.com/clowncar/',
'md5': '4e2986c793694b55b37cf92521d12bb4',
'info_dict': {
'id': 'cG4CEr2aiSg',
'id': 'clowncar',
'ext': 'mp4',
'title': 'Basset hound clown car...incredible!',
'description': 'md5:8d228485e0719898c017203f900b3a35',
'uploader': 'Gretchen Hoey',
'uploader_id': 'gretchenandjeff1',
'upload_date': '20140303',
'title': 'It\'s like a clown car.',
'description': 'md5:0e56db1370a6e49c5c1d19124c0d2fb2',
},
'add_ie': ['Youtube'],
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
[r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"],

2
youtube_dl/extractor/xuite.py
View File

@ -19,7 +19,7 @@ class XuiteIE(InfoExtractor):
_TESTS = [{
# Audio
'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
'md5': '63a42c705772aa53fd4c1a0027f86adf',
'md5': 'e79284c87b371424885448d11f6398c8',
'info_dict': {
'id': '3860914',
'ext': 'mp3',

62
youtube_dl/extractor/yahoo.py
View File

@ -101,7 +101,7 @@ class YahooIE(InfoExtractor):
}
}, {
'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
'md5': '67010fdf3a08d290e060a4dd96baa07b',
'md5': '88e209b417f173d86186bef6e4d1f160',
'info_dict': {
'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521',
'ext': 'mp4',
@ -144,6 +144,17 @@ class YahooIE(InfoExtractor):
}, {
'url': 'https://tw.news.yahoo.com/-100120367.html',
'only_matching': True,
}, {
# Query result is embedded in webpage, but explicit request to video API fails with geo restriction
'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html',
'md5': '4fbafb9c9b6f07aa8f870629f6671b35',
'info_dict': {
'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504',
'ext': 'mp4',
'title': 'Communitary - Community Episode 1: Ladders',
'description': 'md5:8fc39608213295748e1e289807838c97',
'duration': 1646,
},
}
]
@ -171,6 +182,19 @@ class YahooIE(InfoExtractor):
if nbc_sports_url:
return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
# Query result is often embedded in webpage as JSON. Sometimes explicit requests
# to video API results in a failure with geo restriction reason therefore using
# embedded query result when present sounds reasonable.
config_json = self._search_regex(
r'window\.Af\.bootstrap\[[^\]]+\]\s*=\s*({.*?"applet_type"\s*:\s*"td-applet-videoplayer".*?});(?:</script>|$)',
webpage, 'videoplayer applet', default=None)
if config_json:
config = self._parse_json(config_json, display_id, fatal=False)
if config:
sapi = config.get('models', {}).get('applet_model', {}).get('data', {}).get('sapi')
if sapi:
return self._extract_info(display_id, sapi, webpage)
items_json = self._search_regex(
r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,
default=None)
@ -190,22 +214,10 @@ class YahooIE(InfoExtractor):
video_id = info['id']
return self._get_info(video_id, display_id, webpage)
def _get_info(self, video_id, display_id, webpage):
region = self._search_regex(
r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"',
webpage, 'region', fatal=False, default='US')
data = compat_urllib_parse.urlencode({
'protocol': 'http',
'region': region,
})
query_url = (
'https://video.media.yql.yahoo.com/v1/video/sapi/streams/'
'{id}?{data}'.format(id=video_id, data=data))
query_result = self._download_json(
query_url, display_id, 'Downloading video info')
info = query_result['query']['results']['mediaObj'][0]
def _extract_info(self, display_id, query, webpage):
info = query['query']['results']['mediaObj'][0]
meta = info.get('meta')
video_id = info.get('id')
if not meta:
msg = info['status'].get('msg')
@ -231,6 +243,9 @@ class YahooIE(InfoExtractor):
'ext': 'flv',
})
else:
if s.get('format') == 'm3u8_playlist':
format_info['protocol'] = 'm3u8_native'
format_info['ext'] = 'mp4'
format_url = compat_urlparse.urljoin(host, path)
format_info['url'] = format_url
formats.append(format_info)
@ -264,6 +279,21 @@ class YahooIE(InfoExtractor):
'subtitles': subtitles,
}
def _get_info(self, video_id, display_id, webpage):
region = self._search_regex(
r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"',
webpage, 'region', fatal=False, default='US')
data = compat_urllib_parse.urlencode({
'protocol': 'http',
'region': region,
})
query_url = (
'https://video.media.yql.yahoo.com/v1/video/sapi/streams/'
'{id}?{data}'.format(id=video_id, data=data))
query_result = self._download_json(
query_url, display_id, 'Downloading video info')
return self._extract_info(display_id, query_result, webpage)
class YahooSearchIE(SearchInfoExtractor):
IE_DESC = 'Yahoo screen search'

53
youtube_dl/extractor/yandexmusic.py
View File

@ -5,7 +5,11 @@ import re
import hashlib
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import (
compat_str,
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
int_or_none,
float_or_none,
@ -67,7 +71,7 @@ class YandexMusicPlaylistBaseIE(InfoExtractor):
return [
self.url_result(
'http://music.yandex.ru/album/%s/track/%s' % (track['albums'][0]['id'], track['id']))
for track in tracks]
for track in tracks if track.get('albums') and isinstance(track.get('albums'), list)]
class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
@ -106,7 +110,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
IE_DESC = 'Яндекс.Музыка - Плейлист'
_VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
'info_dict': {
'id': '1245',
@ -114,19 +118,54 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
},
'playlist_count': 6,
}
}, {
# playlist exceeding the limit of 150 tracks shipped with webpage (see
# https://github.com/rg3/youtube-dl/issues/6666)
'url': 'https://music.yandex.ru/users/ya.playlist/playlists/1036',
'info_dict': {
'id': '1036',
'title': 'Музыка 90-х',
},
'playlist_count': 310,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
playlist = self._parse_json(
mu = self._parse_json(
self._search_regex(
r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
playlist_id)['pageData']['playlist']
playlist_id)
playlist = mu['pageData']['playlist']
tracks, track_ids = playlist['tracks'], playlist['trackIds']
# tracks dictionary shipped with webpage is limited to 150 tracks,
# missing tracks should be retrieved manually.
if len(tracks) < len(track_ids):
present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')])
missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids)
request = compat_urllib_request.Request(
'https://music.yandex.ru/handlers/track-entries.jsx',
compat_urllib_parse.urlencode({
'entries': ','.join(missing_track_ids),
'lang': mu.get('settings', {}).get('lang', 'en'),
'external-domain': 'music.yandex.ru',
'overembed': 'false',
'sign': mu.get('authData', {}).get('user', {}).get('sign'),
'strict': 'true',
}).encode('utf-8'))
request.add_header('Referer', url)
request.add_header('X-Requested-With', 'XMLHttpRequest')
missing_tracks = self._download_json(
request, playlist_id, 'Downloading missing tracks JSON', fatal=False)
if missing_tracks:
tracks.extend(missing_tracks)
return self.playlist_result(
self._build_playlist(playlist['tracks']),
self._build_playlist(tracks),
compat_str(playlist_id),
playlist['title'], playlist.get('description'))

19
youtube_dl/extractor/youku.py
View File

@ -49,6 +49,17 @@ class YoukuIE(InfoExtractor):
},
'playlist_count': 13,
'skip': 'Available in China only',
}, {
'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
'note': 'Video protected with password',
'info_dict': {
'id': 'XNjA1NzA2Njgw',
'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
},
'playlist_count': 19,
'params': {
'videopassword': '100600',
},
}]
def construct_video_urls(self, data1, data2):
@ -185,9 +196,15 @@ class YoukuIE(InfoExtractor):
raw_data = self._download_json(req, video_id, note=note)
return raw_data['data'][0]
video_password = self._downloader.params.get('videopassword', None)
# request basic data
basic_data_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id
if video_password:
basic_data_url += '?password=%s' % video_password
data1 = retrieve_data(
'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id,
basic_data_url,
'Downloading JSON metadata 1')
data2 = retrieve_data(
'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,

86
youtube_dl/extractor/youtube.py
View File

@ -26,6 +26,7 @@ from ..compat import (
)
from ..utils import (
clean_html,
encode_dict,
ExtractorError,
float_or_none,
get_element_by_attribute,
@ -111,10 +112,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
'hl': 'en_US',
}
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('ascii')
req = compat_urllib_request.Request(self._LOGIN_URL, login_data)
login_results = self._download_webpage(
@ -147,8 +145,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
'TrustDevice': 'on',
})
tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items())
tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii')
tfa_data = compat_urllib_parse.urlencode(encode_dict(tfa_form_strs)).encode('ascii')
tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data)
tfa_results = self._download_webpage(
@ -660,7 +657,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_signature_function(self, video_id, player_url, example_sig):
id_m = re.match(
r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$',
r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?)?\.(?P<ext>[a-z]+)$',
player_url)
if not id_m:
raise ExtractorError('Cannot identify player %r' % player_url)
@ -1243,7 +1240,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
if 'rtmpe%3Dyes' in encoded_url_map:
raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
url_map = {}
formats = []
for url_data_str in encoded_url_map.split(','):
url_data = compat_parse_qs(url_data_str)
if 'itag' not in url_data or 'url' not in url_data:
@ -1289,7 +1286,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
player_desc = 'flash player %s' % player_version
else:
player_version = self._search_regex(
r'html5player-([^/]+?)(?:/html5player)?\.js',
r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
player_url,
'html5 player', fatal=False)
player_desc = 'html5 player %s' % player_version
@ -1303,8 +1300,50 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
url += '&signature=' + signature
if 'ratebypass' not in url:
url += '&ratebypass=yes'
url_map[format_id] = url
formats = _map_to_format_list(url_map)
# Some itags are not included in DASH manifest thus corresponding formats will
# lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
# Trying to extract metadata from url_encoded_fmt_stream_map entry.
mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
dct = {
'format_id': format_id,
'url': url,
'player_url': player_url,
'filesize': int_or_none(url_data.get('clen', [None])[0]),
'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
'width': width,
'height': height,
'fps': int_or_none(url_data.get('fps', [None])[0]),
'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
}
type_ = url_data.get('type', [None])[0]
if type_:
type_split = type_.split(';')
kind_ext = type_split[0].split('/')
if len(kind_ext) == 2:
kind, ext = kind_ext
dct['ext'] = ext
if kind in ('audio', 'video'):
codecs = None
for mobj in re.finditer(
r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
if mobj.group('key') == 'codecs':
codecs = mobj.group('val')
break
if codecs:
codecs = codecs.split(',')
if len(codecs) == 2:
acodec, vcodec = codecs[0], codecs[1]
else:
acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
dct.update({
'acodec': acodec,
'vcodec': vcodec,
})
if format_id in self._formats:
dct.update(self._formats[format_id])
formats.append(dct)
elif video_info.get('hlsvp'):
manifest_url = video_info['hlsvp'][0]
url_map = self._extract_from_m3u8(manifest_url, video_id)
@ -1615,12 +1654,15 @@ class YoutubeChannelIE(InfoExtractor):
channel_page = self._download_webpage(
url + '?view=57', channel_id,
'Downloading channel page', fatal=False)
channel_playlist_id = self._html_search_meta(
'channelId', channel_page, 'channel id', default=None)
if not channel_playlist_id:
channel_playlist_id = self._search_regex(
r'data-channel-external-id="([^"]+)"',
channel_page, 'channel id', default=None)
if channel_page is False:
channel_playlist_id = False
else:
channel_playlist_id = self._html_search_meta(
'channelId', channel_page, 'channel id', default=None)
if not channel_playlist_id:
channel_playlist_id = self._search_regex(
r'data-channel-external-id="([^"]+)"',
channel_page, 'channel id', default=None)
if channel_playlist_id and channel_playlist_id.startswith('UC'):
playlist_id = 'UU' + channel_playlist_id[2:]
return self.url_result(
@ -1796,8 +1838,8 @@ class YoutubeShowIE(InfoExtractor):
_VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)'
IE_NAME = 'youtube:show'
_TESTS = [{
'url': 'http://www.youtube.com/show/airdisasters',
'playlist_mincount': 3,
'url': 'https://www.youtube.com/show/airdisasters',
'playlist_mincount': 5,
'info_dict': {
'id': 'airdisasters',
'title': 'Air Disasters',
@ -1808,7 +1850,7 @@ class YoutubeShowIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
webpage = self._download_webpage(
url, playlist_id, 'Downloading show webpage')
'https://www.youtube.com/show/%s/playlists' % playlist_id, playlist_id, 'Downloading show webpage')
# There's one playlist for each season of the show
m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage))
self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons)))
@ -1931,6 +1973,7 @@ class YoutubeTruncatedURLIE(InfoExtractor):
annotation_id=annotation_[^&]+|
x-yt-cl=[0-9]+|
hl=[^&]*|
t=[0-9]+
)?
|
attribution_link\?a=[^&]+
@ -1953,6 +1996,9 @@ class YoutubeTruncatedURLIE(InfoExtractor):
}, {
'url': 'https://www.youtube.com/watch?hl=en-GB',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/watch?t=2372',
'only_matching': True,
}]
def _real_extract(self, url):

6
youtube_dl/options.py
View File

@ -2,7 +2,6 @@ from __future__ import unicode_literals
import os.path
import optparse
import shlex
import sys
from .downloader.external import list_external_downloaders
@ -11,6 +10,7 @@ from .compat import (
compat_get_terminal_size,
compat_getenv,
compat_kwargs,
compat_shlex_split,
)
from .utils import (
preferredencoding,
@ -28,7 +28,7 @@ def parseOpts(overrideArguments=None):
try:
res = []
for l in optionf:
res += shlex.split(l, comments=True)
res += compat_shlex_split(l, comments=True)
finally:
optionf.close()
return res
@ -320,7 +320,7 @@ def parseOpts(overrideArguments=None):
authentication.add_option(
'--video-password',
dest='videopassword', metavar='PASSWORD',
help='Video password (vimeo, smotri)')
help='Video password (vimeo, smotri, youku)')
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option(

7
youtube_dl/postprocessor/common.py
View File

@ -4,6 +4,7 @@ import os
from ..utils import (
PostProcessingError,
cli_configuration_args,
encodeFilename,
)
@ -61,11 +62,7 @@ class PostProcessor(object):
self._downloader.report_warning(errnote)
def _configuration_args(self, default=[]):
pp_args = self._downloader.params.get('postprocessor_args')
if pp_args is None:
return default
assert isinstance(pp_args, list)
return pp_args
return cli_configuration_args(self._downloader.params, 'postprocessor_args', default)
class AudioConversionError(PostProcessingError):

13
youtube_dl/postprocessor/ffmpeg.py
View File

@ -135,7 +135,10 @@ class FFmpegPostProcessor(PostProcessor):
files_cmd = []
for path in input_paths:
files_cmd.extend([encodeArgument('-i'), encodeFilename(path, True)])
files_cmd.extend([
encodeArgument('-i'),
encodeFilename(self._ffmpeg_filename_argument(path), True)
])
cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] +
files_cmd +
[encodeArgument(o) for o in opts] +
@ -155,10 +158,10 @@ class FFmpegPostProcessor(PostProcessor):
self.run_ffmpeg_multiple_files([path], out_path, opts)
def _ffmpeg_filename_argument(self, fn):
# ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
if fn.startswith('-'):
return './' + fn
return fn
# Always use 'file:' because the filename may contain ':' (ffmpeg
# interprets that as a protocol) or can start with '-' (-- is broken in
# ffmpeg, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details)
return 'file:' + fn
class FFmpegExtractAudioPP(FFmpegPostProcessor):

96
youtube_dl/utils.py
View File

@ -141,7 +141,7 @@ def write_json_file(obj, fn):
if sys.version_info >= (2, 7):
def find_xpath_attr(node, xpath, key, val=None):
""" Find the xpath xpath[@key=val] """
assert re.match(r'^[a-zA-Z-]+$', key)
assert re.match(r'^[a-zA-Z_-]+$', key)
if val:
assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val)
expr = xpath + ('[@%s]' % key if val is None else "[@%s='%s']" % (key, val))
@ -176,12 +176,12 @@ def xpath_with_ns(path, ns_map):
return '/'.join(replaced)
def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
if sys.version_info < (2, 7): # Crazy 2.6
xpath = xpath.encode('ascii')
n = node.find(xpath)
if n is None or n.text is None:
if n is None:
if default is not NO_DEFAULT:
return default
elif fatal:
@ -189,9 +189,37 @@ def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
raise ExtractorError('Could not find XML element %s' % name)
else:
return None
return n
def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
n = xpath_element(node, xpath, name, fatal=fatal, default=default)
if n is None or n == default:
return n
if n.text is None:
if default is not NO_DEFAULT:
return default
elif fatal:
name = xpath if name is None else name
raise ExtractorError('Could not find XML element\'s text %s' % name)
else:
return None
return n.text
def xpath_attr(node, xpath, key, name=None, fatal=False, default=NO_DEFAULT):
n = find_xpath_attr(node, xpath, key)
if n is None:
if default is not NO_DEFAULT:
return default
elif fatal:
name = '%s[@%s]' % (xpath, key) if name is None else name
raise ExtractorError('Could not find XML attribute %s' % name)
else:
return None
return n.attrib[key]
def get_element_by_id(id, html):
"""Return the content of the tag with the specified ID in the passed HTML document"""
return get_element_by_attribute("id", id, html)
@ -587,6 +615,11 @@ class ContentTooShortError(Exception):
def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
# Working around python 2 bug (see http://bugs.python.org/issue17849) by limiting
# expected HTTP responses to meet HTTP/1.0 or later (see also
# https://github.com/rg3/youtube-dl/issues/6727)
if sys.version_info < (3, 0):
kwargs['strict'] = True
hc = http_class(*args, **kwargs)
source_address = ydl_handler._params.get('source_address')
if source_address is not None:
@ -715,7 +748,8 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
gz = io.BytesIO(self.deflate(resp.read()))
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
# Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986
# Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986 (see
# https://github.com/rg3/youtube-dl/issues/6457).
if 300 <= resp.code < 400:
location = resp.headers.get('Location')
if location:
@ -749,6 +783,30 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
req, **kwargs)
class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
def __init__(self, cookiejar=None):
compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar)
def http_response(self, request, response):
# Python 2 will choke on next HTTP request in row if there are non-ASCII
# characters in Set-Cookie HTTP header of last response (see
# https://github.com/rg3/youtube-dl/issues/6769).
# In order to at least prevent crashing we will percent encode Set-Cookie
# header before HTTPCookieProcessor starts processing it.
# if sys.version_info < (3, 0) and response.headers:
# for set_cookie_header in ('Set-Cookie', 'Set-Cookie2'):
# set_cookie = response.headers.get(set_cookie_header)
# if set_cookie:
# set_cookie_escaped = compat_urllib_parse.quote(set_cookie, b"%/;:@&=+$,!~*'()?#[] ")
# if set_cookie != set_cookie_escaped:
# del response.headers[set_cookie_header]
# response.headers[set_cookie_header] = set_cookie_escaped
return compat_urllib_request.HTTPCookieProcessor.http_response(self, request, response)
https_request = compat_urllib_request.HTTPCookieProcessor.http_request
https_response = http_response
def parse_iso8601(date_str, delimiter='T', timezone=None):
""" Return a UNIX timestamp from the given date """
@ -1578,6 +1636,10 @@ def urlencode_postdata(*args, **kargs):
return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii')
def encode_dict(d, encoding='utf-8'):
return dict((k.encode(encoding), v.encode(encoding)) for k, v in d.items())
try:
etree_iter = xml.etree.ElementTree.Element.iter
except AttributeError: # Python <=2.6
@ -1918,6 +1980,32 @@ def dfxp2srt(dfxp_data):
return ''.join(out)
def cli_option(params, command_option, param):
param = params.get(param)
return [command_option, param] if param is not None else []
def cli_bool_option(params, command_option, param, true_value='true', false_value='false', separator=None):
param = params.get(param)
assert isinstance(param, bool)
if separator:
return [command_option + separator + (true_value if param else false_value)]
return [command_option, true_value if param else false_value]
def cli_valueless_option(params, command_option, param, expected_value=True):
param = params.get(param)
return [command_option] if param == expected_value else []
def cli_configuration_args(params, param, default=[]):
ex_args = params.get(param)
if ex_args is None:
return default
assert isinstance(ex_args, list)
return ex_args
class ISO639Utils(object):
# See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
_lang_map = {

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2015.08.23'
__version__ = '2015.09.09'