expected filesize (experimental)
--hls-prefer-native Use the native HLS downloader instead of
ffmpeg (experimental)
+ --hls-use-mpegts Use the mpegts container for HLS videos,
+ allowing to play the video while
+ downloading (some players may not be able
+ to play it)
--external-downloader COMMAND Use the specified external downloader.
Currently supports
aria2c,axel,curl,httpie,wget
- **audiomack**
- **audiomack:album**
- **Azubu**
+ - **AzubuLive**
- **BaiduVideo**: 百度视频
- **bambuser**
- **bambuser:channel**
- **mailru**: Видео@Mail.Ru
- **MakerTV**
- **Malemotion**
+ - **MatchTV**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **metacafe**
- **Sapo**: SAPO Vídeos
- **savefrom.net**
- **SBS**: sbs.com.au
+ - **schooltv**
- **SciVee**
- **screen.yahoo:search**: Yahoo screen search
- **Screencast**
NPOIE,
ComedyCentralIE,
NRKTVIE,
- RaiIE,
+ RaiTVIE,
VikiIE,
ThePlatformIE,
ThePlatformFeedIE,
class TestRaiSubtitles(BaseTestSubtitles):
url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
- IE = RaiIE
+ IE = RaiTVIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
- entries = result['entries']
+ entries = list(result['entries'])
self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
NPOLiveIE,
NPORadioIE,
NPORadioFragmentIE,
+ SchoolTVIE,
VPROIE,
WNLIE
)
if digiteka_url:
return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
+ # Look for Limelight embeds
+ mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
+ if mobj:
+ lm = {
+ 'Media': 'media',
+ 'Channel': 'channel',
+ 'ChannelList': 'channel_list',
+ }
+ return self.url_result('limelight:%s:%s' % (
+ lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
+
# Look for AdobeTVVideo embeds
mobj = re.search(
r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
import re
import time
import base64
+import hashlib
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_ord,
+ compat_str,
)
from ..utils import (
determine_ext,
},
}, {
'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=ec93197892&pu=2c7cd40209&auto_play=1&gpcflag=1&width=640&height=360',
+ 'md5': 'e03d9cc8d9c13191e1caf277e42dbd31',
'info_dict': {
'id': 'p7jnfw5hw9_ec93197892',
'ext': 'mp4',
},
}, {
'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=187060b6fd',
+ 'md5': 'cb988699a776b22d4a41b9d43acfb3ac',
'info_dict': {
'id': 'p7jnfw5hw9_187060b6fd',
'ext': 'mp4',
},
}]
- def _real_extract(self, url):
- uu_mobj = re.search('uu=([\w]+)', url)
- vu_mobj = re.search('vu=([\w]+)', url)
-
- if not uu_mobj or not vu_mobj:
- raise ExtractorError('Invalid URL: %s' % url, expected=True)
-
- uu = uu_mobj.group(1)
- vu = vu_mobj.group(1)
- media_id = uu + '_' + vu
-
- play_json_req = sanitized_Request(
- 'http://api.letvcloud.com/gpc.php?cf=html5&sign=signxxxxx&ver=2.2&format=json&' +
- 'uu=' + uu + '&vu=' + vu)
- play_json = self._download_json(play_json_req, media_id, 'Downloading playJson data')
+ @staticmethod
+ def sign_data(obj):
+ if obj['cf'] == 'flash':
+ salt = '2f9d6924b33a165a6d8b5d3d42f4f987'
+ items = ['cf', 'format', 'ran', 'uu', 'ver', 'vu']
+ elif obj['cf'] == 'html5':
+ salt = 'fbeh5player12c43eccf2bec3300344'
+ items = ['cf', 'ran', 'uu', 'bver', 'vu']
+ input_data = ''.join([item + obj[item] for item in items]) + salt
+ obj['sign'] = hashlib.md5(input_data.encode('utf-8')).hexdigest()
+
+ def _get_formats(self, cf, uu, vu, media_id):
+ def get_play_json(cf, timestamp):
+ data = {
+ 'cf': cf,
+ 'ver': '2.2',
+ 'bver': 'firefox44.0',
+ 'format': 'json',
+ 'uu': uu,
+ 'vu': vu,
+ 'ran': compat_str(timestamp),
+ }
+ self.sign_data(data)
+ return self._download_json(
+ 'http://api.letvcloud.com/gpc.php?' + compat_urllib_parse.urlencode(data),
+ media_id, 'Downloading playJson data for type %s' % cf)
+
+ play_json = get_play_json(cf, time.time())
+ # The server time may be different from local time
+ if play_json.get('code') == 10071:
+ play_json = get_play_json(cf, play_json['timestamp'])
if not play_json.get('data'):
if play_json.get('message'):
'width': int_or_none(play_url.get('vwidth')),
'height': int_or_none(play_url.get('vheight')),
})
+
+ return formats
+
+ def _real_extract(self, url):
+ uu_mobj = re.search('uu=([\w]+)', url)
+ vu_mobj = re.search('vu=([\w]+)', url)
+
+ if not uu_mobj or not vu_mobj:
+ raise ExtractorError('Invalid URL: %s' % url, expected=True)
+
+ uu = uu_mobj.group(1)
+ vu = vu_mobj.group(1)
+ media_id = uu + '_' + vu
+
+ formats = self._get_formats('flash', uu, vu, media_id) + self._get_formats('html5', uu, vu, media_id)
self._sort_formats(formats)
return {
if not stream_url:
continue
if '.f4m' in stream_url:
- formats.extend(self._extract_f4m_formats(stream_url, video_id))
+ formats.extend(self._extract_f4m_formats(
+ stream_url, video_id, fatal=False))
else:
fmt = {
'url': stream_url,
format_id = mobile_url.get('targetMediaPlatform')
if determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
- media_url, video_id, 'mp4', entry_protocol='m3u8_native',
- preference=-1, m3u8_id=format_id))
+ media_url, video_id, 'mp4', 'm3u8_native',
+ m3u8_id=format_id, fatal=False))
else:
formats.append({
'url': media_url,
'md5': '9e7729d3010a9c71506fd1248f74e4f4',
'info_dict': {
'id': '0021200253-okc-bkn-recap',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Thunder vs. Nets',
'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
'duration': 181,
'timestamp': 1354638466,
'upload_date': '20121204',
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
'only_matching': True,
if video_url.startswith('/'):
continue
if video_url.endswith('.m3u8'):
- formats.extend(self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', fatal=False))
+ formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls', fatal=False))
elif video_url.endswith('.f4m'):
formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False))
else:
_TESTS = [
{
'url': 'http://www.nbc.com/the-tonight-show/segments/112966',
- # md5 checksum is not stable
'info_dict': {
- 'id': 'c9xnCo0YPOPH',
- 'ext': 'flv',
+ 'id': '112966',
+ 'ext': 'mp4',
'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
},
{
'url': 'http://www.nbc.com/the-tonight-show/episodes/176',
'info_dict': {
- 'id': 'XwU9KZkp98TH',
+ 'id': '176',
'ext': 'flv',
'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen',
'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.',
},
- 'skip': 'Only works from US',
+ 'skip': '404 Not Found',
},
{
'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
'info_dict': {
- 'id': '8iUuyzWDdYUZ',
- 'ext': 'flv',
+ 'id': '2832821',
+ 'ext': 'mp4',
'title': 'Star Wars Teaser',
'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
'skip': 'Only works from US',
},
{
webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
if theplatform_url.startswith('//'):
theplatform_url = 'http:' + theplatform_url
- return self.url_result(smuggle_url(theplatform_url, {'source_url': url}))
+ return {
+ '_type': 'url_transparent',
+ 'url': smuggle_url(theplatform_url, {'source_url': url}),
+ 'id': video_id,
+ }
class NBCSportsVPlayerIE(InfoExtractor):
if not video_url:
continue
if format_id == 'adaptive':
- formats.extend(self._extract_m3u8_formats(video_url, video_id))
+ formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
else:
formats.append({
'url': video_url,
}
+class SchoolTVIE(InfoExtractor):
+ IE_NAME = 'schooltv'
+ _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
+
+ _TEST = {
+ 'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
+ 'info_dict': {
+ 'id': 'WO_NTR_429477',
+ 'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
+ 'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
+ 'ext': 'mp4',
+ 'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
+ },
+ 'params': {
+ # Skip because of m3u8 download
+ 'skip_download': True
+ }
+ }
+
+ 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-mid=(["\'])(?P<id>.+?)\1', webpage, 'video_id', group='id')
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': 'NPO',
+ 'url': 'npo:%s' % video_id,
+ 'display_id': display_id
+ }
+
+
class VPROIE(NPOIE):
IE_NAME = 'vpro'
_VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P<id>[^/]+)\.html'
_TESTS = [
{
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
- 'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
'info_dict': {
'id': 'MUHH48000314',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': '20 spørsmål',
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
'upload_date': '20140523',
'duration': 1741.52,
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
},
{
'url': 'https://tv.nrk.no/program/mdfp15000514',
- 'md5': '383650ece2b25ecec996ad7b5bb2a384',
'info_dict': {
'id': 'mdfp15000514',
- 'ext': 'flv',
- 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
+ 'ext': 'mp4',
+ 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
'upload_date': '20140524',
- 'duration': 4605.0,
+ 'duration': 4605.08,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
},
},
{
formats = []
for source in sources:
if source['type'] == 'hls':
- formats.extend(self._extract_m3u8_formats(source['file'], video_id))
+ formats.extend(self._extract_m3u8_formats(source['file'], video_id, ext='mp4'))
else:
file_ = source.get('file')
if not file_:
'upload_date': '20130401',
'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar',
'title': 'A Moment With TFS Episode 4',
- }
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}
def _real_extract(self, url):
'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
'info_dict': {
'id': 'judiciary031715',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Integrated Senate Video Player',
'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
- }
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
'info_dict': {
'id': 'commerce011514',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Integrated Senate Video Player'
- }
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
# checksum differs each time
_VALID_URL = 'http://(?:www\.)?tv2\.no/v/(?P<id>\d+)'
_TEST = {
'url': 'http://www.tv2.no/v/916509/',
- 'md5': '9cb9e3410b18b515d71892f27856e9b1',
'info_dict': {
'id': '916509',
- 'ext': 'flv',
- 'title': 'Se Gryttens hyllest av Steven Gerrard',
+ 'ext': 'mp4',
+ 'title': 'Se Frode Gryttens hyllest av Steven Gerrard',
'description': 'TV 2 Sportens huspoet tar avskjed med Liverpools kaptein Steven Gerrard.',
'timestamp': 1431715610,
'upload_date': '20150515',
'duration': 156.967,
'view_count': int,
'categories': list,
- }
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}
def _real_extract(self, url):
{
# streamType: wasLive
'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
- 'md5': '458f4841239dab414343b50e5af8869c',
'info_dict': {
'id': '113063',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'V75 fra Solvalla 30.05.15',
'description': 'md5:b3743425765355855f88e096acc93231',
'thumbnail': 're:^https?://.*\.jpg',
'upload_date': '20150530',
'view_count': int,
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
},
{
'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
'upload_date': '20130627',
'duration': 565,
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
}, {
# video with invalid direct format links (HTTP 403)
'url': 'http://videolectures.net/russir2010_filippova_nlp/',
},
}, {
# Video with only one format
- 'url': 'http://vlog.xuite.net/play/TkRZNjhULTM0NDE2MjkuZmx2',
- 'md5': 'c45737fc8ac5dc8ac2f92ecbcecf505e',
+ 'url': 'http://vlog.xuite.net/play/WUxxR2xCLTI1OTI1MDk5LmZsdg==',
+ 'md5': '21f7b39c009b5a4615b4463df6eb7a46',
'info_dict': {
- 'id': '3441629',
+ 'id': '25925099',
'ext': 'mp4',
- 'title': '孫燕姿 - 眼淚成詩',
+ 'title': 'BigBuckBunny_320x180',
'thumbnail': 're:^https?://.*\.jpg$',
- 'duration': 217.399,
- 'timestamp': 1299383640,
- 'upload_date': '20110306',
- 'uploader': 'Valen',
- 'uploader_id': '10400126',
- 'categories': ['影視娛樂'],
+ 'duration': 596.458,
+ 'timestamp': 1454242500,
+ 'upload_date': '20160131',
+ 'uploader': 'yan12125',
+ 'uploader_id': '12158353',
+ 'categories': ['個人短片'],
+ 'description': 'http://download.blender.org/peach/bigbuckbunny_movies/BigBuckBunny_320x180.mp4',
},
}, {
# Video with two formats
formats.append(f)
self._sort_formats(formats)
- description = self._html_search_regex(
- r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
- webpage, 'description', default=None)
+ description = self._og_search_description(webpage, default=None)
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
uploader = self._html_search_regex(
- r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
+ r'(?s)<div[^>]+class=["\']videoInfoBy(?:\s+[^"\']+)?["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
return
-class YoutubeEntryListBaseInfoExtractor(InfoExtractor):
+class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
# Extract entries from page with "Load more" button
def _entries(self, page, playlist_id):
more_widget_html = content_html = page
class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
def _process_page(self, content):
- for playlist_id in re.findall(r'href="/?playlist\?list=(.+?)"', content):
+ for playlist_id in orderedSet(re.findall(r'href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', content)):
yield self.url_result(
'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
}
-class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtractor):
+class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com playlists'
_VALID_URL = r"""(?x)(?:
(?:https?://)?
self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to convert')
return [], info
self._downloader.to_screen('[ffmpeg] Converting subtitles')
+ sub_filenames = []
for lang, sub in subs.items():
ext = sub['ext']
if ext == new_ext:
'[ffmpeg] Subtitle file for %s is already in the requested'
'format' % new_ext)
continue
+ old_file = subtitles_filename(filename, lang, ext)
+ sub_filenames.append(old_file)
new_file = subtitles_filename(filename, lang, new_ext)
if ext == 'dfxp' or ext == 'ttml':
'You have requested to convert dfxp (TTML) subtitles into another format, '
'which results in style information loss')
- dfxp_file = subtitles_filename(filename, lang, ext)
+ dfxp_file = old_file
srt_file = subtitles_filename(filename, lang, 'srt')
with io.open(dfxp_file, 'rt', encoding='utf-8') as f:
if new_ext == 'srt':
continue
- self.run_ffmpeg(
- subtitles_filename(filename, lang, ext),
- new_file, ['-f', new_format])
+ self.run_ffmpeg(old_file, new_file, ['-f', new_format])
with io.open(new_file, 'rt', encoding='utf-8') as f:
subs[lang] = {
'data': f.read(),
}
- return [], info
+ return sub_filenames, info
from __future__ import unicode_literals
-__version__ = '2016.01.29'
+__version__ = '2016.01.31'
projects / youtube-dl / commitdiff