mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 10:52:34 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into bliptv

Browse Source
This commit is contained in:
remitamine 2015-12-03 20:33:22 +01:00
commit 78653a33aa
188 changed files with 4047 additions and 1760 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
AUTHORS
View File

@ -144,3 +144,6 @@ Lee Jenkins
Anssi Hannula
Lukáš Lalinský
Qijiang Fan
Rémy Léone
Marco Ferragina
reiv

5
CONTRIBUTING.md
View File

@ -1,6 +1,6 @@
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
@ -114,12 +114,13 @@ ### Adding support for a new site
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```

14
Makefile
View File

@ -61,34 +61,34 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
chmod a+x youtube-dl
README.md: youtube_dl/*.py youtube_dl/*/*.py
COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
COLUMNS=80 $(PYTHON) youtube_dl/__main__.py --help | $(PYTHON) devscripts/make_readme.py
CONTRIBUTING.md: README.md
python devscripts/make_contributing.py README.md CONTRIBUTING.md
$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
supportedsites:
python devscripts/make_supportedsites.py docs/supportedsites.md
$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
README.txt: README.md
pandoc -f markdown -t plain README.md -o README.txt
youtube-dl.1: README.md
python devscripts/prepare_manpage.py >youtube-dl.1.temp.md
$(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md
pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
rm -f youtube-dl.1.temp.md
youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
python devscripts/bash-completion.py
$(PYTHON) devscripts/bash-completion.py
bash-completion: youtube-dl.bash-completion
youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
python devscripts/zsh-completion.py
$(PYTHON) devscripts/zsh-completion.py
zsh-completion: youtube-dl.zsh
youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
python devscripts/fish-completion.py
$(PYTHON) devscripts/fish-completion.py
fish-completion: youtube-dl.fish

18
README.md
View File

@ -319,7 +319,8 @@ ## Video Format Options:
--all-formats Download all available video formats
--prefer-free-formats Prefer free video formats unless a specific
one is requested
-F, --list-formats List all available formats
-F, --list-formats List all available formats of specified
videos
--youtube-skip-dash-manifest Do not download the DASH manifests and
related data on YouTube videos
--merge-output-format FORMAT If a merge is required (e.g.
@ -329,8 +330,8 @@ ## Video Format Options:
## Subtitle Options:
--write-sub Write subtitle file
--write-auto-sub Write automatic subtitle file (YouTube
only)
--write-auto-sub Write automatically generated subtitle file
(YouTube only)
--all-subs Download all the available subtitles of the
video
--list-subs List all available subtitles for the video
@ -534,6 +535,12 @@ ### I get HTTP error 402 when trying to download a video. What's this?
Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
### Do I need any other programs?
youtube-dl works fine on its own on most sites. However, if you want to convert video/audio, you'll need [avconv](https://libav.org/) or [ffmpeg](https://www.ffmpeg.org/). On some sites - most notably YouTube - videos can be retrieved in a higher quality format without sound. youtube-dl will detect whether avconv/ffmpeg is present and automatically pick the best option.
Videos or video formats streamed via RTMP protocol can only be downloaded when [rtmpdump](https://rtmpdump.mplayerhq.hu/) is installed. Downloading MMS and RTSP videos requires either [mplayer](http://mplayerhq.hu/) or [mpv](https://mpv.io/) to be installed.
### I have downloaded a video but how can I play it?
Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
@ -710,12 +717,13 @@ ### Adding support for a new site
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```
@ -794,7 +802,7 @@ # BUGS
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):

24
docs/supportedsites.md
View File

@ -53,6 +53,7 @@ # Supported sites
- **Bandcamp:album**
- **bbc**: BBC
- **bbc.co.uk**: BBC iPlayer
- **bbc.co.uk:article**: BBC articles
- **BeatportPro**
- **Beeg**
- **BehindKink**
@ -66,7 +67,8 @@ # Supported sites
- **Bpb**: Bundeszentrale für politische Bildung
- **BR**: Bayerischer Rundfunk Mediathek
- **Break**
- **Brightcove**
- **brightcove:legacy**
- **brightcove:new**
- **bt:article**: Bergens Tidende Articles
- **bt:vestlendingen**: Bergens Tidende - Vestlendingen
- **BuzzFeed**
@ -92,6 +94,7 @@ # Supported sites
- **Clipsyndicate**
- **Cloudy**
- **Clubic**
- **Clyp**
- **cmt.com**
- **CNET**
- **CNN**
@ -121,10 +124,12 @@ # Supported sites
- **DctpTv**
- **DeezerPlaylist**
- **defense.gouv.fr**
- **democracynow**
- **DHM**: Filmarchiv - Deutsches Historisches Museum
- **Discovery**
- **Dotsub**
- **DouyuTV**: 斗鱼
- **DPlay**
- **dramafever**
- **dramafever:series**
- **DRBonanza**
@ -159,6 +164,7 @@ # Supported sites
- **facebook**
- **faz.net**
- **fc2**
- **Fczenit**
- **fernsehkritik.tv**
- **Firstpost**
- **FiveTV**
@ -192,10 +198,10 @@ # Supported sites
- **Giga**
- **Glide**: Glide mobile video messages (glide.me)
- **Globo**
- **GloboArticle**
- **GodTube**
- **GoldenMoustache**
- **Golem**
- **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com
- **Goshgay**
- **Groupon**
- **Hark**
@ -279,9 +285,8 @@ # Supported sites
- **macgamestore**: MacGameStore trailers
- **mailru**: Видео@Mail.Ru
- **Malemotion**
- **MDR**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **MegaVideoz**
- **metacafe**
- **Metacritic**
- **Mgoon**
@ -363,6 +368,7 @@ # Supported sites
- **nowness:playlist**
- **nowness:series**
- **NowTV**
- **NowTVList**
- **nowvideo**: NowVideo
- **npo**: npo.nl and ntr.nl
- **npo.nl:live**
@ -422,7 +428,6 @@ # Supported sites
- **qqmusic:playlist**: QQ音乐 - 歌单
- **qqmusic:singer**: QQ音乐 - 歌手
- **qqmusic:toplist**: QQ音乐 - 排行榜
- **Quickscope**: Quick Scope
- **QuickVid**
- **R7**
- **radio.de**
@ -489,6 +494,7 @@ # Supported sites
- **soompi:show**
- **soundcloud**
- **soundcloud:playlist**
- **soundcloud:search**: Soundcloud search
- **soundcloud:set**
- **soundcloud:user**
- **soundgasm**
@ -515,6 +521,7 @@ # Supported sites
- **SSA**
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **Stitcher**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
@ -588,7 +595,8 @@ # Supported sites
- **twitch:stream**
- **twitch:video**
- **twitch:vod**
- **TwitterCard**
- **twitter**
- **twitter:card**
- **Ubu**
- **udemy**
- **udemy:course**
@ -613,7 +621,6 @@ # Supported sites
- **video.mit.edu**
- **VideoDetective**
- **videofy.me**
- **videolectures.net**
- **VideoMega**
- **VideoPremium**
- **VideoTt**: video.tt - Your True Tube
@ -623,6 +630,7 @@ # Supported sites
- **vier**
- **vier:videos**
- **Viewster**
- **Viidea**
- **viki**
- **viki:channel**
- **vimeo**
@ -665,6 +673,7 @@ # Supported sites
- **WSJ**: Wall Street Journal
- **XBef**
- **XboxClips**
- **XFileShare**: XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me
- **XHamster**
- **XHamsterEmbed**
- **XMinus**
@ -699,6 +708,7 @@ # Supported sites
- **youtube:show**: YouTube.com (multi-season) shows
- **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:user:playlists**: YouTube.com user playlists
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **Zapiks**
- **ZDF**

2
setup.py
View File

@ -28,7 +28,7 @@
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe'],
"dll_excludes": ['w9xpopen.exe', 'crypt32.dll'],
}
py2exe_console = [{

4
test/test_InfoExtractor.py
View File

@ -37,12 +37,16 @@ def test_opengraph(self):
<meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
<meta content='application/x-shockwave-flash' property='og:video:type'>
<meta content='Foo' property=og:foobar>
<meta name="og:test1" content='foo > < bar'/>
<meta name="og:test2" content="foo >//< bar"/>
'''
self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
self.assertEqual(ie._og_search_video_url(html, default=None), None)
self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
def test_html_search_meta(self):
ie = self.ie

17
test/test_compat.py
View File

@ -13,8 +13,10 @@
from youtube_dl.utils import get_filesystem_encoding
from youtube_dl.compat import (
compat_getenv,
compat_etree_fromstring,
compat_expanduser,
compat_shlex_split,
compat_str,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
@ -71,5 +73,20 @@ def test_compat_urllib_parse_unquote_plus(self):
def test_compat_shlex_split(self):
self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
def test_compat_etree_fromstring(self):
xml = '''
<root foo="bar" spam="中文">
<normal>foo</normal>
<chinese>中文</chinese>
<foo><bar>spam</bar></foo>
</root>
'''
doc = compat_etree_fromstring(xml.encode('utf-8'))
self.assertTrue(isinstance(doc.attrib['foo'], compat_str))
self.assertTrue(isinstance(doc.attrib['spam'], compat_str))
self.assertTrue(isinstance(doc.find('normal').text, compat_str))
self.assertTrue(isinstance(doc.find('chinese').text, compat_str))
self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str))
if __name__ == '__main__':
unittest.main()

2
test/test_download.py
View File

@ -102,7 +102,7 @@ def print_skipping(reason):
params = get_params(test_case.get('params', {}))
if is_playlist and 'playlist' not in test_case:
params.setdefault('extract_flat', True)
params.setdefault('extract_flat', 'in_playlist')
params.setdefault('skip_download', True)
ydl = YoutubeDL(params, auto_init=False)

3
test/test_jsinterp.py
View File

@ -19,6 +19,9 @@ def test_basic(self):
jsi = JSInterpreter('function x3(){return 42;}')
self.assertEqual(jsi.call_function('x3'), 42)
jsi = JSInterpreter('var x5 = function(){return 42;}')
self.assertEqual(jsi.call_function('x5'), 42)
def test_calc(self):
jsi = JSInterpreter('function x4(a){return 2*a+1;}')
self.assertEqual(jsi.call_function('x4', 3), 7)

21
test/test_subtitles.py
View File

@ -28,6 +28,7 @@
ThePlatformFeedIE,
RTVEALaCartaIE,
FunnyOrDieIE,
DemocracynowIE,
)
@ -346,5 +347,25 @@ def test_allsubtitles(self):
self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
class TestDemocracynowSubtitles(BaseTestSubtitles):
url = 'http://www.democracynow.org/shows/2015/7/3'
IE = DemocracynowIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
def test_subtitles_in_page(self):
self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
if __name__ == '__main__':
unittest.main()

36
test/test_utils.py
View File

@ -21,6 +21,7 @@
clean_html,
DateRange,
detect_exe_version,
determine_ext,
encodeFilename,
escape_rfc3986,
escape_url,
@ -68,6 +69,9 @@
cli_valueless_option,
cli_bool_option,
)
from youtube_dl.compat import (
compat_etree_fromstring,
)
class TestUtil(unittest.TestCase):
@ -207,8 +211,8 @@ def test_unescape_html(self):
self.assertEqual(unescapeHTML('%20;'), '%20;')
self.assertEqual(unescapeHTML('&#x2F;'), '/')
self.assertEqual(unescapeHTML('&#47;'), '/')
self.assertEqual(
unescapeHTML('&eacute;'), 'é')
self.assertEqual(unescapeHTML('&eacute;'), 'é')
self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
def test_daterange(self):
_20century = DateRange("19000101", "20000101")
@ -233,6 +237,14 @@ def test_unified_dates(self):
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
def test_find_xpath_attr(self):
testxml = '''<root>
@ -242,7 +254,7 @@ def test_find_xpath_attr(self):
<node x="b" y="d" />
<node x="" />
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
@ -263,7 +275,7 @@ def test_xpath_with_ns(self):
<url>http://server.com/download.mp3</url>
</media:song>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
self.assertTrue(find('media:song') is not None)
self.assertEqual(find('media:song/media:author').text, 'The Author')
@ -275,9 +287,16 @@ def test_xpath_element(self):
p = xml.etree.ElementTree.SubElement(div, 'p')
p.text = 'Foo'
self.assertEqual(xpath_element(doc, 'div/p'), p)
self.assertEqual(xpath_element(doc, ['div/p']), p)
self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
self.assertTrue(xpath_element(doc, 'div/bar') is None)
self.assertTrue(xpath_element(doc, ['div/bar']) is None)
self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
def test_xpath_text(self):
testxml = '''<root>
@ -285,7 +304,7 @@ def test_xpath_text(self):
<p>Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_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)
@ -297,7 +316,7 @@ def test_xpath_attr(self):
<p x="a">Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_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)
@ -425,6 +444,8 @@ def test_parse_iso8601(self):
self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
def test_strip_jsonp(self):
stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
@ -495,6 +516,9 @@ def test_js_to_json_realworld(self):
"playlist":[{"controls":{"all":null}}]
}''')
inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
json_code = js_to_json(inp)
self.assertEqual(json.loads(json_code), json.loads(inp))

9
test/test_youtube_lists.py
View File

@ -57,5 +57,14 @@ def test_youtube_toptracks(self):
entries = result['entries']
self.assertEqual(len(entries), 100)
def test_youtube_flat_playlist_titles(self):
dl = FakeYDL()
dl.params['extract_flat'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertIsPlaylist(result)
for entry in result['entries']:
self.assertTrue(entry.get('title'))
if __name__ == '__main__':
unittest.main()

19
youtube_dl/YoutubeDL.py
View File

@ -28,6 +28,7 @@
import ctypes
from .compat import (
compat_basestring,
compat_cookiejar,
compat_expanduser,
compat_get_terminal_size,
@ -37,6 +38,7 @@
compat_tokenize_tokenize,
compat_urllib_error,
compat_urllib_request,
compat_urllib_request_DataHandler,
)
from .utils import (
ContentTooShortError,
@ -62,6 +64,7 @@
SameFileError,
sanitize_filename,
sanitize_path,
sanitized_Request,
std_headers,
subtitles_filename,
UnavailableVideoError,
@ -155,7 +158,7 @@ class YoutubeDL(object):
writethumbnail: Write the thumbnail image to a file
write_all_thumbnails: Write all thumbnail formats to files
writesubtitles: Write the video subtitles to a file
writeautomaticsub: Write the automatic subtitles to a file
writeautomaticsub: Write the automatically generated subtitles to a file
allsubtitles: Downloads all the subtitles of the video
(requires writesubtitles or writeautomaticsub)
listsubtitles: Lists all available subtitles for the video
@ -571,7 +574,7 @@ def prepare_filename(self, info_dict):
if v is not None)
template_dict = collections.defaultdict(lambda: 'NA', template_dict)
outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
tmpl = compat_expanduser(outtmpl)
filename = tmpl % template_dict
# Temporary fix for #4787
@ -579,7 +582,7 @@ def prepare_filename(self, info_dict):
# to workaround encoding issues with subprocess on python2 @ Windows
if sys.version_info < (3, 0) and sys.platform == 'win32':
filename = encodeFilename(filename, True).decode(preferredencoding())
return filename
return sanitize_path(filename)
except ValueError as err:
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
return None
@ -832,6 +835,7 @@ def iter_playlistitems(format):
extra_info=extra)
playlist_results.append(entry_result)
ie_result['entries'] = playlist_results
self.to_screen('[download] Finished downloading playlist: %s' % playlist)
return ie_result
elif result_type == 'compat_list':
self.report_warning(
@ -936,7 +940,7 @@ def _parse_filter(tokens):
filter_parts.append(string)
def _remove_unused_ops(tokens):
# Remove operators that we don't use and join them with the sourrounding strings
# Remove operators that we don't use and join them with the surrounding strings
# for example: 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
ALLOWED_OPS = ('/', '+', ',', '(', ')')
last_string, last_start, last_end, last_line = None, None, None, None
@ -1185,7 +1189,7 @@ def _calc_headers(self, info_dict):
return res
def _calc_cookies(self, info_dict):
pr = compat_urllib_request.Request(info_dict['url'])
pr = sanitized_Request(info_dict['url'])
self.cookiejar.add_cookie_header(pr)
return pr.get_header('Cookie')
@ -1869,6 +1873,8 @@ def list_subtitles(self, video_id, subtitles, name='subtitles'):
def urlopen(self, req):
""" Start an HTTP download """
if isinstance(req, compat_basestring):
req = sanitized_Request(req)
return self._opener.open(req, timeout=self._socket_timeout)
def print_debug_header(self):
@ -1967,8 +1973,9 @@ def _setup_opener(self):
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
data_handler = compat_urllib_request_DataHandler()
opener = compat_urllib_request.build_opener(
proxy_handler, https_handler, cookie_processor, ydlh)
proxy_handler, https_handler, cookie_processor, ydlh, data_handler)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play

2
youtube_dl/__init__.py
View File

@ -377,7 +377,7 @@ def _real_main(argv=None):
with YoutubeDL(ydl_opts) as ydl:
# Update version
if opts.update_self:
update_self(ydl.to_screen, opts.verbose)
update_self(ydl.to_screen, opts.verbose, ydl._opener)
# Remove cache dir
if opts.rm_cachedir:

83
youtube_dl/compat.py
View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
import binascii
import collections
import email
import getpass
import io
import optparse
import os
import re
@ -11,6 +14,7 @@
import subprocess
import sys
import itertools
import xml.etree.ElementTree
try:
@ -38,6 +42,11 @@
except ImportError: # Python 2
import urlparse as compat_urlparse
try:
import urllib.response as compat_urllib_response
except ImportError: # Python 2
import urllib as compat_urllib_response
try:
import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
@ -155,6 +164,40 @@ def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace')
string = string.replace('+', ' ')
return compat_urllib_parse_unquote(string, encoding, errors)
try:
from urllib.request import DataHandler as compat_urllib_request_DataHandler
except ImportError: # Python < 3.4
# Ported from CPython 98774:1733b3bd46db, Lib/urllib/request.py
class compat_urllib_request_DataHandler(compat_urllib_request.BaseHandler):
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(":", 1)
mediatype, data = data.split(",", 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(";base64"):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = "text/plain;charset=US-ASCII"
headers = email.message_from_string(
"Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
try:
compat_basestring = basestring # Python 2
except NameError:
@ -170,6 +213,43 @@ def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace')
except ImportError: # Python 2.6
from xml.parsers.expat import ExpatError as compat_xml_parse_error
if sys.version_info[0] >= 3:
compat_etree_fromstring = xml.etree.ElementTree.fromstring
else:
# python 2.x tries to encode unicode strings with ascii (see the
# XMLParser._fixtext method)
etree = xml.etree.ElementTree
try:
_etree_iter = etree.Element.iter
except AttributeError: # Python <=2.6
def _etree_iter(root):
for el in root.findall('*'):
yield el
for sub in _etree_iter(el):
yield sub
# on 2.6 XML doesn't have a parser argument, function copied from CPython
# 2.7 source
def _XML(text, parser=None):
if not parser:
parser = etree.XMLParser(target=etree.TreeBuilder())
parser.feed(text)
return parser.close()
def _element_factory(*args, **kwargs):
el = etree.Element(*args, **kwargs)
for k, v in el.items():
if isinstance(v, bytes):
el.set(k, v.decode('utf-8'))
return el
def compat_etree_fromstring(text):
doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory)))
for el in _etree_iter(doc):
if el.text is not None and isinstance(el.text, bytes):
el.text = el.text.decode('utf-8')
return doc
try:
from urllib.parse import parse_qs as compat_parse_qs
@ -465,6 +545,7 @@ def compat_itertools_count(start=0, step=1):
'compat_chr',
'compat_cookiejar',
'compat_cookies',
'compat_etree_fromstring',
'compat_expanduser',
'compat_get_terminal_size',
'compat_getenv',
@ -489,6 +570,8 @@ def compat_itertools_count(start=0, step=1):
'compat_urllib_parse_unquote_to_bytes',
'compat_urllib_parse_urlparse',
'compat_urllib_request',
'compat_urllib_request_DataHandler',
'compat_urllib_response',
'compat_urlparse',
'compat_urlretrieve',
'compat_xml_parse_error',

2
youtube_dl/downloader/common.py
View File

@ -42,7 +42,7 @@ class FileDownloader(object):
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
(experimenatal)
(experimental)
external_downloader_args: A list of additional command-line arguments for the
external downloader.

4
youtube_dl/downloader/dash.py
View File

@ -3,7 +3,7 @@
import re
from .common import FileDownloader
from ..compat import compat_urllib_request
from ..utils import sanitized_Request
class DashSegmentsFD(FileDownloader):
@ -22,7 +22,7 @@ def real_download(self, filename, info_dict):
def append_url_to_file(outf, target_url, target_name, remaining_bytes=None):
self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name))
req = compat_urllib_request.Request(target_url)
req = sanitized_Request(target_url)
if remaining_bytes is not None:
req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))

22
youtube_dl/downloader/f4m.py
View File

@ -5,12 +5,13 @@
import itertools
import os
import time
import xml.etree.ElementTree as etree
from .fragment import FragmentFD
from ..compat import (
compat_etree_fromstring,
compat_urlparse,
compat_urllib_error,
compat_urllib_parse_urlparse,
)
from ..utils import (
encodeFilename,
@ -285,9 +286,11 @@ def real_download(self, filename, info_dict):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
manifest = self.ydl.urlopen(man_url).read()
urlh = self.ydl.urlopen(man_url)
man_url = urlh.geturl()
manifest = urlh.read()
doc = etree.fromstring(manifest)
doc = compat_etree_fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f)
for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None:
@ -329,20 +332,25 @@ def real_download(self, filename, info_dict):
if not live:
write_metadata_tag(dest_stream, metadata)
base_url_parsed = compat_urllib_parse_urlparse(base_url)
self._start_frag_download(ctx)
frags_filenames = []
while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
url = base_url + name
query = []
if base_url_parsed.query:
query.append(base_url_parsed.query)
if akamai_pv:
url += '?' + akamai_pv.strip(';')
query.append(akamai_pv.strip(';'))
if info_dict.get('extra_param_to_segment_url'):
url += info_dict.get('extra_param_to_segment_url')
query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
try:
success = ctx['dl'].download(frag_filename, {'url': url})
success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
if not success:
return False
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')

6
youtube_dl/downloader/hls.py
View File

@ -13,6 +13,7 @@
encodeArgument,
encodeFilename,
sanitize_open,
handle_youtubedl_headers,
)
@ -30,12 +31,13 @@ def real_download(self, filename, info_dict):
args = [ffpp.executable, '-y']
if info_dict['http_headers']:
if info_dict['http_headers'] and re.match(r'^https?://', url):
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
headers = handle_youtubedl_headers(info_dict['http_headers'])
args += [
'-headers',
''.join('%s: %s\r\n' % (key, val) for key, val in info_dict['http_headers'].items())]
''.join('%s: %s\r\n' % (key, val) for key, val in headers.items())]
args += ['-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc']

10
youtube_dl/downloader/http.py
View File

@ -7,14 +7,12 @@
import re
from .common import FileDownloader
from ..compat import (
compat_urllib_request,
compat_urllib_error,
)
from ..compat import compat_urllib_error
from ..utils import (
ContentTooShortError,
encodeFilename,
sanitize_open,
sanitized_Request,
)
@ -29,8 +27,8 @@ def real_download(self, filename, info_dict):
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
basic_request = compat_urllib_request.Request(url, None, headers)
request = compat_urllib_request.Request(url, None, headers)
basic_request = sanitized_Request(url, None, headers)
request = sanitized_Request(url, None, headers)
is_test = self.params.get('test', False)

2
youtube_dl/downloader/rtmp.py
View File

@ -117,7 +117,7 @@ def run_rtmpdump(args):
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# the connection was interrupted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = [
'rtmpdump', '--verbose', '-r', url,

40
youtube_dl/extractor/__init__.py
View File

@ -38,6 +38,7 @@
)
from .atresplayer import AtresPlayerIE
from .atttechchannel import ATTTechChannelIE
from .audimedia import AudiMediaIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .azubu import AzubuIE
from .baidu import BaiduVideoIE
@ -45,6 +46,7 @@
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbc import (
BBCCoUkIE,
BBCCoUkArticleIE,
BBCIE,
)
from .beeg import BeegIE
@ -58,7 +60,10 @@
from .bpb import BpbIE
from .br import BRIE
from .breakcom import BreakIE
from .brightcove import BrightcoveIE
from .brightcove import (
BrightcoveLegacyIE,
BrightcoveNewIE,
)
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE
from .c56 import C56IE
@ -88,6 +93,7 @@
from .clipsyndicate import ClipsyndicateIE
from .cloudy import CloudyIE
from .clubic import ClubicIE
from .clyp import ClypIE
from .cmt import CMTIE
from .cnet import CNETIE
from .cnn import (
@ -121,10 +127,12 @@
from .dcn import DCNIE
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .democracynow import DemocracynowIE
from .dfb import DFBIE
from .dhm import DHMIE
from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
from .dplay import DPlayIE
from .dramafever import (
DramaFeverIE,
DramaFeverSeriesIE,
@ -208,13 +216,15 @@
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
from .globo import GloboIE
from .globo import (
GloboIE,
GloboArticleIE,
)
from .godtube import GodTubeIE
from .goldenmoustache import GoldenMoustacheIE
from .golem import GolemIE
from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE
from .gorillavid import GorillaVidIE
from .goshgay import GoshgayIE
from .groupon import GrouponIE
from .hark import HarkIE
@ -413,7 +423,10 @@
NownessPlaylistIE,
NownessSeriesIE,
)
from .nowtv import NowTVIE
from .nowtv import (
NowTVIE,
NowTVListIE,
)
from .nowvideo import NowVideoIE
from .npo import (
NPOIE,
@ -451,10 +464,7 @@
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
from .periscope import (
PeriscopeIE,
QuickscopeIE,
)
from .periscope import PeriscopeIE
from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
@ -546,6 +556,10 @@
from .shared import SharedIE
from .sharesix import ShareSixIE
from .sina import SinaIE
from .skynewsarabia import (
SkyNewsArabiaIE,
SkyNewsArabiaArticleIE,
)
from .slideshare import SlideshareIE
from .slutload import SlutloadIE
from .smotri import (
@ -568,7 +582,8 @@
SoundcloudIE,
SoundcloudSetIE,
SoundcloudUserIE,
SoundcloudPlaylistIE
SoundcloudPlaylistIE,
SoundcloudSearchIE
)
from .soundgasm import (
SoundgasmIE,
@ -587,6 +602,7 @@
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .stitcher import StitcherIE
from .sport5 import Sport5IE
from .sportbox import (
SportBoxIE,
@ -691,7 +707,7 @@
TwitchBookmarksIE,
TwitchStreamIE,
)
from .twitter import TwitterCardIE
from .twitter import TwitterCardIE, TwitterIE
from .ubu import UbuIE
from .udemy import (
UdemyIE,
@ -718,7 +734,6 @@
from .vice import ViceIE
from .viddler import ViddlerIE
from .videodetective import VideoDetectiveIE
from .videolecturesnet import VideoLecturesNetIE
from .videofyme import VideofyMeIE
from .videomega import VideoMegaIE
from .videopremium import VideoPremiumIE
@ -728,6 +743,7 @@
from .vidzi import VidziIE
from .vier import VierIE, VierVideosIE
from .viewster import ViewsterIE
from .viidea import ViideaIE
from .vimeo import (
VimeoIE,
VimeoAlbumIE,
@ -780,6 +796,7 @@
from .wsj import WSJIE
from .xbef import XBefIE
from .xboxclips import XboxClipsIE
from .xfileshare import XFileShareIE
from .xhamster import (
XHamsterIE,
XHamsterEmbedIE,
@ -823,6 +840,7 @@
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
YoutubeUserIE,
YoutubeUserPlaylistsIE,
YoutubeWatchLaterIE,
)
from .zapiks import ZapiksIE

18
youtube_dl/extractor/abc.py
View File

@ -12,7 +12,7 @@
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
_VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@ -36,6 +36,18 @@ class ABCIE(InfoExtractor):
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
}, {
'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
},
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
'only_matching': True,
}]
def _real_extract(self, url):
@ -43,7 +55,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id)
mobj = re.search(
r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
raise ExtractorError('Unable to extract video urls')
@ -60,11 +72,13 @@ def _real_extract(self, url):
formats = [{
'url': url_info['url'],
'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
'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)
return {

2
youtube_dl/extractor/adultswim.py
View File

@ -183,7 +183,7 @@ def _real_extract(self, url):
media_url = file_el.text
if determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, segment_title, 'mp4', 'm3u8_native', preference=0, m3u8_id='hls'))
media_url, segment_title, 'mp4', preference=0, m3u8_id='hls'))
else:
formats.append({
'format_id': '%s_%s' % (bitrate, ftype),

4
youtube_dl/extractor/aljazeera.py
View File

@ -15,7 +15,7 @@ class AlJazeeraIE(InfoExtractor):
'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
'uploader': 'Al Jazeera English',
},
'add_ie': ['Brightcove'],
'add_ie': ['BrightcoveLegacy'],
'skip': 'Not accessible from Travis CI server',
}
@ -32,5 +32,5 @@ def _real_extract(self, url):
'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
'&%40videoPlayer={0}'.format(brightcove_id)
),
'ie_key': 'Brightcove',
'ie_key': 'BrightcoveLegacy',
}

4
youtube_dl/extractor/anitube.py
View File

@ -26,8 +26,8 @@ def _real_extract(self, url):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
key = self._html_search_regex(
r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
key = self._search_regex(
r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
config_xml = self._download_xml(
'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)

4
youtube_dl/extractor/ard.py
View File

@ -14,8 +14,8 @@
parse_duration,
unified_strdate,
xpath_text,
parse_xml,
)
from ..compat import compat_etree_fromstring
class ARDMediathekIE(InfoExtractor):
@ -161,7 +161,7 @@ def _real_extract(self, url):
raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = parse_xml(webpage)
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)

6
youtube_dl/extractor/atresplayer.py
View File

@ -7,11 +7,11 @@
from ..compat import (
compat_str,
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
int_or_none,
float_or_none,
sanitized_Request,
xpath_text,
ExtractorError,
)
@ -63,7 +63,7 @@ def _login(self):
'j_password': password,
}
request = compat_urllib_request.Request(
request = sanitized_Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = self._download_webpage(
@ -94,7 +94,7 @@ def _real_extract(self, url):
formats = []
for fmt in ['windows', 'android_tablet']:
request = compat_urllib_request.Request(
request = sanitized_Request(
self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
request.add_header('User-Agent', self._USER_AGENT)

80
youtube_dl/extractor/audimedia.py Normal file
View File

@ -0,0 +1,80 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
sanitized_Request,
)
class AudiMediaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)'
_TEST = {
'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test',
'md5': '79a8b71c46d49042609795ab59779b66',
'info_dict': {
'id': '1564',
'ext': 'mp4',
'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
'description': 'md5:60e5d30a78ced725f7b8d34370762941',
'upload_date': '20151124',
'timestamp': 1448354940,
'duration': 74022,
'view_count': int,
}
}
# extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken)
_AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload');
_, stage_mode, video_id, lang = raw_payload.split('-')
# TODO: handle s and e stage_mode (live streams and ended live streams)
if stage_mode not in ('s', 'e'):
request = sanitized_Request(
'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang),
headers={'X-Auth-Token': self._AUTH_TOKEN})
json_data = self._download_json(request, video_id)['results']
formats = []
stream_url_hls = json_data.get('stream_url_hls')
if stream_url_hls:
m3u8_formats = self._extract_m3u8_formats(stream_url_hls, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
stream_url_hds = json_data.get('stream_url_hds')
if stream_url_hds:
f4m_formats = self._extract_f4m_formats(json_data.get('stream_url_hds') + '?hdcore=3.4.0', video_id, -1, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
for video_version in json_data.get('video_versions'):
video_version_url = video_version.get('download_url') or video_version.get('stream_url')
if not video_version_url:
continue
formats.append({
'url': video_version_url,
'width': int_or_none(video_version.get('width')),
'height': int_or_none(video_version.get('height')),
'abr': int_or_none(video_version.get('audio_bitrate')),
'vbr': int_or_none(video_version.get('video_bitrate')),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': json_data['title'],
'description': json_data.get('subtitle'),
'thumbnail': json_data.get('thumbnail_image', {}).get('file'),
'timestamp': parse_iso8601(json_data.get('publication_date')),
'duration': int_or_none(json_data.get('duration')),
'view_count': int_or_none(json_data.get('view_count')),
'formats': formats,
}

6
youtube_dl/extractor/bambuser.py
View File

@ -6,13 +6,13 @@
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_str,
)
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
sanitized_Request,
)
@ -57,7 +57,7 @@ def _login(self):
'pass': password,
}
request = compat_urllib_request.Request(
request = sanitized_Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Referer', self._LOGIN_URL)
response = self._download_webpage(
@ -126,7 +126,7 @@ def _real_extract(self, url):
'&sort=created&access_mode=0%2C1%2C2&limit={count}'
'&method=broadcast&format=json&vid_older_than={last}'
).format(user=user, count=self._STEP, last=last_id)
req = compat_urllib_request.Request(req_url)
req = sanitized_Request(req_url)
# Without setting this header, we wouldn't get any result
req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
data = self._download_json(

8
youtube_dl/extractor/bandcamp.py
View File

@ -10,6 +10,8 @@
)
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
)
@ -52,11 +54,11 @@ def _real_extract(self, url):
ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
'url': format_url,
'url': self._proto_relative_url(format_url, 'http:'),
'ext': ext,
'vcodec': 'none',
'acodec': ext,
'abr': int(abr_str),
'abr': int_or_none(abr_str),
})
self._sort_formats(formats)
@ -65,7 +67,7 @@ def _real_extract(self, url):
'id': compat_str(data['id']),
'title': data['title'],
'formats': formats,
'duration': float(data['duration']),
'duration': float_or_none(data.get('duration')),
}
else:
raise ExtractorError('No free songs found')

61
youtube_dl/extractor/bbc.py
View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
@ -14,18 +13,22 @@
remove_end,
unescapeHTML,
)
from ..compat import compat_HTTPError
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
)
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
_ID_REGEX = r'[pb][\da-z]{7}'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails
# with geolocation in some cases when it's even not geo restricted at all (e.g.
# http://www.bbc.co.uk/programmes/b06bp7lf)
# http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
'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',
]
@ -332,7 +335,7 @@ def _download_media_selector(self, programme_id):
return self._download_media_selector_url(
mediaselector_url % programme_id, programme_id)
except BBCCoUkIE.MediaSelectionError as e:
if e.id in ('notukerror', 'geolocation'):
if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
last_exception = e
continue
self._raise_extractor_error(e)
@ -343,8 +346,8 @@ def _download_media_selector_url(self, url, programme_id=None):
media_selection = self._download_xml(
url, programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
else:
raise
return self._process_media_selector(media_selection, programme_id)
@ -421,7 +424,7 @@ def _extract_from_legacy_playlist(self, playlist, playlist_id):
continue
title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
description = description_el.text if description_el else None
description = description_el.text if description_el is not None else None
def get_programme_id(item):
def get_from_attributes(item):
@ -463,7 +466,7 @@ def _real_extract(self, url):
if not programme_id:
programme_id = self._search_regex(
r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
@ -625,6 +628,7 @@ class BBCIE(BBCCoUkIE):
'id': 'p02xycnp',
'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
'duration': 140,
},
'params': {
@ -651,7 +655,7 @@ class BBCIE(BBCCoUkIE):
@classmethod
def suitable(cls, url):
return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url)
return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
def _extract_from_media_meta(self, media_meta, video_id):
# Direct links to media in media metadata (e.g.
@ -777,8 +781,9 @@ def _real_extract(self, url):
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
programme_id = self._search_regex(
[r'data-video-player-vpid="([\da-z]{8})"',
r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
[r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
webpage, 'vpid', default=None)
if programme_id:
@ -813,7 +818,7 @@ def extract_all(pattern):
# Multiple video article (e.g.
# http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
entries = []
for match in extract_all(r'new\s+SMP\(({.+?})\)'):
embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
@ -902,3 +907,33 @@ def extract_all(pattern):
})
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
class BBCCoUkArticleIE(InfoExtractor):
_VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
IE_NAME = 'bbc.co.uk:article'
IE_DESC = 'BBC articles'
_TEST = {
'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
'info_dict': {
'id': '3jNQLTMrPlYGTBn0WV6M2MS',
'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
},
'playlist_count': 4,
'add_ie': ['BBCCoUk'],
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage).strip()
entries = [self.url_result(programme_url) for programme_url in re.findall(
r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
return self.playlist_result(entries, playlist_id, title, description)

28
youtube_dl/extractor/beeg.py
View File

@ -1,6 +1,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_chr,
compat_ord,
compat_urllib_parse_unquote,
)
from ..utils import (
int_or_none,
parse_iso8601,
@ -29,16 +34,35 @@ def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://beeg.com/api/v1/video/%s' % video_id, video_id)
'http://beeg.com/api/v3/video/%s' % video_id, video_id)
def decrypt_key(key):
# Reverse engineered from http://static.beeg.com/cpl/1067.js
a = '8RPUUCS35ZWp3ADnKcSmpH71ZusrROo'
e = compat_urllib_parse_unquote(key)
return ''.join([
compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 25)
for n in range(len(e))])
def decrypt_url(encrypted_url):
encrypted_url = self._proto_relative_url(
encrypted_url.replace('{DATA_MARKERS}', ''), 'http:')
key = self._search_regex(
r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None)
if not key:
return encrypted_url
return encrypted_url.replace(key, decrypt_key(key))
formats = []
for format_id, video_url in video.items():
if not video_url:
continue
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
if not height:
continue
formats.append({
'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
'url': decrypt_url(video_url),
'format_id': format_id,
'height': int(height),
})

149
youtube_dl/extractor/bilibili.py
View File

@ -2,141 +2,116 @@
from __future__ import unicode_literals
import re
import itertools
import json
import xml.etree.ElementTree as ET
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
)
from ..utils import (
int_or_none,
unified_strdate,
unescapeHTML,
ExtractorError,
)
class BiliBiliIE(InfoExtractor):
_VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
_VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
'md5': '2c301e4dab317596e837c3e7633e7d86',
'info_dict': {
'id': '1074402_part1',
'id': '1554319',
'ext': 'flv',
'title': '【金坷垃】金泡沫',
'duration': 308,
'duration': 308313,
'upload_date': '20140420',
'thumbnail': 're:^https?://.+\.jpg',
'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
'timestamp': 1397983878,
'uploader': '菊子桑',
},
}, {
'url': 'http://www.bilibili.com/video/av1041170/',
'info_dict': {
'id': '1041170',
'title': '【BD1080P】刀语【诸神&异域】',
'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
'uploader': '枫叶逝去',
'timestamp': 1396501299,
},
'playlist_count': 9,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page_num = mobj.group('page_num') or '1'
if '(此视频不存在或被删除)' in webpage:
raise ExtractorError(
'The video does not exist or was deleted', expected=True)
view_data = self._download_json(
'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num),
video_id)
if 'error' in view_data:
raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True)
if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
raise ExtractorError(
'The video is not available in your region due to copyright reasons',
expected=True)
cid = view_data['cid']
title = unescapeHTML(view_data['title'])
video_code = self._search_regex(
r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
title = self._html_search_meta(
'media:title', video_code, 'title', fatal=True)
duration_str = self._html_search_meta(
'duration', video_code, 'duration')
if duration_str is None:
duration = None
else:
duration_mobj = re.match(
r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
duration_str)
duration = (
int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
int(duration_mobj.group('minutes')) * 60 +
int(duration_mobj.group('seconds')))
upload_date = unified_strdate(self._html_search_meta(
'uploadDate', video_code, fatal=False))
thumbnail = self._html_search_meta(
'thumbnailUrl', video_code, 'thumbnail', fatal=False)
cid = self._search_regex(r'cid=(\d+)', webpage, 'cid')
entries = []
lq_page = self._download_webpage(
'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid,
video_id,
note='Downloading LQ video info'
page = self._download_webpage(
'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
cid,
'Downloading page %s/%s' % (page_num, view_data['pages'])
)
try:
err_info = json.loads(lq_page)
err_info = json.loads(page)
raise ExtractorError(
'BiliBili said: ' + err_info['error_text'], expected=True)
except ValueError:
pass
lq_doc = ET.fromstring(lq_page)
lq_durls = lq_doc.findall('./durl')
doc = compat_etree_fromstring(page)
hq_doc = self._download_xml(
'http://interface.bilibili.com/playurl?appkey=1&cid=%s' % cid,
video_id,
note='Downloading HQ video info',
fatal=False,
)
if hq_doc is not False:
hq_durls = hq_doc.findall('./durl')
assert len(lq_durls) == len(hq_durls)
else:
hq_durls = itertools.repeat(None)
entries = []
i = 1
for lq_durl, hq_durl in zip(lq_durls, hq_durls):
for durl in doc.findall('./durl'):
size = durl.find('./filesize|./size')
formats = [{
'format_id': 'lq',
'quality': 1,
'url': lq_durl.find('./url').text,
'filesize': int_or_none(
lq_durl.find('./size'), get_attr='text'),
'url': durl.find('./url').text,
'filesize': int_or_none(size.text) if size else None,
'ext': 'flv',
}]
if hq_durl is not None:
formats.append({
'format_id': 'hq',
'quality': 2,
'ext': 'flv',
'url': hq_durl.find('./url').text,
'filesize': int_or_none(
hq_durl.find('./size'), get_attr='text'),
})
self._sort_formats(formats)
backup_urls = durl.find('./backup_url')
if backup_urls is not None:
for backup_url in backup_urls.findall('./url'):
formats.append({'url': backup_url.text})
formats.reverse()
entries.append({
'id': '%s_part%d' % (video_id, i),
'id': '%s_part%s' % (cid, durl.find('./order').text),
'title': title,
'duration': int_or_none(durl.find('./length').text) // 1000,
'formats': formats,
'duration': duration,
'upload_date': upload_date,
'thumbnail': thumbnail,
})
i += 1
return {
'_type': 'multi_video',
'entries': entries,
'id': video_id,
'title': title
info = {
'id': str(cid),
'title': title,
'description': view_data.get('description'),
'thumbnail': view_data.get('pic'),
'uploader': view_data.get('author'),
'timestamp': int_or_none(view_data.get('created')),
'view_count': view_data.get('play'),
'duration': int_or_none(doc.find('./timelength').text),
}
if len(entries) == 1:
entries[0].update(info)
return entries[0]
else:
info.update({
'_type': 'multi_video',
'id': video_id,
'entries': entries,
})
return info

31
youtube_dl/extractor/bloomberg.py
View File

@ -6,9 +6,9 @@
class BloombergIE(InfoExtractor):
_VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
_TEST = {
_TESTS = [{
'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
# The md5 checksum changes
'info_dict': {
@ -17,22 +17,39 @@ class BloombergIE(InfoExtractor):
'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
'description': 'md5:a8ba0302912d03d246979735c17d2761',
},
}
}, {
'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
'only_matching': True,
}, {
'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump',
'only_matching': True,
}]
def _real_extract(self, url):
name = self._match_id(url)
webpage = self._download_webpage(url, name)
video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
video_id = self._search_regex(
r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
webpage, 'id', group='url')
title = re.sub(': Video$', '', self._og_search_title(webpage))
embed_info = self._download_json(
'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
formats = []
for stream in embed_info['streams']:
if stream["muxing_format"] == "TS":
formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
stream_url = stream.get('url')
if not stream_url:
continue
if stream['muxing_format'] == 'TS':
m3u8_formats = self._extract_m3u8_formats(
stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
else:
formats.extend(self._extract_f4m_formats(stream['url'], video_id))
f4m_formats = self._extract_f4m_formats(
stream_url, video_id, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
self._sort_formats(formats)
return {

184
youtube_dl/extractor/brightcove.py
View File

@ -3,15 +3,14 @@
import re
import json
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
compat_str,
compat_urllib_parse,
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urlparse,
compat_xml_parse_error,
)
@ -20,12 +19,18 @@
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
float_or_none,
js_to_json,
int_or_none,
parse_iso8601,
sanitized_Request,
unescapeHTML,
unsmuggle_url,
)
class BrightcoveIE(InfoExtractor):
class BrightcoveLegacyIE(InfoExtractor):
IE_NAME = 'brightcove:legacy'
_VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
_FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
@ -119,7 +124,7 @@ def _build_brighcove_url(cls, object_str):
object_str = fix_xml_ampersands(object_str)
try:
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
object_doc = compat_etree_fromstring(object_str.encode('utf-8'))
except compat_xml_parse_error:
return
@ -245,7 +250,7 @@ def _real_extract(self, url):
def _get_video_info(self, video_id, query_str, query, referer=None):
request_url = self._FEDERATED_URL_TEMPLATE % query_str
req = compat_urllib_request.Request(request_url)
req = sanitized_Request(request_url)
linkBase = query.get('linkBaseURL')
if linkBase is not None:
referer = linkBase[0]
@ -346,3 +351,172 @@ def _extract_video_info(self, video_info):
if 'url' not in info and not info.get('formats'):
raise ExtractorError('Unable to extract video url for %s' % info['id'])
return info
class BrightcoveNewIE(InfoExtractor):
IE_NAME = 'brightcove:new'
_VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+)'
_TESTS = [{
'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
'md5': 'c8100925723840d4b0d243f7025703be',
'info_dict': {
'id': '4463358922001',
'ext': 'mp4',
'title': 'Meet the man behind Popcorn Time',
'description': 'md5:eac376a4fe366edc70279bfb681aea16',
'duration': 165.768,
'timestamp': 1441391203,
'upload_date': '20150904',
'uploader_id': '929656772001',
'formats': 'mincount:22',
},
}, {
# with rtmp streams
'url': 'http://players.brightcove.net/4036320279001/5d112ed9-283f-485f-a7f9-33f42e8bc042_default/index.html?videoId=4279049078001',
'info_dict': {
'id': '4279049078001',
'ext': 'mp4',
'title': 'Titansgrave: Chapter 0',
'description': 'Titansgrave: Chapter 0',
'duration': 1242.058,
'timestamp': 1433556729,
'upload_date': '20150606',
'uploader_id': '4036320279001',
'formats': 'mincount:41',
},
'params': {
'skip_download': True,
}
}]
@staticmethod
def _extract_urls(webpage):
# Reference:
# 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe
# 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript)
# 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html
entries = []
# Look for iframe embeds [1]
for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
entries.append(url)
# Look for embed_in_page embeds [2]
for video_id, account_id, player_id, embed in re.findall(
# According to examples from [3] it's unclear whether video id
# may be optional and what to do when it is
r'''(?sx)
<video[^>]+
data-video-id=["\'](\d+)["\'][^>]*>.*?
</video>.*?
<script[^>]+
src=["\'](?:https?:)?//players\.brightcove\.net/
(\d+)/([\da-f-]+)_([^/]+)/index\.min\.js
''', webpage):
entries.append(
'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
% (account_id, player_id, embed, video_id))
return entries
def _real_extract(self, url):
account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
% (account_id, player_id, embed), video_id)
policy_key = None
catalog = self._search_regex(
r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
if catalog:
catalog = self._parse_json(
js_to_json(catalog), video_id, fatal=False)
if catalog:
policy_key = catalog.get('policyKey')
if not policy_key:
policy_key = self._search_regex(
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
req = sanitized_Request(
'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s'
% (account_id, video_id),
headers={'Accept': 'application/json;pk=%s' % policy_key})
json_data = self._download_json(req, video_id)
title = json_data['name']
formats = []
for source in json_data.get('sources', []):
source_type = source.get('type')
src = source.get('src')
if source_type == 'application/x-mpegURL':
if not src:
continue
m3u8_formats = self._extract_m3u8_formats(
src, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
else:
streaming_src = source.get('streaming_src')
stream_name, app_name = source.get('stream_name'), source.get('app_name')
if not src and not streaming_src and (not stream_name or not app_name):
continue
tbr = float_or_none(source.get('avg_bitrate'), 1000)
height = int_or_none(source.get('height'))
f = {
'tbr': tbr,
'width': int_or_none(source.get('width')),
'height': height,
'filesize': int_or_none(source.get('size')),
'container': source.get('container'),
'vcodec': source.get('codec'),
'ext': source.get('container').lower(),
}
def build_format_id(kind):
format_id = kind
if tbr:
format_id += '-%dk' % int(tbr)
if height:
format_id += '-%dp' % height
return format_id
if src or streaming_src:
f.update({
'url': src or streaming_src,
'format_id': build_format_id('http' if src else 'http-streaming'),
'preference': 2 if src else 1,
})
else:
f.update({
'url': app_name,
'play_path': stream_name,
'format_id': build_format_id('rtmp'),
})
formats.append(f)
self._sort_formats(formats)
description = json_data.get('description')
thumbnail = json_data.get('thumbnail')
timestamp = parse_iso8601(json_data.get('published_at'))
duration = float_or_none(json_data.get('duration'), 1000)
tags = json_data.get('tags', [])
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'uploader_id': account_id,
'formats': formats,
'tags': tags,
}

43
youtube_dl/extractor/canalc2.py
View File

@ -4,38 +4,53 @@
import re
from .common import InfoExtractor
from ..utils import parse_duration
class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv'
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
_TEST = {
'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
'url': 'http://www.canalc2.tv/video/12163',
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
'id': '12163',
'ext': 'mp4',
'title': 'Terrasses du Numérique'
'ext': 'flv',
'title': 'Terrasses du Numérique',
'duration': 122,
},
'params': {
'skip_download': True, # Requires rtmpdump
}
}
def _real_extract(self, url):
video_id = re.match(self._VALID_URL, url).group('id')
# We need to set the voir field for getting the file name
url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
file_name = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);",
webpage, 'file name')
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
video_url = self._search_regex(
r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
webpage, 'video_url', group='file')
formats = [{'url': video_url}]
if video_url.startswith('rtmp://'):
rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
formats[0].update({
'url': rtmp.group('url'),
'ext': 'flv',
'app': rtmp.group('app'),
'play_path': rtmp.group('play_path'),
'page_url': url,
})
title = self._html_search_regex(
r'class="evenement8">(.*?)</a>', webpage, 'title')
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
duration = parse_duration(self._search_regex(
r'id=["\']video_duree["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
return {
'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
'duration': duration,
'formats': formats,
}

14
youtube_dl/extractor/cbs.py
View File

@ -1,6 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
sanitized_Request,
smuggle_url,
)
class CBSIE(InfoExtractor):
@ -46,13 +50,19 @@ class CBSIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
request = sanitized_Request(url)
# Android UA is served with higher quality (720p) streams (see
# https://github.com/rg3/youtube-dl/issues/7490)
request.add_header('User-Agent', 'Mozilla/5.0 (Linux; Android 4.4; Nexus 5)')
webpage = self._download_webpage(request, display_id)
real_id = self._search_regex(
[r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
webpage, 'real video ID')
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': 'theplatform:%s' % real_id,
'url': smuggle_url(
'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true&manifest=m3u' % real_id,
{'force_smil_url': True}),
'display_id': display_id,
}

5
youtube_dl/extractor/cbsnews.py
View File

@ -67,9 +67,12 @@ def _real_extract(self, url):
'format_id': format_id,
}
if uri.startswith('rtmp'):
play_path = re.sub(
r'{slistFilePath}', '',
uri.split('<break>')[-1].split('{break}')[-1])
fmt.update({
'app': 'ondemand?auth=cbs',
'play_path': 'mp4:' + uri.split('<break>')[-1],
'play_path': 'mp4:' + play_path,
'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
'page_url': 'http://www.cbsnews.com',
'ext': 'flv',

6
youtube_dl/extractor/ceskatelevize.py
View File

@ -5,7 +5,6 @@
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urllib_parse_urlparse,
@ -13,6 +12,7 @@
from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
)
@ -100,7 +100,7 @@ def _real_extract(self, url):
'requestSource': 'iVysilani',
}
req = compat_urllib_request.Request(
req = sanitized_Request(
'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
data=compat_urllib_parse.urlencode(data))
@ -115,7 +115,7 @@ def _real_extract(self, url):
if playlist_url == 'error_region':
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url))
req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url)
playlist_title = self._og_search_title(webpage)

57
youtube_dl/extractor/clyp.py Normal file
View File

@ -0,0 +1,57 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
parse_iso8601,
)
class ClypIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)'
_TEST = {
'url': 'https://clyp.it/ojz2wfah',
'md5': '1d4961036c41247ecfdcc439c0cddcbb',
'info_dict': {
'id': 'ojz2wfah',
'ext': 'mp3',
'title': 'Krisson80 - bits wip wip',
'description': '#Krisson80BitsWipWip #chiptune\n#wip',
'duration': 263.21,
'timestamp': 1443515251,
'upload_date': '20150929',
},
}
def _real_extract(self, url):
audio_id = self._match_id(url)
metadata = self._download_json(
'https://api.clyp.it/%s' % audio_id, audio_id)
formats = []
for secure in ('', 'Secure'):
for ext in ('Ogg', 'Mp3'):
format_id = '%s%s' % (secure, ext)
format_url = metadata.get('%sUrl' % format_id)
if format_url:
formats.append({
'url': format_url,
'format_id': format_id,
'vcodec': 'none',
})
self._sort_formats(formats)
title = metadata['Title']
description = metadata.get('Description')
duration = float_or_none(metadata.get('Duration'))
timestamp = parse_iso8601(metadata.get('DateCreated'))
return {
'id': audio_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
}

5
youtube_dl/extractor/cmt.py
View File

@ -4,7 +4,7 @@
class CMTIE(MTVIE):
IE_NAME = 'cmt.com'
_VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
_VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
_FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
_TESTS = [{
@ -16,4 +16,7 @@ class CMTIE(MTVIE):
'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
'description': 'Blame It All On My Roots',
},
}, {
'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
'only_matching': True,
}]

4
youtube_dl/extractor/collegerama.py
View File

@ -3,10 +3,10 @@
import json
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
float_or_none,
int_or_none,
sanitized_Request,
)
@ -52,7 +52,7 @@ def _real_extract(self, url):
}
}
request = compat_urllib_request.Request(
request = sanitized_Request(
'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
json.dumps(player_options_request))
request.add_header('Content-Type', 'application/json')

35
youtube_dl/extractor/common.py
View File

@ -10,20 +10,18 @@
import socket
import sys
import time
import xml.etree.ElementTree
from ..compat import (
compat_cookiejar,
compat_cookies,
compat_getpass,
compat_HTTPError,
compat_http_client,
compat_urllib_error,
compat_urllib_parse,
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urlparse,
compat_str,
compat_etree_fromstring,
)
from ..utils import (
NO_DEFAULT,
@ -38,6 +36,7 @@
int_or_none,
RegexNotFoundError,
sanitize_filename,
sanitized_Request,
unescapeHTML,
unified_strdate,
url_basename,
@ -168,10 +167,11 @@ class InfoExtractor(object):
"ext" will be calculated from URL if missing
automatic_captions: Like 'subtitles', used by the YoutubeIE for
automatically generated captions
duration: Length of the video in seconds, as an integer.
duration: Length of the video in seconds, as an integer or float.
view_count: How many users have watched the video on the platform.
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
repost_count: Number of reposts of the video
average_rating: Average rating give by users, the scale used depends on the webpage
comment_count: Number of comments on the video
comments: A list of comments, each with one or more of the following
@ -310,11 +310,11 @@ def _real_extract(self, url):
@classmethod
def ie_key(cls):
"""A string for getting the InfoExtractor with get_info_extractor"""
return cls.__name__[:-2]
return compat_str(cls.__name__[:-2])
@property
def IE_NAME(self):
return type(self).__name__[:-2]
return compat_str(type(self).__name__[:-2])
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
""" Returns the response handle """
@ -461,7 +461,7 @@ def _download_xml(self, url_or_request, video_id,
return xml_string
if transform_source:
xml_string = transform_source(xml_string)
return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
return compat_etree_fromstring(xml_string.encode('utf-8'))
def _download_json(self, url_or_request, video_id,
note='Downloading JSON metadata',
@ -645,7 +645,7 @@ def _get_tfa_info(self, note='two-factor verification code'):
# Helper functions for extracting OpenGraph info
@staticmethod
def _og_regexes(prop):
content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\'|\s*([^\s"\'=<>`]+?))'
content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
% {'prop': re.escape(prop)})
template = r'<meta[^>]+?%s[^>]+?%s'
@ -841,7 +841,7 @@ def _is_valid_url(self, url, video_id, item='video'):
self._request_webpage(url, video_id, 'Checking %s URL' % item)
return True
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
if isinstance(e.cause, compat_urllib_error.URLError):
self.to_screen(
'%s: %s URL is invalid, skipping' % (video_id, item))
return False
@ -891,6 +891,11 @@ def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=N
if not media_nodes:
manifest_version = '2.0'
media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
base_url = xpath_text(
manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'],
'base URL', default=None)
if base_url:
base_url = base_url.strip()
for i, media_el in enumerate(media_nodes):
if manifest_version == '2.0':
media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
@ -898,7 +903,7 @@ def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=N
continue
manifest_url = (
media_url if media_url.startswith('http://') or media_url.startswith('https://')
else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url))
else ((base_url or '/'.join(manifest_url.split('/')[:-1])) + '/' + media_url))
# If media_url is itself a f4m manifest do the recursive extraction
# since bitrates in parent manifest (this one) and media_url manifest
# may differ leading to inability to resolve the format by requested
@ -943,13 +948,15 @@ def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u))
m3u8_doc = self._download_webpage(
res = self._download_webpage_handle(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
errnote=errnote or 'Failed to download m3u8 information',
fatal=fatal)
if m3u8_doc is False:
return m3u8_doc
if res is False:
return res
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
last_info = None
last_media = None
kv_rex = re.compile(
@ -1278,7 +1285,7 @@ def _set_cookie(self, domain, name, value, expire_time=None):
def _get_cookies(self, url):
""" Return a compat_cookies.SimpleCookie with the cookies for the url """
req = compat_urllib_request.Request(url)
req = sanitized_Request(url)
self._downloader.cookiejar.add_cookie_header(req)
return compat_cookies.SimpleCookie(req.get_header('Cookie'))

104
youtube_dl/extractor/crunchyroll.py
View File

@ -5,12 +5,12 @@
import json
import base64
import zlib
import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urllib_request,
@ -21,7 +21,9 @@
bytes_to_intlist,
intlist_to_bytes,
int_or_none,
lowercase_escape,
remove_end,
sanitized_Request,
unified_strdate,
urlencode_postdata,
xpath_text,
@ -32,9 +34,29 @@
class CrunchyrollBaseIE(InfoExtractor):
_NETRC_MACHINE = 'crunchyroll'
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = sanitized_Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
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))
else sanitized_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
@ -46,10 +68,22 @@ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, f
return super(CrunchyrollBaseIE, self)._download_webpage(
request, video_id, note, errnote, fatal, tries, timeout, encoding)
@staticmethod
def _add_skip_wall(url):
parsed_url = compat_urlparse.urlparse(url)
qs = compat_urlparse.parse_qs(parsed_url.query)
# Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
# > This content may be inappropriate for some people.
# > Are you sure you want to continue?
# since it's not disabled by default in crunchyroll account's settings.
# See https://github.com/rg3/youtube-dl/issues/7202.
qs['skip_wall'] = ['1']
return compat_urlparse.urlunparse(
parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
class CrunchyrollIE(CrunchyrollBaseIE):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_NETRC_MACHINE = 'crunchyroll'
_TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'info_dict': {
@ -72,7 +106,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'id': '589804',
'ext': 'flv',
'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Danny Choo Network',
'upload_date': '20120213',
@ -81,10 +115,13 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# rtmp
'skip_download': True,
},
}, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True,
}, {
# geo-restricted (US), 18+ maturity wall, non-premium available
'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
'only_matching': True,
}]
_FORMAT_IDS = {
@ -94,24 +131,6 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'1080': ('80', '108'),
}
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
@ -217,7 +236,7 @@ def ass_bool(strvalue):
return output
def _extract_subtitles(self, subtitle):
sub_root = xml.etree.ElementTree.fromstring(subtitle)
sub_root = compat_etree_fromstring(subtitle)
return [{
'ext': 'srt',
'data': self._convert_subtitles_to_srt(sub_root),
@ -228,7 +247,7 @@ def _extract_subtitles(self, subtitle):
def _get_subtitles(self, video_id, webpage):
subtitles = {}
for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
sub_page = self._download_webpage(
'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
video_id, note='Downloading subtitles for ' + sub_name)
@ -254,7 +273,7 @@ def _real_extract(self, url):
else:
webpage_url = 'http://www.' + mobj.group('url')
webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='')
@ -270,11 +289,15 @@ def _real_extract(self, url):
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 = self._html_search_regex(
r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
webpage, 'video_title')
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_description = self._html_search_regex(
r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
webpage, 'description', default=None)
if video_description:
video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
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)
@ -285,7 +308,7 @@ def _real_extract(self, url):
'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)
playerdata_req = sanitized_Request(playerdata_url)
playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
@ -297,7 +320,7 @@ def _real_extract(self, url):
for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
stream_quality, stream_format = self._FORMAT_IDS[fmt]
video_format = fmt + 'p'
streamdata_req = compat_urllib_request.Request(
streamdata_req = sanitized_Request(
'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
% (stream_id, stream_format, stream_quality),
compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
@ -352,7 +375,7 @@ def _real_extract(self, url):
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\-]+))/?$'
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
_TESTS = [{
'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@ -361,12 +384,25 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
},
'playlist_count': 13,
}, {
# geo-restricted (US), 18+ maturity wall, non-premium available
'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
'info_dict': {
'id': 'cosplay-complex-ova',
'title': 'Cosplay Complex OVA'
},
'playlist_count': 3,
'skip': 'Georestricted',
}, {
# geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
'only_matching': True,
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
webpage = self._download_webpage(self._add_skip_wall(url), show_id)
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')

114
youtube_dl/extractor/cspan.py
View File

@ -9,6 +9,7 @@
find_xpath_attr,
smuggle_url,
determine_ext,
ExtractorError,
)
from .senateisvp import SenateISVPIE
@ -18,33 +19,32 @@ class CSpanIE(InfoExtractor):
IE_DESC = 'C-SPAN'
_TESTS = [{
'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
'md5': '8e44ce11f0f725527daccc453f553eb0',
'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
'info_dict': {
'id': '315139',
'ext': 'mp4',
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
'description': 'Attorney General Eric Holder speaks to reporters following the Supreme Court decision in [Shelby County v. Holder], in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced.',
},
'skip': 'Regularly fails on travis, for unknown reasons',
}, {
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
# For whatever reason, the served video alternates between
# two different ones
'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
'info_dict': {
'id': '340723',
'id': 'c4486943',
'ext': 'mp4',
'title': 'International Health Care Models',
'title': 'CSPAN - International Health Care Models',
'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
}
}, {
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
'md5': '446562a736c6bf97118e389433ed88d4',
'md5': '2ae5051559169baadba13fc35345ae74',
'info_dict': {
'id': '342759',
'ext': 'mp4',
'title': 'General Motors Ignition Switch Recall',
'duration': 14848,
'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
},
}, {
# Video from senate.gov
@ -57,67 +57,77 @@ class CSpanIE(InfoExtractor):
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
page_id = mobj.group('id')
webpage = self._download_webpage(url, page_id)
video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
if matches:
video_type, video_id = matches.groups()
if video_type == 'prog':
video_type = 'program'
else:
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
title = self._og_search_title(webpage)
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
description = self._html_search_regex(
[
# The full description
r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
# If the description is small enough the other div is not
# present, otherwise this is a stripped version
r'<p class=\'initial\'>(.*?)</p>'
],
webpage, 'description', flags=re.DOTALL, default=None)
def get_text_attr(d, attr):
return d.get(attr, {}).get('#text')
info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
data = self._download_json(info_url, video_id)
data = self._download_json(
'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
video_id)['video']
if data['@status'] != 'Success':
raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
doc = self._download_xml(
'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
video_id)
description = self._html_search_meta('description', webpage)
title = find_xpath_attr(doc, './/string', 'name', 'title').text
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
files = data['files']
capfile = get_text_attr(data, 'capfile')
files = data['video']['files']
try:
capfile = data['video']['capfile']['#text']
except KeyError:
capfile = None
entries = [{
'id': '%s_%d' % (video_id, partnum + 1),
'title': (
title if len(files) == 1 else
'%s part %d' % (title, partnum + 1)),
'url': unescapeHTML(f['path']['#text']),
'description': description,
'thumbnail': thumbnail,
'duration': int_or_none(f.get('length', {}).get('#text')),
'subtitles': {
'en': [{
'url': capfile,
'ext': determine_ext(capfile, 'dfxp')
}],
} if capfile else None,
} for partnum, f in enumerate(files)]
entries = []
for partnum, f in enumerate(files):
formats = []
for quality in f['qualities']:
formats.append({
'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
'url': unescapeHTML(get_text_attr(quality, 'file')),
'height': int_or_none(get_text_attr(quality, 'height')),
'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
})
self._sort_formats(formats)
entries.append({
'id': '%s_%d' % (video_id, partnum + 1),
'title': (
title if len(files) == 1 else
'%s part %d' % (title, partnum + 1)),
'formats': formats,
'description': description,
'thumbnail': thumbnail,
'duration': int_or_none(get_text_attr(f, 'length')),
'subtitles': {
'en': [{
'url': capfile,
'ext': determine_ext(capfile, 'dfxp')
}],
} if capfile else None,
})
if len(entries) == 1:
entry = dict(entries[0])
entry['id'] = video_id
entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
return entry
else:
return {
'_type': 'playlist',
'entries': entries,
'title': title,
'id': video_id,
'id': 'c' + video_id if video_type == 'clip' else video_id,
}

39
youtube_dl/extractor/dailymotion.py
View File

@ -7,15 +7,13 @@
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_request,
)
from ..compat import compat_str
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
parse_iso8601,
sanitized_Request,
str_to_int,
unescapeHTML,
)
@ -25,7 +23,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
@staticmethod
def _build_request(url):
"""Build a request with the family filter disabled"""
request = compat_urllib_request.Request(url)
request = sanitized_Request(url)
request.add_header('Cookie', 'family_filter=off; ff=off')
return request
@ -96,6 +94,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader': 'HotWaves1012',
'age_limit': 18,
}
},
# geo-restricted, player v5
{
'url': 'http://www.dailymotion.com/video/xhza0o',
'only_matching': True,
}
]
@ -124,6 +127,9 @@ def _real_extract(self, url):
if player_v5:
player = self._parse_json(player_v5, video_id)
metadata = player['metadata']
self._check_error(metadata)
formats = []
for quality, media_list in metadata['qualities'].items():
for media in media_list:
@ -133,9 +139,17 @@ def _real_extract(self, url):
type_ = media.get('type')
if type_ == 'application/vnd.lumberjack.manifest':
continue
if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls'))
ext = determine_ext(media_url)
if type_ == 'application/x-mpegURL' or ext == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
elif type_ == 'application/f4m' or ext == 'f4m':
f4m_formats = self._extract_f4m_formats(
media_url, video_id, preference=-1, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
else:
f = {
'url': media_url,
@ -201,9 +215,7 @@ def _real_extract(self, url):
'video info', flags=re.MULTILINE),
video_id)
if info.get('error') is not None:
msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
raise ExtractorError(msg, expected=True)
self._check_error(info)
formats = []
for (key, format_id) in self._FORMATS:
@ -246,6 +258,11 @@ def _real_extract(self, url):
'duration': info['duration']
}
def _check_error(self, info):
if info.get('error') is not None:
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
def _get_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(

14
youtube_dl/extractor/dbtv.py
View File

@ -13,8 +13,8 @@
class DBTVIE(InfoExtractor):
_VALID_URL = r'http://dbtv\.no/(?P<id>[0-9]+)#(?P<display_id>.+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
_TESTS = [{
'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
'info_dict': {
@ -30,12 +30,18 @@ class DBTVIE(InfoExtractor):
'view_count': int,
'categories': list,
}
}
}, {
'url': 'http://dbtv.no/3649835190001',
'only_matching': True,
}, {
'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
display_id = mobj.group('display_id') or video_id
data = self._download_json(
'http://api.dbtv.no/discovery/%s' % video_id, display_id)

8
youtube_dl/extractor/dcn.py
View File

@ -2,13 +2,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse
from ..utils import (
int_or_none,
parse_iso8601,
sanitized_Request,
)
@ -36,7 +34,7 @@ class DCNIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
request = compat_urllib_request.Request(
request = sanitized_Request(
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
headers={'Origin': 'http://www.dcndigital.ae'})

88
youtube_dl/extractor/democracynow.py Normal file
View File

@ -0,0 +1,88 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import os.path
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
url_basename,
remove_start,
)
class DemocracynowIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
IE_NAME = 'democracynow'
_TESTS = [{
'url': 'http://www.democracynow.org/shows/2015/7/3',
'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
'info_dict': {
'id': '2015-0703-001',
'ext': 'mp4',
'title': 'July 03, 2015 - Democracy Now!',
'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
},
}, {
'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
'info_dict': {
'id': '2015-0703-001',
'ext': 'mp4',
'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
description = self._og_search_description(webpage)
json_data = self._parse_json(self._search_regex(
r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
display_id)
video_id = None
formats = []
default_lang = 'en'
subtitles = {}
def add_subtitle_item(lang, info_dict):
if lang not in subtitles:
subtitles[lang] = []
subtitles[lang].append(info_dict)
# chapter_file are not subtitles
if 'caption_file' in json_data:
add_subtitle_item(default_lang, {
'url': compat_urlparse.urljoin(url, json_data['caption_file']),
})
for subtitle_item in json_data.get('captions', []):
lang = subtitle_item.get('language', '').lower() or default_lang
add_subtitle_item(lang, {
'url': compat_urlparse.urljoin(url, subtitle_item['url']),
})
for key in ('file', 'audio', 'video'):
media_url = json_data.get(key, '')
if not media_url:
continue
media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
formats.append({
'url': media_url,
})
self._sort_formats(formats)
return {
'id': video_id or display_id,
'title': json_data['title'],
'description': description,
'subtitles': subtitles,
'formats': formats,
}

51
youtube_dl/extractor/dplay.py Normal file
View File

@ -0,0 +1,51 @@
# encoding: utf-8
from __future__ import unicode_literals
import time
from .common import InfoExtractor
from ..utils import int_or_none
class DPlayIE(InfoExtractor):
_VALID_URL = r'http://www\.dplay\.se/[^/]+/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
'info_dict': {
'id': '3172',
'ext': 'mp4',
'display_id': 'season-1-svensken-lar-sig-njuta-av-livet',
'title': 'Svensken lär sig njuta av livet',
'duration': 2650,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-video-id="(\d+)"', webpage, 'video id')
info = self._download_json(
'http://www.dplay.se/api/v2/ajax/videos?video_id=' + video_id,
video_id)['data'][0]
self._set_cookie(
'secure.dplay.se', 'dsc-geo',
'{"countryCode":"NL","expiry":%d}' % ((time.time() + 20 * 60) * 1000))
# TODO: consider adding support for 'stream_type=hds', it seems to
# require setting some cookies
manifest_url = self._download_json(
'https://secure.dplay.se/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % video_id,
video_id, 'Getting manifest url for hls stream')['hls']
formats = self._extract_m3u8_formats(
manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native')
return {
'id': video_id,
'display_id': display_id,
'title': info['title'],
'formats': formats,
'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
}

4
youtube_dl/extractor/dramafever.py
View File

@ -7,7 +7,6 @@
from ..compat import (
compat_HTTPError,
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
)
from ..utils import (
@ -16,6 +15,7 @@
determine_ext,
int_or_none,
parse_iso8601,
sanitized_Request,
)
@ -51,7 +51,7 @@ def _login(self):
'password': password,
}
request = compat_urllib_request.Request(
request = sanitized_Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
response = self._download_webpage(
request, None, 'Logging in as %s' % username)

17
youtube_dl/extractor/dumpert.py
View File

@ -2,14 +2,17 @@
from __future__ import unicode_literals
import base64
import re
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import qualities
from ..utils import (
qualities,
sanitized_Request,
)
class DumpertIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
_VALID_URL = r'(?P<protocol>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',
@ -26,10 +29,12 @@ class DumpertIE(InfoExtractor):
}]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
protocol = mobj.group('protocol')
url = 'https://www.dumpert.nl/mediabase/' + video_id
req = compat_urllib_request.Request(url)
url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
req = sanitized_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

@ -87,7 +87,7 @@ def _real_extract(self, url):
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
formats = self._extract_m3u8_formats(
m3u8_url, video_id,
'mp4', entry_protocol='m3u8_native')
'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
mp4_url = self._get_video_url(
# Secure mp4 URL is constructed according to Player.prototype.mp4 from

95
youtube_dl/extractor/eitb.py
View File

@ -1,39 +1,92 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .brightcove import BrightcoveIE
from ..utils import ExtractorError
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
sanitized_Request,
)
class EitbIE(InfoExtractor):
IE_NAME = 'eitb.tv'
_VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
_VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)'
_TEST = {
'add_ie': ['Brightcove'],
'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/',
'md5': 'edf4436247185adee3ea18ce64c47998',
'info_dict': {
'id': '2743577154001',
'id': '4090227752001',
'ext': 'mp4',
'title': '60 minutos (Lasa y Zabala, 30 años)',
# All videos from eitb has this description in the brightcove info
'description': '.',
'uploader': 'Euskal Telebista',
'description': 'Programa de reportajes de actualidad.',
'duration': 3996.76,
'timestamp': 1381789200,
'upload_date': '20131014',
'tags': list,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
chapter_id = mobj.group('chapter_id')
webpage = self._download_webpage(url, chapter_id)
bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if bc_url is None:
raise ExtractorError('Could not extract the Brightcove url')
# The BrightcoveExperience object doesn't contain the video id, we set
# it manually
bc_url += '&%40videoPlayer={0}'.format(chapter_id)
return self.url_result(bc_url, BrightcoveIE.ie_key())
video_id = self._match_id(url)
video = self._download_json(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/%s/' % video_id,
video_id, 'Downloading video JSON')
media = video['web_media'][0]
formats = []
for rendition in media['RENDITIONS']:
video_url = rendition.get('PMD_URL')
if not video_url:
continue
tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
format_id = 'http'
if tbr:
format_id += '-%d' % int(tbr)
formats.append({
'url': rendition['PMD_URL'],
'format_id': format_id,
'width': int_or_none(rendition.get('FRAME_WIDTH')),
'height': int_or_none(rendition.get('FRAME_HEIGHT')),
'tbr': tbr,
})
hls_url = media.get('HLS_SURL')
if hls_url:
request = sanitized_Request(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
headers={'Referer': url})
token_data = self._download_json(
request, video_id, 'Downloading auth token', fatal=False)
if token_data:
token = token_data.get('token')
if token:
m3u8_formats = self._extract_m3u8_formats(
'%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
hds_url = media.get('HDS_SURL')
if hds_url:
f4m_formats = self._extract_f4m_formats(
'%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'),
video_id, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
self._sort_formats(formats)
return {
'id': video_id,
'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'],
'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'),
'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'),
'duration': float_or_none(media.get('LENGTH'), 1000),
'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '),
'tags': media.get('TAGS'),
'formats': formats,
}

5
youtube_dl/extractor/escapist.py
View File

@ -3,13 +3,12 @@
import json
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
determine_ext,
clean_html,
int_or_none,
float_or_none,
sanitized_Request,
)
@ -75,7 +74,7 @@ def _real_extract(self, url):
video_id = ims_video['videoID']
key = ims_video['hash']
config_req = compat_urllib_request.Request(
config_req = sanitized_Request(
'http://www.escapistmagazine.com/videos/'
'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
config_req.add_header('Referer', url)

8
youtube_dl/extractor/everyonesmixtape.py
View File

@ -3,11 +3,9 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
from ..utils import (
ExtractorError,
sanitized_Request,
)
@ -42,7 +40,7 @@ def _real_extract(self, url):
playlist_id = mobj.group('id')
pllist_url = 'http://everyonesmixtape.com/mixtape.php?a=getMixes&u=-1&linked=%s&explore=' % playlist_id
pllist_req = compat_urllib_request.Request(pllist_url)
pllist_req = sanitized_Request(pllist_url)
pllist_req.add_header('X-Requested-With', 'XMLHttpRequest')
playlist_list = self._download_json(
@ -55,7 +53,7 @@ def _real_extract(self, url):
raise ExtractorError('Playlist id not found')
pl_url = 'http://everyonesmixtape.com/mixtape.php?a=getMix&id=%s&userId=null&code=' % playlist_no
pl_req = compat_urllib_request.Request(pl_url)
pl_req = sanitized_Request(pl_url)
pl_req.add_header('X-Requested-With', 'XMLHttpRequest')
playlist = self._download_json(
pl_req, playlist_id, note='Downloading playlist info')

61
youtube_dl/extractor/extremetube.py
View File

@ -3,23 +3,20 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_request,
)
from ..utils import (
qualities,
int_or_none,
sanitized_Request,
str_to_int,
)
class ExtremeTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
_VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
_TESTS = [{
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
'info_dict': {
'id': '652431',
'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'ext': 'mp4',
'title': 'Music Video 14 british euro brit european cumshots swallow',
'uploader': 'unknown',
@ -29,14 +26,18 @@ class ExtremeTubeIE(InfoExtractor):
}, {
'url': 'http://www.extremetube.com/gay/video/abcde-1234',
'only_matching': True,
}, {
'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
'only_matching': True,
}, {
'url': 'http://www.extremetube.com/video/652431',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req = sanitized_Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
@ -49,20 +50,36 @@ def _real_extract(self, url):
r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
webpage, 'view count', fatal=False))
flash_vars = compat_parse_qs(self._search_regex(
r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
flash_vars = self._parse_json(
self._search_regex(
r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
video_id)
formats = []
quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
for k, vals in flash_vars.items():
m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
if m is not None:
formats.append({
'format_id': m.group('quality'),
'quality': quality(m.group('quality')),
'url': vals[0],
for quality_key, video_url in flash_vars.items():
height = int_or_none(self._search_regex(
r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
if not height:
continue
f = {
'url': video_url,
}
mobj = re.search(
r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
if mobj:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'height': height,
'tbr': bitrate,
})
else:
f.update({
'format_id': '%dp' % height,
'height': height,
})
formats.append(f)
self._sort_formats(formats)
return {

33
youtube_dl/extractor/facebook.py
View File

@ -10,12 +10,11 @@
compat_str,
compat_urllib_error,
compat_urllib_parse_unquote,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
int_or_none,
limit_length,
sanitized_Request,
urlencode_postdata,
get_element_by_id,
clean_html,
@ -74,7 +73,7 @@ def _login(self):
if useremail is None:
return
login_page_req = compat_urllib_request.Request(self._LOGIN_URL)
login_page_req = sanitized_Request(self._LOGIN_URL)
login_page_req.add_header('Cookie', 'locale=en_US')
login_page = self._download_webpage(login_page_req, None,
note='Downloading login page',
@ -95,7 +94,7 @@ def _login(self):
'timezone': '-60',
'trynum': '1',
}
request = compat_urllib_request.Request(self._LOGIN_URL, urlencode_postdata(login_form))
request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
try:
login_results = self._download_webpage(request, None,
@ -110,7 +109,7 @@ def _login(self):
r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
'name_action_selected': 'dont_save',
}
check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
check_response = self._download_webpage(check_req, None,
note='Confirming login')
@ -142,16 +141,20 @@ def _real_extract(self, url):
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
params = json.loads(params_raw)
video_data = params['video_data'][0]
formats = []
for quality in ['sd', 'hd']:
src = video_data.get('%s_src' % quality)
if src is not None:
formats.append({
'format_id': quality,
'url': src,
})
for format_id, f in params['video_data'].items():
if not f or not isinstance(f, list):
continue
for quality in ('sd', 'hd'):
for src_type in ('src', 'src_no_ratelimit'):
src = f[0].get('%s_%s' % (quality, src_type))
if src:
formats.append({
'format_id': '%s_%s_%s' % (format_id, quality, src_type),
'url': src,
'preference': -10 if format_id == 'progressive' else 0,
})
if not formats:
raise ExtractorError('Cannot find video formats')
@ -161,7 +164,7 @@ def _real_extract(self, url):
if not video_title:
video_title = self._html_search_regex(
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
webpage, 'alternative title', fatal=False)
webpage, 'alternative title', default=None)
video_title = limit_length(video_title, 80)
if not video_title:
video_title = 'Facebook video #%s' % video_id
@ -171,7 +174,5 @@ def _real_extract(self, url):
'id': video_id,
'title': video_title,
'formats': formats,
'duration': int_or_none(video_data.get('video_duration')),
'thumbnail': video_data.get('thumbnail_src'),
'uploader': uploader,
}

5
youtube_dl/extractor/fc2.py
View File

@ -12,6 +12,7 @@
from ..utils import (
encode_dict,
ExtractorError,
sanitized_Request,
)
@ -57,7 +58,7 @@ def _login(self):
}
login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8')
request = compat_urllib_request.Request(
request = sanitized_Request(
'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
@ -66,7 +67,7 @@ def _login(self):
return False
# this is also needed
login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done')
login_redir = sanitized_Request('http://id.fc2.com/?mode=redirect&login=done')
self._download_webpage(
login_redir, None, note='Login redirect', errnote='Login redirect failed')

4
youtube_dl/extractor/flickr.py
View File

@ -3,10 +3,10 @@
import re
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
ExtractorError,
find_xpath_attr,
sanitized_Request,
)
@ -30,7 +30,7 @@ def _real_extract(self, url):
video_id = mobj.group('id')
video_uploader_id = mobj.group('uploader_id')
webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
req = compat_urllib_request.Request(webpage_url)
req = sanitized_Request(webpage_url)
req.add_header(
'User-Agent',
# it needs a more recent version

6
youtube_dl/extractor/fourtube.py
View File

@ -3,12 +3,10 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
from ..utils import (
parse_duration,
parse_iso8601,
sanitized_Request,
str_to_int,
)
@ -93,7 +91,7 @@ def _real_extract(self, url):
b'Content-Type': b'application/x-www-form-urlencoded',
b'Origin': b'http://www.4tube.com',
}
token_req = compat_urllib_request.Request(token_url, b'{}', headers)
token_req = sanitized_Request(token_url, b'{}', headers)
tokens = self._download_json(token_req, video_id)
formats = [{
'url': tokens[format]['token'],

28
youtube_dl/extractor/francetv.py
View File

@ -83,6 +83,14 @@ def _extract_video(self, video_id, catalogue):
if subtitle:
title += ' - %s' % subtitle
subtitles = {}
subtitles_list = [{
'url': subformat['url'],
'ext': subformat.get('format'),
} for subformat in info.get('subtitles', []) if subformat.get('url')]
if subtitles_list:
subtitles['fr'] = subtitles_list
return {
'id': video_id,
'title': title,
@ -91,20 +99,27 @@ def _extract_video(self, video_id, catalogue):
'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
'timestamp': int_or_none(info['diffusion']['timestamp']),
'formats': formats,
'subtitles': subtitles,
}
class PluzzIE(FranceTVBaseInfoExtractor):
IE_NAME = 'pluzz.francetv.fr'
_VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
_VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P<id>.+?)\.html'
# Can't use tests, videos expire in 7 days
def _real_extract(self, url):
title = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, title)
video_id = self._search_regex(
r'data-diffusion="(\d+)"', webpage, 'ID')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_meta(
'id_video', webpage, 'video id', default=None)
if not video_id:
video_id = self._search_regex(
r'data-diffusion=["\'](\d+)', webpage, 'video id')
return self._extract_video(video_id, 'Pluzz')
@ -120,6 +135,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
'title': 'Soir 3',
'upload_date': '20130826',
'timestamp': 1377548400,
'subtitles': {
'fr': 'mincount:2',
},
},
}, {
'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',

15
youtube_dl/extractor/funnyordie.py
View File

@ -45,11 +45,20 @@ def _real_extract(self, url):
links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
bitrates.sort()
m3u8_url = self._search_regex(
r'<source[^>]+src=(["\'])(?P<url>.+?/master\.m3u8)\1',
webpage, 'm3u8 url', default=None, group='url')
formats = []
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)]
bitrates.sort()
for bitrate in bitrates:
for link in links:
formats.append({

61
youtube_dl/extractor/gametrailers.py
View File

@ -1,19 +1,62 @@
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_age_limit,
url_basename,
)
class GametrailersIE(MTVServicesInfoExtractor):
_VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
class GametrailersIE(InfoExtractor):
_VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
_TEST = {
'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7',
'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review',
'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a',
'info_dict': {
'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d',
'id': '2983958',
'ext': 'mp4',
'title': 'E3 2013: Debut Trailer',
'description': 'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
'display_id': '116437-Just-Cause-3-Review',
'title': 'Just Cause 3 - Review',
'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?',
},
}
_FEED_URL = 'http://www.gametrailers.com/feeds/mrss'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = self._html_search_regex(
r'<title>(.+?)\|', webpage, 'title').strip()
embed_url = self._proto_relative_url(
self._search_regex(
r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage,
'embed url'),
scheme='http:')
video_id = url_basename(embed_url)
embed_page = self._download_webpage(embed_url, video_id)
embed_vars_json = self._search_regex(
r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page,
'embed vars')
info = self._parse_json(embed_vars_json, video_id)
formats = []
for media in info['media']:
if media['mediaPurpose'] == 'play':
formats.append({
'url': media['uri'],
'height': media['height'],
'width:': media['width'],
})
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'formats': formats,
'thumbnail': info.get('thumbUri'),
'description': self._og_search_description(webpage),
'duration': int_or_none(info.get('videoLengthInSeconds')),
'age_limit': parse_age_limit(info.get('audienceRating')),
}

8
youtube_dl/extractor/gdcvault.py
View File

@ -3,13 +3,11 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse
from ..utils import (
remove_end,
HEADRequest,
sanitized_Request,
)
@ -125,7 +123,7 @@ def _login(self, webpage_url, display_id):
'password': password,
}
request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form))
request = sanitized_Request(login_url, compat_urllib_parse.urlencode(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(request, display_id, 'Logging in')
start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')

109
youtube_dl/extractor/generic.py
View File

@ -9,8 +9,8 @@
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
compat_etree_fromstring,
compat_urllib_parse_unquote,
compat_urllib_request,
compat_urlparse,
compat_xml_parse_error,
)
@ -21,7 +21,7 @@
HEADRequest,
is_html,
orderedSet,
parse_xml,
sanitized_Request,
smuggle_url,
unescapeHTML,
unified_strdate,
@ -30,7 +30,10 @@
url_basename,
xpath_text,
)
from .brightcove import BrightcoveIE
from .brightcove import (
BrightcoveLegacyIE,
BrightcoveNewIE,
)
from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
@ -140,6 +143,7 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'upload_date': '20130627',
'formats': 'mincount:16',
'subtitles': 'mincount:1',
},
@ -273,7 +277,7 @@ class GenericIE(InfoExtractor):
# it also tests brightcove videos that need to set the 'Referer' in the
# http requests
{
'add_ie': ['Brightcove'],
'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
'info_dict': {
'id': '2765128793001',
@ -297,7 +301,7 @@ class GenericIE(InfoExtractor):
'uploader': 'thestar.com',
'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
},
'add_ie': ['Brightcove'],
'add_ie': ['BrightcoveLegacy'],
},
{
'url': 'http://www.championat.com/video/football/v/87/87499.html',
@ -312,7 +316,7 @@ class GenericIE(InfoExtractor):
},
{
# https://github.com/rg3/youtube-dl/issues/3541
'add_ie': ['Brightcove'],
'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
'info_dict': {
'id': '3866516442001',
@ -818,6 +822,19 @@ class GenericIE(InfoExtractor):
'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
},
},
# Kaltura embed protected with referrer
{
'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
'info_dict': {
'id': '1_g4fbemnq',
'ext': 'mp4',
'title': 'Violetta - Achter De Schermen - Ruggero',
'description': 'Achter de schermen met Ruggero',
'timestamp': 1435133761,
'upload_date': '20150624',
'uploader_id': 'echojecka',
},
},
# Eagle.Platform embed (generic URL)
{
'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@ -1029,6 +1046,31 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'cinemasnob',
},
},
# BrightcoveInPageEmbed embed
{
'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
'info_dict': {
'id': '4238694884001',
'ext': 'flv',
'title': 'Tabletop: Dread, Last Thoughts',
'description': 'Tabletop: Dread, Last Thoughts',
'duration': 51690,
},
},
# JWPlayer with M3U8
{
'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
'info_dict': {
'id': 'playlist',
'ext': 'mp4',
'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
'uploader': 'ren.tv',
},
'params': {
# m3u8 downloads
'skip_download': True,
}
}
]
@ -1172,7 +1214,7 @@ def _real_extract(self, url):
full_response = None
if head_response is False:
request = compat_urllib_request.Request(url)
request = sanitized_Request(url)
request.add_header('Accept-Encoding', '*')
full_response = self._request_webpage(request, video_id)
head_response = full_response
@ -1201,7 +1243,7 @@ def _real_extract(self, url):
'%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
if not full_response:
request = compat_urllib_request.Request(url)
request = sanitized_Request(url)
# Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
# making it impossible to download only chunk of the file (yet we need only 512kB to
# test whether it's HTML or not). According to youtube-dl default Accept-Encoding
@ -1236,7 +1278,7 @@ def _real_extract(self, url):
# Is it an RSS feed, a SMIL file or a XSPF playlist?
try:
doc = parse_xml(webpage)
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
@ -1288,14 +1330,14 @@ def _playlist_from_matches(matches, getter=None, ie=None):
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
# Look for BrightCove:
bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
# Look for Brightcove Legacy Studio embeds
bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
self.to_screen('Brightcove video detected.')
entries = [{
'_type': 'url',
'url': smuggle_url(bc_url, {'Referer': url}),
'ie_key': 'Brightcove'
'ie_key': 'BrightcoveLegacy'
} for bc_url in bc_urls]
return {
@ -1305,6 +1347,11 @@ def _playlist_from_matches(matches, getter=None, ie=None):
'entries': entries,
}
# Look for Brightcove New Studio embeds
bc_urls = BrightcoveNewIE._extract_urls(webpage)
if bc_urls:
return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
# Look for embedded rtl.nl player
matches = re.findall(
r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
@ -1665,10 +1712,12 @@ def _playlist_from_matches(matches, getter=None, ie=None):
return self.url_result(mobj.group('url'), 'Zapiks')
# Look for Kaltura embeds
mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
if mobj is not None:
return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
return self.url_result(smuggle_url(
'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
{'source_url': url}), 'Kaltura')
# Look for Eagle.Platform embeds
mobj = re.search(
@ -1713,7 +1762,7 @@ def _playlist_from_matches(matches, getter=None, ie=None):
# Look for UDN embeds
mobj = re.search(
r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
if mobj is not None:
return self.url_result(
compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
@ -1833,6 +1882,7 @@ def filter_video(urls):
entries = []
for video_url in found:
video_url = video_url.replace('\\/', '/')
video_url = compat_urlparse.urljoin(url, video_url)
video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
@ -1844,25 +1894,24 @@ def filter_video(urls):
# here's a fun little line of code for you:
video_id = os.path.splitext(video_id)[0]
entry_info_dict = {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
}
ext = determine_ext(video_url)
if ext == 'smil':
entries.append({
'id': video_id,
'formats': self._extract_smil_formats(video_url, video_id),
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
})
entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
elif ext == 'xspf':
return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
elif ext == 'm3u8':
entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
else:
entries.append({
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
})
entry_info_dict['url'] = video_url
entries.append(entry_info_dict)
if len(entries) == 1:
return entries[0]

159
youtube_dl/extractor/globo.py
View File

@ -14,79 +14,58 @@
ExtractorError,
float_or_none,
int_or_none,
str_or_none,
)
class GloboIE(InfoExtractor):
_VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)'
_VALID_URL = '(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
_API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
_SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s'
_VIDEOID_REGEXES = [
r'\bdata-video-id="(\d+)"',
r'\bdata-player-videosids="(\d+)"',
r'<div[^>]+\bid="(\d+)"',
]
_RESIGN_EXPIRATION = 86400
_TESTS = [
{
'url': 'http://globotv.globo.com/sportv/futebol-nacional/v/os-gols-de-atletico-mg-3-x-2-santos-pela-24a-rodada-do-brasileirao/3654973/',
'md5': '03ebf41cb7ade43581608b7d9b71fab0',
'info_dict': {
'id': '3654973',
'ext': 'mp4',
'title': 'Os gols de Atlético-MG 3 x 2 Santos pela 24ª rodada do Brasileirão',
'duration': 251.585,
'uploader': 'SporTV',
'uploader_id': 698,
'like_count': int,
}
_TESTS = [{
'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/',
'md5': 'b3ccc801f75cd04a914d51dadb83a78d',
'info_dict': {
'id': '3607726',
'ext': 'mp4',
'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa',
'duration': 103.204,
'uploader': 'Globo.com',
'uploader_id': '265',
},
{
'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/',
'md5': 'b3ccc801f75cd04a914d51dadb83a78d',
'info_dict': {
'id': '3607726',
'ext': 'mp4',
'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa',
'duration': 103.204,
'uploader': 'Globo.com',
'uploader_id': 265,
'like_count': int,
}
}, {
'url': 'http://globoplay.globo.com/v/4581987/',
'md5': 'f36a1ecd6a50da1577eee6dd17f67eff',
'info_dict': {
'id': '4581987',
'ext': 'mp4',
'title': 'Acidentes de trânsito estão entre as maiores causas de queda de energia em SP',
'duration': 137.973,
'uploader': 'Rede Globo',
'uploader_id': '196',
},
{
'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
'info_dict': {
'id': '3652183',
'ext': 'mp4',
'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
'duration': 110.711,
'uploader': 'Rede Globo',
'uploader_id': 196,
'like_count': int,
}
},
{
'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
'md5': 'c1defca721ce25b2354e927d3e4b3dec',
'info_dict': {
'id': '3928201',
'ext': 'mp4',
'title': 'Ator e diretor argentino, Ricado Darín fala sobre utopias e suas perdas',
'duration': 1472.906,
'uploader': 'Canal Brasil',
'uploader_id': 705,
'like_count': int,
}
},
]
}, {
'url': 'http://canalbrasil.globo.com/programas/sangue-latino/videos/3928201.html',
'only_matching': True,
}, {
'url': 'http://globosatplay.globo.com/globonews/v/4472924/',
'only_matching': True,
}, {
'url': 'http://globotv.globo.com/t/programa/v/clipe-sexo-e-as-negas-adeus/3836166/',
'only_matching': True,
}, {
'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
'only_matching': True,
}, {
'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html',
'only_matching': True,
}]
class MD5():
class MD5:
HEX_FORMAT_LOWERCASE = 0
HEX_FORMAT_UPPERCASE = 1
BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = ''
@ -353,9 +332,6 @@ def lshift(value, count):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
video = self._download_json(
self._API_URL_TEMPLATE % video_id, video_id)['videos'][0]
@ -364,7 +340,7 @@ def _real_extract(self, url):
formats = []
for resource in video['resources']:
resource_id = resource.get('_id')
if not resource_id:
if not resource_id or resource_id.endswith('manifest'):
continue
security = self._download_json(
@ -393,20 +369,23 @@ def _real_extract(self, url):
resource_url = resource['url']
signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(signed_url, resource_id, 'mp4'))
m3u8_formats = self._extract_m3u8_formats(
signed_url, resource_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
else:
formats.append({
'url': signed_url,
'format_id': resource_id,
'height': resource.get('height'),
'format_id': 'http-%s' % resource_id,
'height': int_or_none(resource.get('height')),
})
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')
uploader_id = str_or_none(video.get('channel_id'))
return {
'id': video_id,
@ -414,6 +393,46 @@ def _real_extract(self, url):
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'like_count': like_count,
'formats': formats
}
class GloboArticleIE(InfoExtractor):
_VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)\.html'
_VIDEOID_REGEXES = [
r'\bdata-video-id=["\'](\d{7,})',
r'\bdata-player-videosids=["\'](\d{7,})',
r'\bvideosIDs\s*:\s*["\'](\d{7,})',
r'\bdata-id=["\'](\d{7,})',
r'<div[^>]+\bid=["\'](\d{7,})',
]
_TESTS = [{
'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
'info_dict': {
'id': '3652183',
'ext': 'mp4',
'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
'duration': 110.711,
'uploader': 'Rede Globo',
'uploader_id': '196',
}
}, {
'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html',
'only_matching': True,
}, {
'url': 'http://gshow.globo.com/programas/tv-xuxa/O-Programa/noticia/2014/01/xuxa-e-junno-namoram-muuuito-em-luau-de-zeze-di-camargo-e-luciano.html',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if GloboIE.suitable(url) else super(GloboArticleIE, cls).suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
return self.url_result('globo:%s' % video_id, 'Globo')

2
youtube_dl/extractor/googleplus.py
View File

@ -61,7 +61,7 @@ def unicode_escape(s):
'width': int(width),
'height': int(height),
} for width, height, video_url in re.findall(
r'\d+,(\d+),(\d+),"(https?://redirector\.googlevideo\.com.*?)"', webpage)]
r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent.com.*?)"', webpage)]
self._sort_formats(formats)
return {

8
youtube_dl/extractor/hearthisat.py
View File

@ -4,12 +4,10 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
compat_urlparse,
)
from ..compat import compat_urlparse
from ..utils import (
HEADRequest,
sanitized_Request,
str_to_int,
urlencode_postdata,
urlhandle_detect_ext,
@ -47,7 +45,7 @@ def _real_extract(self, url):
r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
payload = urlencode_postdata({'tracks[]': track_id})
req = compat_urllib_request.Request(self._PLAYLIST_URL, payload)
req = sanitized_Request(self._PLAYLIST_URL, payload)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
track = self._download_json(req, track_id, 'Downloading playlist')[0]

8
youtube_dl/extractor/hotnewhiphop.py
View File

@ -3,13 +3,11 @@
import base64
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse
from ..utils import (
ExtractorError,
HEADRequest,
sanitized_Request,
)
@ -41,7 +39,7 @@ def _real_extract(self, url):
('mediaType', 's'),
('mediaId', video_id),
])
r = compat_urllib_request.Request(
r = sanitized_Request(
'http://www.hotnewhiphop.com/ajax/media/getActions/', data=reqdata)
r.add_header('Content-Type', 'application/x-www-form-urlencoded')
mkd = self._download_json(

10
youtube_dl/extractor/hypem.py
View File

@ -4,12 +4,10 @@
import time
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse
from ..utils import (
ExtractorError,
sanitized_Request,
)
@ -32,7 +30,7 @@ def _real_extract(self, url):
data = {'ax': 1, 'ts': time.time()}
data_encoded = compat_urllib_parse.urlencode(data)
complete_url = url + "?" + data_encoded
request = compat_urllib_request.Request(complete_url)
request = sanitized_Request(complete_url)
response, urlh = self._download_webpage_handle(
request, track_id, 'Downloading webpage with the url')
cookie = urlh.headers.get('Set-Cookie', '')
@ -52,7 +50,7 @@ def _real_extract(self, url):
title = track['song']
serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
request = compat_urllib_request.Request(
request = sanitized_Request(
serve_url, '', {'Content-Type': 'application/json'})
request.add_header('cookie', cookie)
song_data = self._download_json(request, track_id, 'Downloading metadata')

29
youtube_dl/extractor/imdb.py
View File

@ -4,8 +4,8 @@
import json
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
from ..utils import (
qualities,
)
@ -30,24 +30,33 @@ def _real_extract(self, url):
descr = self._html_search_regex(
r'(?s)<span itemprop="description">(.*?)</span>',
webpage, 'description', fatal=False)
available_formats = re.findall(
r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
flags=re.MULTILINE)
player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
player_page = self._download_webpage(
player_url, video_id, 'Downloading player page')
# the player page contains the info for the default format, we have to
# fetch other pages for the rest of the formats
extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
format_pages = [
self._download_webpage(
f_url, video_id, 'Downloading info for %s format' % f_name)
for f_url, f_name in extra_formats]
format_pages.append(player_page)
quality = qualities(['SD', '480p', '720p'])
formats = []
for f_id, f_path in available_formats:
f_path = f_path.strip()
format_page = self._download_webpage(
compat_urlparse.urljoin(url, f_path),
'Downloading info for %s format' % f_id)
for format_page in format_pages:
json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
format_page, 'json data', flags=re.DOTALL)
info = json.loads(json_data)
format_info = info['videoPlayerObject']['video']
f_id = format_info['ffname']
formats.append({
'format_id': f_id,
'url': format_info['videoInfoList'][0]['videoUrl'],
'quality': quality(f_id),
})
self._sort_formats(formats)
return {
'id': video_id,

9
youtube_dl/extractor/instagram.py
View File

@ -10,8 +10,8 @@
class InstagramIE(InfoExtractor):
_VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
'info_dict': {
@ -21,7 +21,10 @@ class InstagramIE(InfoExtractor):
'title': 'Video by naomipq',
'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
}
}
}, {
'url': 'https://instagram.com/p/-Cmh1cukG2/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)

6
youtube_dl/extractor/iprima.py
View File

@ -6,12 +6,10 @@
from math import floor
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
from ..utils import (
ExtractorError,
remove_end,
sanitized_Request,
)
@ -61,7 +59,7 @@ def _real_extract(self, url):
(floor(random() * 1073741824), floor(random() * 1073741824))
)
req = compat_urllib_request.Request(player_url)
req = sanitized_Request(player_url)
req.add_header('Referer', url)
playerpage = self._download_webpage(req, video_id)

6
youtube_dl/extractor/iqiyi.py
View File

@ -205,9 +205,9 @@ def get_raw_data(self, tvid, video_id, enc_key, _uuid):
def get_enc_key(self, swf_url, video_id):
# TODO: automatic key extraction
# last update at 2015-10-10 for Zombie::bite
# '7239670519b6ac209a0bee4ef0446a6b24894b8ac2751506e42116212a0d0272e505'[2:66][1::2]
enc_key = '97596c0abee04ab49ba25564161ad225'
# last update at 2015-10-22 for Zombie::bite
# '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2]
enc_key = '2c76de15dcb44bd28ff0927d50d31620'
return enc_key
def _real_extract(self, url):

6
youtube_dl/extractor/ivi.py
View File

@ -5,11 +5,9 @@
import json
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
from ..utils import (
ExtractorError,
sanitized_Request,
)
@ -78,7 +76,7 @@ def _real_extract(self, url):
]
}
request = compat_urllib_request.Request(api_url, json.dumps(data))
request = sanitized_Request(api_url, json.dumps(data))
video_json_page = self._download_webpage(
request, video_id, 'Downloading video JSON')

2
youtube_dl/extractor/jeuxvideo.py
View File

@ -28,7 +28,7 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group(1)
webpage = self._download_webpage(url, title)
title = self._html_search_meta('name', webpage)
title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
config_url = self._html_search_regex(
r'data-src="(/contenu/medias/video.php.*?)"',
webpage, 'config URL')

52
youtube_dl/extractor/kaltura.py
View File

@ -2,12 +2,18 @@
from __future__ import unicode_literals
import re
import base64
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
clean_html,
ExtractorError,
int_or_none,
unsmuggle_url,
)
@ -16,7 +22,7 @@ class KalturaIE(InfoExtractor):
(?:
kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)|
https?://
(:?(?:www|cdnapisec)\.)?kaltura\.com/
(:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/
(?:
(?:
# flash player
@ -121,31 +127,47 @@ def _get_video_info(self, video_id, partner_id):
video_id, actions, note='Downloading video info JSON')
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
mobj = re.match(self._VALID_URL, url)
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)
formats = [{
'format_id': '%(fileExt)s-%(bitrate)s' % f,
'ext': f['fileExt'],
'tbr': f['bitrate'],
'fps': f.get('frameRate'),
'filesize_approx': int_or_none(f.get('size'), invscale=1024),
'container': f.get('containerFormat'),
'vcodec': f.get('videoCodecId'),
'height': f.get('height'),
'width': f.get('width'),
'url': '%s/flavorId/%s' % (info['dataUrl'], f['id']),
} for f in source_data['flavorAssets']]
source_url = smuggled_data.get('source_url')
if source_url:
referrer = base64.b64encode(
'://'.join(compat_urlparse.urlparse(source_url)[:2])
.encode('utf-8')).decode('utf-8')
else:
referrer = None
formats = []
for f in source_data['flavorAssets']:
video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id'])
if referrer:
video_url += '?referrer=%s' % referrer
formats.append({
'format_id': '%(fileExt)s-%(bitrate)s' % f,
'ext': f.get('fileExt'),
'tbr': int_or_none(f['bitrate']),
'fps': int_or_none(f.get('frameRate')),
'filesize_approx': int_or_none(f.get('size'), invscale=1024),
'container': f.get('containerFormat'),
'vcodec': f.get('videoCodecId'),
'height': int_or_none(f.get('height')),
'width': int_or_none(f.get('width')),
'url': video_url,
})
self._check_formats(formats, entry_id)
self._sort_formats(formats)
return {
'id': entry_id,
'title': info['name'],
'formats': formats,
'description': info.get('description'),
'description': clean_html(info.get('description')),
'thumbnail': info.get('thumbnailUrl'),
'duration': info.get('duration'),
'timestamp': info.get('createdAt'),

8
youtube_dl/extractor/keezmovies.py
View File

@ -4,10 +4,8 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse_urlparse
from ..utils import sanitized_Request
class KeezMoviesIE(InfoExtractor):
@ -26,7 +24,7 @@ class KeezMoviesIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req = sanitized_Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)

74
youtube_dl/extractor/letv.py
View File

@ -8,14 +8,15 @@
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
compat_ord,
)
from ..utils import (
determine_ext,
ExtractorError,
parse_iso8601,
sanitized_Request,
int_or_none,
encode_data_uri,
)
@ -25,15 +26,16 @@ class LetvIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.letv.com/ptv/vplay/22005890.html',
'md5': 'cab23bd68d5a8db9be31c9a222c1e8df',
'md5': 'edadcfe5406976f42f9f266057ee5e40',
'info_dict': {
'id': '22005890',
'ext': 'mp4',
'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
'timestamp': 1424747397,
'upload_date': '20150224',
'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
}
},
'params': {
'hls_prefer_native': True,
},
}, {
'url': 'http://www.letv.com/ptv/vplay/1415246.html',
'info_dict': {
@ -42,16 +44,22 @@ class LetvIE(InfoExtractor):
'title': '美人天下01',
'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
},
'params': {
'hls_prefer_native': True,
},
}, {
'note': 'This video is available only in Mainland China, thus a proxy is needed',
'url': 'http://www.letv.com/ptv/vplay/1118082.html',
'md5': 'f80936fbe20fb2f58648e81386ff7927',
'md5': '2424c74948a62e5f31988438979c5ad1',
'info_dict': {
'id': '1118082',
'ext': 'mp4',
'title': '与龙共舞 完整版',
'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
},
'params': {
'hls_prefer_native': True,
},
'skip': 'Only available in China',
}]
@ -74,6 +82,27 @@ def calc_time_key(self, param1):
_loc3_ = self.ror(_loc3_, _loc2_ % 17)
return _loc3_
# see M3U8Encryption class in KLetvPlayer.swf
@staticmethod
def decrypt_m3u8(encrypted_data):
if encrypted_data[:5].decode('utf-8').lower() != 'vc_01':
return encrypted_data
encrypted_data = encrypted_data[5:]
_loc4_ = bytearray()
while encrypted_data:
b = compat_ord(encrypted_data[0])
_loc4_.extend([b // 16, b & 0x0f])
encrypted_data = encrypted_data[1:]
idx = len(_loc4_) - 11
_loc4_ = _loc4_[idx:] + _loc4_[:idx]
_loc7_ = bytearray()
while _loc4_:
_loc7_.append(_loc4_[0] * 16 + _loc4_[1])
_loc4_ = _loc4_[2:]
return bytes(_loc7_)
def _real_extract(self, url):
media_id = self._match_id(url)
page = self._download_webpage(url, media_id)
@ -85,7 +114,7 @@ def _real_extract(self, url):
'tkey': self.calc_time_key(int(time.time())),
'domain': 'www.letv.com'
}
play_json_req = compat_urllib_request.Request(
play_json_req = sanitized_Request(
'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
)
cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
@ -115,23 +144,28 @@ def _real_extract(self, url):
for format_id in formats:
if format_id in dispatch:
media_url = playurl['domain'][0] + dispatch[format_id][0]
# Mimic what flvxz.com do
url_parts = list(compat_urlparse.urlparse(media_url))
qs = dict(compat_urlparse.parse_qs(url_parts[4]))
qs.update({
'platid': '14',
'splatid': '1401',
'tss': 'no',
'retry': 1
media_url += '&' + compat_urllib_parse.urlencode({
'm3v': 1,
'format': 1,
'expect': 3,
'rateid': format_id,
})
url_parts[4] = compat_urllib_parse.urlencode(qs)
media_url = compat_urlparse.urlunparse(url_parts)
nodes_data = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id)
req = self._request_webpage(
nodes_data['nodelist'][0]['location'], media_id,
note='Downloading m3u8 information for format %s' % format_id)
m3u8_data = self.decrypt_m3u8(req.read())
url_info_dict = {
'url': media_url,
'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
'ext': determine_ext(dispatch[format_id][1]),
'format_id': format_id,
'protocol': 'm3u8',
}
if format_id[-1:] == 'p':

84
youtube_dl/extractor/lynda.py
View File

@ -7,12 +7,12 @@
from ..compat import (
compat_str,
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
sanitized_Request,
)
@ -25,7 +25,7 @@ def _real_initialize(self):
self._login()
def _login(self):
(username, password) = self._get_login_info()
username, password = self._get_login_info()
if username is None:
return
@ -35,7 +35,7 @@ def _login(self):
'remember': 'false',
'stayPut': 'false'
}
request = compat_urllib_request.Request(
request = sanitized_Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
login_page = self._download_webpage(
request, None, 'Logging in as %s' % username)
@ -64,7 +64,7 @@ def _login(self):
'remember': 'false',
'stayPut': 'false',
}
request = compat_urllib_request.Request(
request = sanitized_Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form).encode('utf-8'))
login_page = self._download_webpage(
request, None,
@ -82,6 +82,15 @@ def _login(self):
expected=True)
raise ExtractorError('Unable to log in')
def _logout(self):
username, _ = self._get_login_info()
if username is None:
return
self._download_webpage(
'http://www.lynda.com/ajax/logout.aspx', None,
'Logging out', 'Unable to log out', fatal=False)
class LyndaIE(LyndaBaseIE):
IE_NAME = 'lynda'
@ -108,50 +117,47 @@ class LyndaIE(LyndaBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(
video = self._download_json(
'http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
video_id, 'Downloading video JSON')
video_json = json.loads(page)
if 'Status' in video_json:
if 'Status' in video:
raise ExtractorError(
'lynda returned error: %s' % video_json['Message'], expected=True)
'lynda returned error: %s' % video['Message'], expected=True)
if video_json['HasAccess'] is False:
if video.get('HasAccess') is False:
self.raise_login_required('Video %s is only available for members' % video_id)
video_id = compat_str(video_json['ID'])
duration = video_json['DurationInSeconds']
title = video_json['Title']
video_id = compat_str(video.get('ID') or video_id)
duration = int_or_none(video.get('DurationInSeconds'))
title = video['Title']
formats = []
fmts = video_json.get('Formats')
fmts = video.get('Formats')
if fmts:
formats.extend([
{
'url': fmt['Url'],
'ext': fmt['Extension'],
'width': fmt['Width'],
'height': fmt['Height'],
'filesize': fmt['FileSize'],
'format_id': str(fmt['Resolution'])
} for fmt in fmts])
formats.extend([{
'url': f['Url'],
'ext': f.get('Extension'),
'width': int_or_none(f.get('Width')),
'height': int_or_none(f.get('Height')),
'filesize': int_or_none(f.get('FileSize')),
'format_id': compat_str(f.get('Resolution')) if f.get('Resolution') else None,
} for f in fmts if f.get('Url')])
prioritized_streams = video_json.get('PrioritizedStreams')
prioritized_streams = video.get('PrioritizedStreams')
if prioritized_streams:
formats.extend([
{
for prioritized_stream_id, prioritized_stream in prioritized_streams.items():
formats.extend([{
'url': video_url,
'width': int_or_none(format_id),
'format_id': format_id,
} for format_id, video_url in prioritized_streams['0'].items()
])
'format_id': '%s-%s' % (prioritized_stream_id, format_id),
} for format_id, video_url in prioritized_stream.items()])
self._check_formats(formats, video_id)
self._sort_formats(formats)
subtitles = self.extract_subtitles(video_id, page)
subtitles = self.extract_subtitles(video_id)
return {
'id': video_id,
@ -182,7 +188,7 @@ def _fix_subtitles(self, subs):
if srt:
return srt
def _get_subtitles(self, video_id, webpage):
def _get_subtitles(self, video_id):
url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
subs = self._download_json(url, None, False)
if subs:
@ -204,12 +210,13 @@ def _real_extract(self, url):
course_path = mobj.group('coursepath')
course_id = mobj.group('courseid')
page = self._download_webpage(
course = self._download_json(
'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
course_id, 'Downloading course JSON')
course_json = json.loads(page)
if 'Status' in course_json and course_json['Status'] == 'NotFound':
self._logout()
if course.get('Status') == 'NotFound':
raise ExtractorError(
'Course %s does not exist' % course_id, expected=True)
@ -219,12 +226,13 @@ def _real_extract(self, url):
# Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
# by single video API anymore
for chapter in course_json['Chapters']:
for video in chapter['Videos']:
if video['HasAccess'] is False:
for chapter in course['Chapters']:
for video in chapter.get('Videos', []):
if video.get('HasAccess') is False:
unaccessible_videos += 1
continue
videos.append(video['ID'])
if video.get('ID'):
videos.append(video['ID'])
if unaccessible_videos > 0:
self._downloader.report_warning(
@ -237,6 +245,6 @@ def _real_extract(self, url):
'Lynda')
for video_id in videos]
course_title = course_json['Title']
course_title = course.get('Title')
return self.playlist_result(entries, course_id, course_title)

187
youtube_dl/extractor/mdr.py
View File

@ -1,64 +1,169 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
determine_ext,
int_or_none,
parse_duration,
parse_iso8601,
xpath_text,
)
class MDRIE(InfoExtractor):
_VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)'
IE_DESC = 'MDR.DE and KiKA'
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
# No tests, MDR regularily deletes its videos
_TEST = {
_TESTS = [{
# MDR regularily deletes its videos
'url': 'http://www.mdr.de/fakt/video189002.html',
'only_matching': True,
}
}, {
# audio
'url': 'http://www.mdr.de/kultur/audio1312272_zc-15948bad_zs-86171fdd.html',
'md5': '64c4ee50f0a791deb9479cd7bbe9d2fa',
'info_dict': {
'id': '1312272',
'ext': 'mp3',
'title': 'Feuilleton vom 30. Oktober 2015',
'duration': 250,
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
},
}, {
'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
'md5': '4930515e36b06c111213e80d1e4aad0e',
'info_dict': {
'id': '19636',
'ext': 'mp4',
'title': 'Baumhaus vom 30. Oktober 2015',
'duration': 134,
'uploader': 'KIKA',
},
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
'info_dict': {
'id': '8182',
'ext': 'mp4',
'title': 'Beutolomäus und der geheime Weihnachtswunsch',
'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
'timestamp': 1419047100,
'upload_date': '20141220',
'duration': 4628,
'uploader': 'KIKA',
},
}, {
'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
'only_matching': True,
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
'only_matching': True,
}]
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('video_id')
domain = m.group('domain')
video_id = self._match_id(url)
# determine title and media streams from webpage
html = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h[12]>(.*?)</h[12]>', html, 'title')
xmlurl = self._search_regex(
r'dataURL:\'(/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, 'XML URL')
data_url = self._search_regex(
r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1',
webpage, 'data url', group='url')
doc = self._download_xml(
compat_urlparse.urljoin(url, data_url), video_id)
title = xpath_text(doc, ['./title', './broadcast/broadcastName'], 'title', fatal=True)
doc = self._download_xml(domain + xmlurl, video_id)
formats = []
for a in doc.findall('./assets/asset'):
url_el = a.find('./progressiveDownloadUrl')
if url_el is None:
continue
abr = int(a.find('bitrateAudio').text) // 1000
media_type = a.find('mediaType').text
format = {
'abr': abr,
'filesize': int(a.find('fileSize').text),
'url': url_el.text,
}
processed_urls = []
for asset in doc.findall('./assets/asset'):
for source in (
'progressiveDownload',
'dynamicHttpStreamingRedirector',
'adaptiveHttpStreamingRedirector'):
url_el = asset.find('./%sUrl' % source)
if url_el is None:
continue
video_url = url_el.text
if video_url in processed_urls:
continue
processed_urls.append(video_url)
vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
ext = determine_ext(url_el.text)
if ext == 'm3u8':
url_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
preference=0, m3u8_id='HLS', fatal=False)
elif ext == 'f4m':
url_formats = self._extract_f4m_formats(
video_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
preference=0, f4m_id='HDS', fatal=False)
else:
media_type = xpath_text(asset, './mediaType', 'media type', default='MP4')
vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
filesize = int_or_none(xpath_text(asset, './fileSize', 'file size'))
f = {
'url': video_url,
'format_id': '%s-%d' % (media_type, vbr or abr),
'filesize': filesize,
'abr': abr,
'preference': 1,
}
if vbr:
width = int_or_none(xpath_text(asset, './frameWidth', 'width'))
height = int_or_none(xpath_text(asset, './frameHeight', 'height'))
f.update({
'vbr': vbr,
'width': width,
'height': height,
})
url_formats = [f]
if not url_formats:
continue
if not vbr:
for f in url_formats:
abr = f.get('tbr') or abr
if 'tbr' in f:
del f['tbr']
f.update({
'abr': abr,
'vcodec': 'none',
})
formats.extend(url_formats)
vbr_el = a.find('bitrateVideo')
if vbr_el is None:
format.update({
'vcodec': 'none',
'format_id': '%s-%d' % (media_type, abr),
})
else:
vbr = int(vbr_el.text) // 1000
format.update({
'vbr': vbr,
'width': int(a.find('frameWidth').text),
'height': int(a.find('frameHeight').text),
'format_id': '%s-%d' % (media_type, vbr),
})
formats.append(format)
self._sort_formats(formats)
description = xpath_text(doc, './broadcast/broadcastDescription', 'description')
timestamp = parse_iso8601(
xpath_text(
doc, [
'./broadcast/broadcastDate',
'./broadcast/broadcastStartDate',
'./broadcast/broadcastEndDate'],
'timestamp', default=None))
duration = parse_duration(xpath_text(doc, './duration', 'duration'))
uploader = xpath_text(doc, './rights', 'uploader')
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'duration': duration,
'uploader': uploader,
'formats': formats,
}

6
youtube_dl/extractor/metacafe.py
View File

@ -7,12 +7,12 @@
compat_parse_qs,
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urllib_request,
)
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
sanitized_Request,
)
@ -117,7 +117,7 @@ def _real_initialize(self):
'filters': '0',
'submit': "Continue - I'm over 18",
}
request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
request = sanitized_Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self.report_age_confirmation()
self._download_webpage(request, None, False, 'Unable to confirm age')
@ -142,7 +142,7 @@ def _real_extract(self, url):
return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
# Retrieve video webpage to extract further information
req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
req = sanitized_Request('http://www.metacafe.com/watch/%s/' % video_id)
# AnyClip videos require the flashversion cookie so that we get the link
# to the mp4 file

8
youtube_dl/extractor/minhateca.py
View File

@ -2,14 +2,12 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse
from ..utils import (
int_or_none,
parse_duration,
parse_filesize,
sanitized_Request,
)
@ -39,7 +37,7 @@ def _real_extract(self, url):
('fileId', video_id),
('__RequestVerificationToken', token),
]
req = compat_urllib_request.Request(
req = sanitized_Request(
'http://minhateca.com.br/action/License/Download',
data=compat_urllib_parse.urlencode(token_data))
req.add_header('Content-Type', 'application/x-www-form-urlencoded')

13
youtube_dl/extractor/miomio.py
View File

@ -8,6 +8,7 @@
xpath_text,
int_or_none,
ExtractorError,
sanitized_Request,
)
@ -51,6 +52,8 @@ def _real_extract(self, url):
mioplayer_path = self._search_regex(
r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
xml_config = self._search_regex(
r'flashvars="type=(?:sina|video)&amp;(.+?)&amp;',
webpage, 'xml config')
@ -60,14 +63,12 @@ def _real_extract(self, url):
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
video_id)
# the following xml contains the actual configuration information on the video file(s)
vid_config = self._download_xml(
vid_config_request = sanitized_Request(
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
video_id)
headers=http_headers)
http_headers = {
'Referer': 'http://www.miomio.tv%s' % mioplayer_path,
}
# the following xml contains the actual configuration information on the video file(s)
vid_config = self._download_xml(vid_config_request, video_id)
if not int_or_none(xpath_text(vid_config, 'timelength')):
raise ExtractorError('Unable to load videos!', expected=True)

2
youtube_dl/extractor/mit.py
View File

@ -86,7 +86,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, page_title)
embed_url = self._search_regex(
r'<iframe .*?src="(.+?)"', webpage, 'embed url')
return self.url_result(embed_url, ie='TechTVMIT')
return self.url_result(embed_url)
class OCWMITIE(InfoExtractor):

10
youtube_dl/extractor/mitele.py
View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
encode_dict,
get_element_by_attribute,
@ -15,7 +18,7 @@ class MiTeleIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
'md5': 'ace7635b2a0b286aaa37d3ff192d2a8a',
'md5': '0ff1a13aebb35d9bc14081ff633dd324',
'info_dict': {
'id': '0NF1jJnxS1Wu3pHrmvFyw2',
'display_id': 'programa-144',
@ -34,6 +37,7 @@ def _real_extract(self, url):
config_url = self._search_regex(
r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
config_url = compat_urlparse.urljoin(url, config_url)
config = self._download_json(
config_url, display_id, 'Downloading config JSON')
@ -56,7 +60,7 @@ def _real_extract(self, url):
'sta': '0',
}
media = self._download_json(
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data)).encode('utf-8')),
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data))),
display_id, 'Downloading %s JSON' % location['loc'])
file_ = media.get('file')
if not file_:

8
youtube_dl/extractor/moevideo.py
View File

@ -5,13 +5,11 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse
from ..utils import (
ExtractorError,
int_or_none,
sanitized_Request,
)
@ -80,7 +78,7 @@ def _real_extract(self, url):
]
r_json = json.dumps(r)
post = compat_urllib_parse.urlencode({'r': r_json})
req = compat_urllib_request.Request(self._API_URL, post)
req = sanitized_Request(self._API_URL, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
response = self._download_json(req, video_id)

4
youtube_dl/extractor/mofosex.py
View File

@ -7,8 +7,8 @@
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlparse,
compat_urllib_request,
)
from ..utils import sanitized_Request
class MofosexIE(InfoExtractor):
@ -29,7 +29,7 @@ def _real_extract(self, url):
video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req = sanitized_Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)

53
youtube_dl/extractor/moniker.py
View File

@ -5,19 +5,17 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_parse
from ..utils import (
ExtractorError,
remove_start,
sanitized_Request,
)
class MonikerIE(InfoExtractor):
IE_DESC = 'allmyvideos.net and vidspot.net'
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)'
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?:(?:2|v)/v-)?(?P<id>[a-zA-Z0-9_-]+)'
_TESTS = [{
'url': 'http://allmyvideos.net/jih3nce3x6wn',
@ -46,6 +44,18 @@ class MonikerIE(InfoExtractor):
}, {
'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
'only_matching': True,
}, {
'url': 'http://vidspot.net/2/v-ywDf99',
'md5': '5f8254ce12df30479428b0152fb8e7ba',
'info_dict': {
'id': 'ywDf99',
'ext': 'mp4',
'title': 'IL FAIT LE MALIN EN PORSHE CAYENNE ( mais pas pour longtemps)',
'description': 'IL FAIT LE MALIN EN PORSHE CAYENNE.',
},
}, {
'url': 'http://allmyvideos.net/v/v-HXZm5t',
'only_matching': True,
}]
def _real_extract(self, url):
@ -64,18 +74,30 @@ def _real_extract(self, url):
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
builtin_url = self._search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+?/builtin-.+?)\1',
orig_webpage, 'builtin URL', default=None, group='url')
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
if builtin_url:
req = sanitized_Request(builtin_url)
req.add_header('Referer', url)
webpage = self._download_webpage(req, video_id, 'Downloading builtin page')
title = self._og_search_title(orig_webpage).strip()
description = self._og_search_description(orig_webpage).strip()
else:
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
title = os.path.splitext(data['fname'])[0]
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = sanitized_Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
title = os.path.splitext(data['fname'])[0]
description = None
# Could be several links with different quality
links = re.findall(r'"file" : "?(.+?)",', webpage)
@ -89,5 +111,6 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
}

8
youtube_dl/extractor/mooshare.py
View File

@ -3,12 +3,10 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
compat_urllib_parse,
)
from ..compat import compat_urllib_parse
from ..utils import (
ExtractorError,
sanitized_Request,
)
@ -59,7 +57,7 @@ def _real_extract(self, url):
'hash': hash_key,
}
request = compat_urllib_request.Request(
request = sanitized_Request(
'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')

80
youtube_dl/extractor/movieclips.py
View File

@ -1,80 +1,40 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import (
ExtractorError,
clean_html,
)
from ..utils import sanitized_Request
class MovieClipsIE(InfoExtractor):
_VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?'
_VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/',
'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597?autoPlay=true&playlistId=5',
'info_dict': {
'id': 'Wy7ZU',
'display_id': 'my-week-with-marilyn-movie-do-you-love-me',
'id': 'pKIGmG83AqD9',
'display_id': 'warcraft-trailer-1-561180739597',
'ext': 'mp4',
'title': 'My Week with Marilyn - Do You Love Me?',
'description': 'md5:e86795bd332fe3cff461e7c8dc542acb',
'title': 'Warcraft Trailer 1',
'description': 'Watch Trailer 1 from Warcraft (2016). Legendary’s WARCRAFT is a 3D epic adventure of world-colliding conflict based.',
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
# rtmp download
'skip_download': True,
}
'add_ie': ['ThePlatform'],
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
show_id = display_id or video_id
display_id = self._match_id(url)
config = self._download_xml(
'http://config.movieclips.com/player/config/%s' % video_id,
show_id, 'Downloading player config')
if config.find('./country-region').text == 'false':
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True)
properties = config.find('./video/properties')
smil_file = properties.attrib['smil_file']
smil = self._download_xml(smil_file, show_id, 'Downloading SMIL')
base_url = smil.find('./head/meta').attrib['base']
formats = []
for video in smil.findall('./body/switch/video'):
vbr = int(video.attrib['system-bitrate']) / 1000
src = video.attrib['src']
formats.append({
'url': base_url,
'play_path': src,
'ext': src.split(':')[0],
'vbr': vbr,
'format_id': '%dk' % vbr,
})
self._sort_formats(formats)
title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title'])
description = clean_html(compat_str(properties.attrib['clip_description']))
thumbnail = properties.attrib['image']
categories = properties.attrib['clip_categories'].split(',')
req = sanitized_Request(url)
# it doesn't work if it thinks the browser it's too old
req.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/43.0 (Chrome)')
webpage = self._download_webpage(req, display_id)
theplatform_link = self._html_search_regex(r'src="(http://player.theplatform.com/p/.*?)"', webpage, 'theplatform link')
title = self._html_search_regex(r'<title[^>]*>([^>]+)-\s*\d+\s*|\s*Movieclips.com</title>', webpage, 'title')
description = self._html_search_meta('description', webpage)
return {
'id': video_id,
'display_id': display_id,
'_type': 'url_transparent',
'url': theplatform_link,
'title': title,
'display_id': display_id,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'formats': formats,
}

4
youtube_dl/extractor/mtv.py
View File

@ -5,7 +5,6 @@
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_str,
)
from ..utils import (
@ -13,6 +12,7 @@
find_xpath_attr,
fix_xml_ampersands,
HEADRequest,
sanitized_Request,
unescapeHTML,
url_basename,
RegexNotFoundError,
@ -53,7 +53,7 @@ def _get_thumbnail_url(self, uri, itemdoc):
def _extract_mobile_video_formats(self, mtvn_id):
webpage_url = self._MOBILE_TEMPLATE % mtvn_id
req = compat_urllib_request.Request(webpage_url)
req = sanitized_Request(webpage_url)
# Otherwise we get a webpage that would execute some javascript
req.add_header('User-Agent', 'curl/7')
webpage = self._download_webpage(req, mtvn_id,

4
youtube_dl/extractor/myvideo.py
View File

@ -11,10 +11,10 @@
compat_ord,
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
sanitized_Request,
)
@ -83,7 +83,7 @@ def _real_extract(self, url):
mobj = re.search(r'data-video-service="/service/data/video/%s/config' % video_id, webpage)
if mobj is not None:
request = compat_urllib_request.Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '')
request = sanitized_Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '')
response = self._download_webpage(request, video_id,
'Downloading video info')
info = json.loads(base64.b64decode(response).decode('utf-8'))

17
youtube_dl/extractor/ndr.py
View File

@ -14,7 +14,8 @@
class NDRBaseIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
display_id = next(group for group in mobj.groups() if group)
webpage = self._download_webpage(url, display_id)
return self._extract_embed(webpage, display_id)
@ -22,7 +23,7 @@ def _real_extract(self, url):
class NDRIE(NDRBaseIE):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
_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',
@ -77,6 +78,9 @@ class NDRIE(NDRBaseIE):
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html',
'only_matching': True,
}]
def _extract_embed(self, webpage, display_id):
@ -101,7 +105,7 @@ def _extract_embed(self, webpage, display_id):
class NJoyIE(NDRBaseIE):
IE_NAME = 'njoy'
IE_DESC = 'N-JOY'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?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',
@ -136,6 +140,9 @@ class NJoyIE(NDRBaseIE):
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.n-joy.de/radio/webradio/morningshow209.html',
'only_matching': True,
}]
def _extract_embed(self, webpage, display_id):
@ -231,7 +238,7 @@ def _real_extract(self, url):
class NDREmbedIE(NDREmbedBaseIE):
IE_NAME = 'ndr:embed'
_VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
_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',
@ -325,7 +332,7 @@ class NDREmbedIE(NDREmbedBaseIE):
class NJoyEmbedIE(NDREmbedBaseIE):
IE_NAME = 'njoy:embed'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
_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',

6
youtube_dl/extractor/neteasemusic.py
View File

@ -8,11 +8,11 @@
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
compat_urllib_parse,
compat_str,
compat_itertools_count,
)
from ..utils import sanitized_Request
class NetEaseMusicBaseIE(InfoExtractor):
@ -40,7 +40,7 @@ def extract_formats(cls, info):
if not details:
continue
formats.append({
'url': 'http://m1.music.126.net/%s/%s.%s' %
'url': 'http://m5.music.126.net/%s/%s.%s' %
(cls._encrypt(details['dfsId']), details['dfsId'],
details['extension']),
'ext': details.get('extension'),
@ -56,7 +56,7 @@ def convert_milliseconds(cls, ms):
return int(round(ms / 1000.0))
def query_api(self, endpoint, video_id, note):
req = compat_urllib_request.Request('%s%s' % (self._API_BASE, endpoint))
req = sanitized_Request('%s%s' % (self._API_BASE, endpoint))
req.add_header('Referer', self._API_BASE)
return self._download_json(req, video_id, note)

11
youtube_dl/extractor/nfb.py
View File

@ -1,10 +1,8 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
compat_urllib_parse,
)
from ..compat import compat_urllib_parse
from ..utils import sanitized_Request
class NFBIE(InfoExtractor):
@ -40,8 +38,9 @@ def _real_extract(self, url):
uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>',
page, 'director name', fatal=False)
request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id,
compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
request = sanitized_Request(
'https://www.nfb.ca/film/%s/player_config' % video_id,
compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf')

6
youtube_dl/extractor/niconico.py
View File

@ -8,7 +8,6 @@
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
)
from ..utils import (
@ -17,6 +16,7 @@
int_or_none,
parse_duration,
parse_iso8601,
sanitized_Request,
xpath_text,
determine_ext,
)
@ -102,7 +102,7 @@ def _login(self):
'password': password,
}
login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('utf-8')
request = compat_urllib_request.Request(
request = sanitized_Request(
'https://secure.nicovideo.jp/secure/login', login_data)
login_results = self._download_webpage(
request, None, note='Logging in', errnote='Unable to log in')
@ -145,7 +145,7 @@ def _real_extract(self, url):
'k': thumb_play_key,
'v': video_id
})
flv_info_request = compat_urllib_request.Request(
flv_info_request = sanitized_Request(
'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
{'Content-Type': 'application/x-www-form-urlencoded'})
flv_info_webpage = self._download_webpage(

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