pytastic code 2
#292
- Author
- Anonymous
- Created
- Nov. 15, 2020, 8 a.m.
- Expires
- Never
- Size
- 958.3 KB
- Hits
- 54
- Syntax
- Python
media_id = video['mediaId']
sources = [compat_str(e['height'])
for e in video['encodings'] if e.get('height')]
formats = self._extract_formats(url, video_id, media_id, sources)
thumbnail = url_or_none(video.get('masterThumb'))
uploader = try_get(video, lambda x: x['user']['username'], compat_str)
uploader_id = str_or_none(try_get(
video, lambda x: x['user']['id'], int))
channel = try_get(video, lambda x: x['channel']['name'], compat_str)
channel_id = str_or_none(try_get(
video, lambda x: x['channel']['id'], int))
like_count = int_or_none(video.get('likes'))
dislike_count = int_or_none(video.get('dislikes'))
view_count = int_or_none(video.get('playsQty'))
duration = int_or_none(video.get('durationInSeconds'))
timestamp = unified_timestamp(video.get('publishedAt'))
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'uploader': uploader or channel,
'uploader_id': uploader_id or channel_id,
'channel': channel,
'channel_id': channel_id,
'timestamp': timestamp,
'like_count': like_count,
'dislike_count': dislike_count,
'view_count': view_count,
'duration': duration,
'age_limit': 18,
}
class PornerBrosIE(FourTubeBaseIE):
_VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?pornerbros\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
_URL_TEMPLATE = 'https://www.pornerbros.com/videos/video_%s'
_TKN_HOST = 'token.pornerbros.com'
_TESTS = [{
'url': 'https://www.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369',
'md5': '6516c8ac63b03de06bc8eac14362db4f',
'info_dict': {
'id': '181369',
'ext': 'mp4',
'title': 'Skinny brunette takes big cock down her anal hole',
'uploader': 'PornerBros HD',
'uploader_id': 'pornerbros-hd',
'upload_date': '20130130',
'timestamp': 1359527401,
'duration': 1224,
'view_count': int,
'categories': list,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.pornerbros.com/embed/181369',
'only_matching': True,
}, {
'url': 'https://m.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369',
'only_matching': True,
}]
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class FOX9IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P<id>\d+)'
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id,
'Anvato', video_id)
class FOX9NewsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P<id>[^/?&#]+)'
_TEST = {
'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota',
'md5': 'd6e1b2572c3bab8a849c9103615dd243',
'info_dict': {
'id': '314473',
'ext': 'mp4',
'title': 'Bear climbs tree in downtown Duluth',
'description': 'md5:6a36bfb5073a411758a752455408ac90',
'duration': 51,
'timestamp': 1478123580,
'upload_date': '20161102',
'uploader': 'EPFOX',
'categories': ['News', 'Sports'],
'tags': ['news', 'video'],
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
anvato_id = self._search_regex(
r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id')
return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9')
from __future__ import unicode_literals
import itertools
from .common import InfoExtractor
from ..utils import (
get_element_by_id,
int_or_none,
remove_end,
)
class FoxgayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
_TEST = {
'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
'md5': '344558ccfea74d33b7adbce22e577f54',
'info_dict': {
'id': '2582',
'ext': 'mp4',
'title': 'Fuck Turkish-style',
'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
'age_limit': 18,
'thumbnail': r're:https?://.*\.jpg$',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' - Foxgay.com')
description = get_element_by_id('inf_tit', webpage)
# The default user-agent with foxgay cookies leads to pages without videos
self._downloader.cookiejar.clear('.foxgay.com')
# Find the URL for the iFrame which contains the actual video.
iframe_url = self._html_search_regex(
r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', webpage,
'video frame', group='url')
iframe = self._download_webpage(
iframe_url, video_id, headers={'User-Agent': 'curl/7.50.1'},
note='Downloading video frame')
video_data = self._parse_json(self._search_regex(
r'video_data\s*=\s*([^;]+);', iframe, 'video data'), video_id)
formats = [{
'url': source,
'height': int_or_none(resolution),
} for source, resolution in zip(
video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'thumbnail': video_data.get('act_vid', {}).get('thumb'),
'age_limit': 18,
}
from __future__ import unicode_literals
import re
from .amp import AMPIE
from .common import InfoExtractor
class FoxNewsIE(AMPIE):
IE_NAME = 'foxnews'
IE_DESC = 'Fox News and Fox Business Video'
_VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [
{
'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
'info_dict': {
'id': '3937480',
'ext': 'flv',
'title': 'Frozen in Time',
'description': '16-year-old girl is size of toddler',
'duration': 265,
'timestamp': 1304411491,
'upload_date': '20110503',
'thumbnail': r're:^https?://.*\.jpg$',
},
},
{
'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
'md5': '5846c64a1ea05ec78175421b8323e2df',
'info_dict': {
'id': '3922535568001',
'ext': 'mp4',
'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
'description': "Congressman discusses president's plan",
'duration': 292,
'timestamp': 1417662047,
'upload_date': '20141204',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
'only_matching': True,
},
{
'url': 'http://video.foxbusiness.com/v/4442309889001',
'only_matching': True,
},
{
# From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
'only_matching': True,
},
]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<(?:amp-)?iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.foxnews\.com/v/video-embed\.html?.*?\bvideo_id=\d+.*?)\1',
webpage)]
def _real_extract(self, url):
host, video_id = re.match(self._VALID_URL, url).groups()
info = self._extract_feed_info(
'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
info['id'] = video_id
return info
class FoxNewsArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:insider\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
IE_NAME = 'foxnews:article'
_TESTS = [{
# data-video-id
'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
'md5': '83d44e1aff1433e7a29a7b537d1700b5',
'info_dict': {
'id': '5116295019001',
'ext': 'mp4',
'title': 'Trump and Clinton asked to defend positions on Iraq War',
'description': 'Veterans react on \'The Kelly File\'',
'timestamp': 1473301045,
'upload_date': '20160908',
},
}, {
# iframe embed
'url': 'http://www.foxnews.com/us/2018/03/09/parkland-survivor-kyle-kashuv-on-meeting-trump-his-app-to-prevent-another-school-shooting.amp.html?__twitter_impression=true',
'info_dict': {
'id': '5748266721001',
'ext': 'flv',
'title': 'Kyle Kashuv has a positive message for the Trump White House',
'description': 'Marjory Stoneman Douglas student disagrees with classmates.',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 229,
'timestamp': 1520594670,
'upload_date': '20180309',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
webpage, 'video ID', group='id', default=None)
if video_id:
return self.url_result(
'http://video.foxnews.com/v/' + video_id, FoxNewsIE.ie_key())
return self.url_result(
FoxNewsIE._extract_urls(webpage)[0], FoxNewsIE.ie_key())
# coding: utf-8
from __future__ import unicode_literals
import json
import uuid
from .adobepass import AdobePassIE
from ..compat import (
compat_HTTPError,
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import (
ExtractorError,
int_or_none,
parse_age_limit,
parse_duration,
try_get,
unified_timestamp,
)
class FOXIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
_TESTS = [{
# clip
'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
'info_dict': {
'id': '4b765a60490325103ea69888fb2bd4e8',
'ext': 'mp4',
'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
'duration': 102,
'timestamp': 1504291893,
'upload_date': '20170901',
'creator': 'FOX',
'series': 'Gotham',
'age_limit': 14,
},
'params': {
'skip_download': True,
},
}, {
# episode, geo-restricted
'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
'only_matching': True,
}, {
# episode, geo-restricted, tv provided required
'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
'only_matching': True,
}]
_GEO_BYPASS = False
_HOME_PAGE_URL = 'https://www.fox.com/'
_API_KEY = 'abdcbed02c124d393b39e818a4312055'
_access_token = None
def _call_api(self, path, video_id, data=None):
headers = {
'X-Api-Key': self._API_KEY,
}
if self._access_token:
headers['Authorization'] = 'Bearer ' + self._access_token
try:
return self._download_json(
'https://api2.fox.com/v2.0/' + path,
video_id, data=data, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
entitlement_issues = self._parse_json(
e.cause.read().decode(), video_id)['entitlementIssues']
for e in entitlement_issues:
if e.get('errorCode') == 1005:
raise ExtractorError(
'This video is only available via cable service provider '
'subscription. You may want to use --cookies.', expected=True)
messages = ', '.join([e['message'] for e in entitlement_issues])
raise ExtractorError(messages, expected=True)
raise
def _real_initialize(self):
if not self._access_token:
mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth')
if mvpd_auth:
self._access_token = (self._parse_json(compat_urllib_parse_unquote(
mvpd_auth.value), None, fatal=False) or {}).get('accessToken')
if not self._access_token:
self._access_token = self._call_api(
'login', None, json.dumps({
'deviceId': compat_str(uuid.uuid4()),
}).encode())['accessToken']
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._call_api('vodplayer/' + video_id, video_id)
title = video['name']
release_url = video['url']
try:
m3u8_url = self._download_json(release_url, video_id)['playURL']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read().decode(), video_id)
if error.get('exception') == 'GeoLocationBlocked':
self.raise_geo_restricted(countries=['US'])
raise ExtractorError(error['description'], expected=True)
raise
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
self._sort_formats(formats)
data = try_get(
video, lambda x: x['trackingData']['properties'], dict) or {}
duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
video.get('duration')) or parse_duration(video.get('duration'))
timestamp = unified_timestamp(video.get('datePublished'))
creator = data.get('brand') or data.get('network') or video.get('network')
series = video.get('seriesName') or data.get(
'seriesName') or data.get('show')
subtitles = {}
for doc_rel in video.get('documentReleases', []):
rel_url = doc_rel.get('url')
if not url or doc_rel.get('format') != 'SCC':
continue
subtitles['en'] = [{
'url': rel_url,
'ext': 'scc',
}]
break
return {
'id': video_id,
'title': title,
'formats': formats,
'description': video.get('description'),
'duration': duration,
'timestamp': timestamp,
'age_limit': parse_age_limit(video.get('contentRating')),
'creator': creator,
'series': series,
'season_number': int_or_none(video.get('seasonNumber')),
'episode': video.get('name'),
'episode_number': int_or_none(video.get('episodeNumber')),
'release_year': int_or_none(video.get('releaseYear')),
'subtitles': subtitles,
}
from __future__ import unicode_literals
from .common import InfoExtractor
class FoxSportsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*video/(?P<id>\d+)'
_TEST = {
'url': 'http://www.foxsports.com/tennessee/video/432609859715',
'md5': 'b49050e955bebe32c301972e4012ac17',
'info_dict': {
'id': '432609859715',
'ext': 'mp4',
'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
'description': 'Courtney Lee talks about Memphis being focused.',
# TODO: fix timestamp
'upload_date': '19700101', # '20150423',
# 'timestamp': 1429761109,
'uploader': 'NEWA-FNG-FOXSPORTS',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'https://feed.theplatform.com/f/BKQ29B/foxsports-all?byId=' + video_id, 'ThePlatformFeed')
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
extract_attributes,
int_or_none,
)
class FranceCultureIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
'info_dict': {
'id': 'rendez-vous-au-pays-des-geeks',
'display_id': 'rendez-vous-au-pays-des-geeks',
'ext': 'mp3',
'title': 'Rendez-vous au pays des geeks',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140301',
'timestamp': 1393642916,
'vcodec': 'none',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_data = extract_attributes(self._search_regex(
r'''(?sx)
(?:
</h1>|
<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
).*?
(<button[^>]+data-asset-source="[^"]+"[^>]+>)
''',
webpage, 'video data'))
video_url = video_data['data-asset-source']
title = video_data.get('data-asset-title') or self._og_search_title(webpage)
description = self._html_search_regex(
r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
webpage, 'description', default=None)
thumbnail = self._search_regex(
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
uploader = self._html_search_regex(
r'(?s)<span class="author">(.*?)</span>',
webpage, 'uploader', default=None)
ext = determine_ext(video_url.lower())
return {
'id': display_id,
'display_id': display_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'ext': ext,
'vcodec': 'none' if ext == 'mp3' else None,
'uploader': uploader,
'timestamp': int_or_none(video_data.get('data-asset-created-date')),
'duration': int_or_none(video_data.get('data-duration')),
}
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import month_by_name
class FranceInterIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
_TEST = {
'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016',
'md5': '9e54d7bdb6fdc02a841007f8a975c094',
'info_dict': {
'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016',
'ext': 'mp3',
'title': 'Affaire Cahuzac : le contentieux du compte en Suisse',
'description': 'md5:401969c5d318c061f86bda1fa359292b',
'upload_date': '20160907',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video url', group='url')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
upload_date_str = self._search_regex(
r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
webpage, 'upload date', fatal=False)
if upload_date_str:
upload_date_list = upload_date_str.split()
upload_date_list.reverse()
upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0)
upload_date_list[2] = '%02d' % int(upload_date_list[2])
upload_date = ''.join(upload_date_list)
else:
upload_date = None
return {
'id': video_id,
'title': title,
'description': description,
'upload_date': upload_date,
'formats': [{
'url': video_url,
'vcodec': 'none',
}],
}
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
clean_html,
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
try_get,
url_or_none,
)
from .dailymotion import DailymotionIE
class FranceTVBaseInfoExtractor(InfoExtractor):
def _make_url_result(self, video_or_full_id, catalog=None):
full_id = 'francetv:%s' % video_or_full_id
if '@' not in video_or_full_id and catalog:
full_id += '@%s' % catalog
return self.url_result(
full_id, ie=FranceTVIE.ie_key(),
video_id=video_or_full_id.split('@')[0])
class FranceTVIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
https?://
sivideo\.webservices\.francetelevisions\.fr/tools/getInfosOeuvre/v2/\?
.*?\bidDiffusion=[^&]+|
(?:
https?://videos\.francetv\.fr/video/|
francetv:
)
(?P<id>[^@]+)(?:@(?P<catalog>.+))?
)
'''
_TESTS = [{
# without catalog
'url': 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=162311093&callback=_jsonp_loader_callback_request_0',
'md5': 'c2248a8de38c4e65ea8fae7b5df2d84f',
'info_dict': {
'id': '162311093',
'ext': 'mp4',
'title': '13h15, le dimanche... - Les mystères de Jésus',
'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
'timestamp': 1502623500,
'upload_date': '20170813',
},
}, {
# with catalog
'url': 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=NI_1004933&catalogue=Zouzous&callback=_jsonp_loader_callback_request_4',
'only_matching': True,
}, {
'url': 'http://videos.francetv.fr/video/NI_657393@Regions',
'only_matching': True,
}, {
'url': 'francetv:162311093',
'only_matching': True,
}, {
'url': 'francetv:NI_1004933@Zouzous',
'only_matching': True,
}, {
'url': 'francetv:NI_983319@Info-web',
'only_matching': True,
}, {
'url': 'francetv:NI_983319',
'only_matching': True,
}, {
'url': 'francetv:NI_657393@Regions',
'only_matching': True,
}, {
# france-3 live
'url': 'francetv:SIM_France3',
'only_matching': True,
}]
def _extract_video(self, video_id, catalogue=None):
# Videos are identified by idDiffusion so catalogue part is optional.
# However when provided, some extra formats may be returned so we pass
# it if available.
info = self._download_json(
'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/',
video_id, 'Downloading video JSON', query={
'idDiffusion': video_id,
'catalogue': catalogue or '',
})
if info.get('status') == 'NOK':
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, info['message']),
expected=True)
allowed_countries = info['videos'][0].get('geoblocage')
if allowed_countries:
georestricted = True
geo_info = self._download_json(
'http://geo.francetv.fr/ws/edgescape.json', video_id,
'Downloading geo restriction info')
country = geo_info['reponse']['geo_info']['country_code']
if country not in allowed_countries:
raise ExtractorError(
'The video is not available from your location',
expected=True)
else:
georestricted = False
def sign(manifest_url, manifest_id):
for host in ('hdfauthftv-a.akamaihd.net', 'hdfauth.francetv.fr'):
signed_url = url_or_none(self._download_webpage(
'https://%s/esi/TA' % host, video_id,
'Downloading signed %s manifest URL' % manifest_id,
fatal=False, query={
'url': manifest_url,
}))
if signed_url:
return signed_url
return manifest_url
is_live = None
formats = []
for video in info['videos']:
if video['statut'] != 'ONLINE':
continue
video_url = video['url']
if not video_url:
continue
if is_live is None:
is_live = (try_get(
video, lambda x: x['plages_ouverture'][0]['direct'],
bool) is True) or '/live.francetv.fr/' in video_url
format_id = video['format']
ext = determine_ext(video_url)
if ext == 'f4m':
if georestricted:
# See https://github.com/ytdl-org/youtube-dl/issues/3963
# m3u8 urls work fine
continue
formats.extend(self._extract_f4m_formats(
sign(video_url, format_id) + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
video_id, f4m_id=format_id, fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
sign(video_url, format_id), video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id=format_id,
fatal=False))
elif video_url.startswith('rtmp'):
formats.append({
'url': video_url,
'format_id': 'rtmp-%s' % format_id,
'ext': 'flv',
})
else:
if self._is_valid_url(video_url, video_id, format_id):
formats.append({
'url': video_url,
'format_id': format_id,
})
self._sort_formats(formats)
title = info['titre']
subtitle = info.get('sous_titre')
if subtitle:
title += ' - %s' % subtitle
title = title.strip()
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': self._live_title(title) if is_live else title,
'description': clean_html(info['synopsis']),
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
'timestamp': int_or_none(info['diffusion']['timestamp']),
'is_live': is_live,
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
catalog = mobj.group('catalog')
if not video_id:
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
video_id = qs.get('idDiffusion', [None])[0]
catalog = qs.get('catalogue', [None])[0]
if not video_id:
raise ExtractorError('Invalid URL', expected=True)
return self._extract_video(video_id, catalog)
class FranceTVSiteIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
_TESTS = [{
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
'info_dict': {
'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1',
'ext': 'mp4',
'title': '13h15, le dimanche... - Les mystères de Jésus',
'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
'timestamp': 1502623500,
'upload_date': '20170813',
},
'params': {
'skip_download': True,
},
'add_ie': [FranceTVIE.ie_key()],
}, {
# france3
'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
'only_matching': True,
}, {
# france4
'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
'only_matching': True,
}, {
# france5
'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
'only_matching': True,
}, {
# franceo
'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
'only_matching': True,
}, {
# france2 live
'url': 'https://www.france.tv/france-2/direct.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
'only_matching': True,
}, {
'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/142749-rouge-sang.html',
'only_matching': True,
}, {
# france-3 live
'url': 'https://www.france.tv/france-3/direct.html',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
catalogue = None
video_id = self._search_regex(
r'(?:data-main-video\s*=|videoId["\']?\s*[:=])\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'video id', default=None, group='id')
if not video_id:
video_id, catalogue = self._html_search_regex(
r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
webpage, 'video ID').split('@')
return self._make_url_result(video_id, catalogue)
class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://embed\.francetv\.fr/*\?.*?\bue=(?P<id>[^&]+)'
_TESTS = [{
'url': 'http://embed.francetv.fr/?ue=7fd581a2ccf59d2fc5719c5c13cf6961',
'info_dict': {
'id': 'NI_983319',
'ext': 'mp4',
'title': 'Le Pen Reims',
'upload_date': '20170505',
'timestamp': 1493981780,
'duration': 16,
},
'params': {
'skip_download': True,
},
'add_ie': [FranceTVIE.ie_key()],
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://api-embed.webservices.francetelevisions.fr/key/%s' % video_id,
video_id)
return self._make_url_result(video['video_id'], video.get('catalog'))
class FranceTVInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetvinfo.fr'
_VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&.]+)'
_TESTS = [{
'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
'info_dict': {
'id': '84981923',
'ext': 'mp4',
'title': 'Soir 3',
'upload_date': '20130826',
'timestamp': 1377548400,
'subtitles': {
'fr': 'mincount:2',
},
},
'params': {
'skip_download': True,
},
'add_ie': [FranceTVIE.ie_key()],
}, {
'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
'only_matching': True,
}, {
'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
'only_matching': True,
}, {
'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
'only_matching': True,
}, {
# Dailymotion embed
'url': 'http://www.francetvinfo.fr/politique/notre-dame-des-landes/video-sur-france-inter-cecile-duflot-denonce-le-regard-meprisant-de-patrick-cohen_1520091.html',
'md5': 'ee7f1828f25a648addc90cb2687b1f12',
'info_dict': {
'id': 'x4iiko0',
'ext': 'mp4',
'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen',
'description': 'Au lendemain de la victoire du "oui" au référendum sur l\'aéroport de Notre-Dame-des-Landes, l\'ancienne ministre écologiste est l\'invitée de Patrick Cohen. Plus d\'info : https://www.franceinter.fr/emissions/le-7-9/le-7-9-27-juin-2016',
'timestamp': 1467011958,
'upload_date': '20160627',
'uploader': 'France Inter',
'uploader_id': 'x2q2ez',
},
'add_ie': ['Dailymotion'],
}, {
'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
dailymotion_urls = DailymotionIE._extract_urls(webpage)
if dailymotion_urls:
return self.playlist_result([
self.url_result(dailymotion_url, DailymotionIE.ie_key())
for dailymotion_url in dailymotion_urls])
video_id = self._search_regex(
(r'player\.load[^;]+src:\s*["\']([^"\']+)',
r'id-video=([^@]+@[^"]+)',
r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
webpage, 'video id')
return self._make_url_result(video_id)
class FranceTVInfoSportIE(FranceTVBaseInfoExtractor):
IE_NAME = 'sport.francetvinfo.fr'
_VALID_URL = r'https?://sport\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://sport.francetvinfo.fr/les-jeux-olympiques/retour-sur-les-meilleurs-moments-de-pyeongchang-2018',
'info_dict': {
'id': '6e49080e-3f45-11e8-b459-000d3a2439ea',
'ext': 'mp4',
'title': 'Retour sur les meilleurs moments de Pyeongchang 2018',
'timestamp': 1523639962,
'upload_date': '20180413',
},
'params': {
'skip_download': True,
},
'add_ie': [FranceTVIE.ie_key()],
}]
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="([^"]+)"', webpage, 'video_id')
return self._make_url_result(video_id, 'Sport-web')
class GenerationWhatIE(InfoExtractor):
IE_NAME = 'france2.fr:generation-what'
_VALID_URL = r'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://generation-what.francetv.fr/portrait/video/present-arms',
'info_dict': {
'id': 'wtvKYUG45iw',
'ext': 'mp4',
'title': 'Generation What - Garde à vous - FRA',
'uploader': 'Generation What',
'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w',
'upload_date': '20160411',
},
'params': {
'skip_download': True,
},
'add_ie': ['Youtube'],
}, {
'url': 'http://generation-what.francetv.fr/europe/video/present-arms',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
youtube_id = self._search_regex(
r"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';",
webpage, 'youtube id')
return self.url_result(youtube_id, ie='Youtube', video_id=youtube_id)
class CultureboxIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://culturebox.francetvinfo.fr/opera-classique/musique-classique/c-est-baroque/concerts/cantates-bwv-4-106-et-131-de-bach-par-raphael-pichon-57-268689',
'info_dict': {
'id': 'EV_134885',
'ext': 'mp4',
'title': 'Cantates BWV 4, 106 et 131 de Bach par Raphaël Pichon 5/7',
'description': 'md5:19c44af004b88219f4daa50fa9a351d4',
'upload_date': '20180206',
'timestamp': 1517945220,
'duration': 5981,
},
'params': {
'skip_download': True,
},
'add_ie': [FranceTVIE.ie_key()],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
if ">Ce live n'est plus disponible en replay<" in webpage:
raise ExtractorError(
'Video %s is not available' % display_id, expected=True)
video_id, catalogue = self._search_regex(
r'["\'>]https?://videos\.francetv\.fr/video/([^@]+@.+?)["\'<]',
webpage, 'video id').split('@')
return self._make_url_result(video_id, catalogue)
class FranceTVJeunesseIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'(?P<url>https?://(?:www\.)?(?:zouzous|ludo)\.fr/heros/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'https://www.zouzous.fr/heros/simon',
'info_dict': {
'id': 'simon',
},
'playlist_count': 9,
}, {
'url': 'https://www.ludo.fr/heros/ninjago',
'info_dict': {
'id': 'ninjago',
},
'playlist_count': 10,
}, {
'url': 'https://www.zouzous.fr/heros/simon?abc',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
playlist = self._download_json(
'%s/%s' % (mobj.group('url'), 'playlist'), playlist_id)
if not playlist.get('count'):
raise ExtractorError(
'%s is not available' % playlist_id, expected=True)
entries = []
for item in playlist['items']:
identity = item.get('identity')
if identity and isinstance(identity, compat_str):
entries.append(self._make_url_result(identity))
return self.playlist_result(entries, playlist_id)
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
get_element_by_class,
get_element_by_id,
unified_strdate,
)
class FreesoundIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?freesound\.org/people/[^/]+/sounds/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
'md5': '12280ceb42c81f19a515c745eae07650',
'info_dict': {
'id': '194503',
'ext': 'mp3',
'title': 'gulls in the city.wav',
'description': 'the sounds of seagulls in the city',
'duration': 130.233,
'uploader': 'miklovan',
'upload_date': '20130715',
'tags': list,
}
}
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
audio_url = self._og_search_property('audio', webpage, 'song url')
title = self._og_search_property('audio:title', webpage, 'song title')
description = self._html_search_regex(
r'(?s)id=["\']sound_description["\'][^>]*>(.+?)</div>',
webpage, 'description', fatal=False)
duration = float_or_none(
get_element_by_class('duration', webpage), scale=1000)
upload_date = unified_strdate(get_element_by_id('sound_date', webpage))
uploader = self._og_search_property(
'audio:artist', webpage, 'uploader', fatal=False)
channels = self._html_search_regex(
r'Channels</dt><dd>(.+?)</dd>', webpage,
'channels info', fatal=False)
tags_str = get_element_by_class('tags', webpage)
tags = re.findall(r'<a[^>]+>([^<]+)', tags_str) if tags_str else None
audio_urls = [audio_url]
LQ_FORMAT = '-lq.mp3'
if LQ_FORMAT in audio_url:
audio_urls.append(audio_url.replace(LQ_FORMAT, '-hq.mp3'))
formats = [{
'url': format_url,
'format_note': channels,
'quality': quality,
} for quality, format_url in enumerate(audio_urls)]
self._sort_formats(formats)
return {
'id': audio_id,
'title': title,
'description': description,
'duration': duration,
'uploader': uploader,
'upload_date': upload_date,
'tags': tags,
'formats': formats,
}
from __future__ import unicode_literals
from .common import InfoExtractor
from .youtube import YoutubeIE
class FreespeechIE(InfoExtractor):
IE_NAME = 'freespeech.org'
_VALID_URL = r'https?://(?:www\.)?freespeech\.org/stories/(?P<id>.+)'
_TEST = {
'add_ie': ['Youtube'],
'url': 'http://www.freespeech.org/stories/fcc-announces-net-neutrality-rollback-whats-stake/',
'info_dict': {
'id': 'waRk6IPqyWM',
'ext': 'mp4',
'title': 'What\'s At Stake - Net Neutrality Special',
'description': 'Presented by MNN and FSTV',
'upload_date': '20170728',
'uploader_id': 'freespeechtv',
'uploader': 'freespeechtv',
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
youtube_url = self._search_regex(
r'data-video-url="([^"]+)"',
webpage, 'youtube url')
return self.url_result(youtube_url, YoutubeIE.ie_key())
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
try_get,
unified_timestamp,
)
class FreshLiveIE(InfoExtractor):
_VALID_URL = r'https?://freshlive\.tv/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'https://freshlive.tv/satotv/74712',
'md5': '9f0cf5516979c4454ce982df3d97f352',
'info_dict': {
'id': '74712',
'ext': 'mp4',
'title': 'テスト',
'description': 'テスト',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1511,
'timestamp': 1483619655,
'upload_date': '20170105',
'uploader': 'サトTV',
'uploader_id': 'satotv',
'view_count': int,
'comment_count': int,
'is_live': False,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
options = self._parse_json(
self._search_regex(
r'window\.__CONTEXT__\s*=\s*({.+?});\s*</script>',
webpage, 'initial context'),
video_id)
info = options['context']['dispatcher']['stores']['ProgramStore']['programs'][video_id]
title = info['title']
if info.get('status') == 'upcoming':
raise ExtractorError('Stream %s is upcoming' % video_id, expected=True)
stream_url = info.get('liveStreamUrl') or info['archiveStreamUrl']
is_live = info.get('liveStreamUrl') is not None
formats = self._extract_m3u8_formats(
stream_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls')
if is_live:
title = self._live_title(title)
return {
'id': video_id,
'formats': formats,
'title': title,
'description': info.get('description'),
'thumbnail': info.get('thumbnailUrl'),
'duration': int_or_none(info.get('airTime')),
'timestamp': unified_timestamp(info.get('createdAt')),
'uploader': try_get(
info, lambda x: x['channel']['title'], compat_str),
'uploader_id': try_get(
info, lambda x: x['channel']['code'], compat_str),
'uploader_url': try_get(
info, lambda x: x['channel']['permalink'], compat_str),
'view_count': int_or_none(info.get('viewCount')),
'comment_count': int_or_none(info.get('commentCount')),
'tags': info.get('tags', []),
'is_live': is_live,
}
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
ExtractorError,
parse_duration,
url_or_none,
urlencode_postdata,
)
class FrontendMastersBaseIE(InfoExtractor):
_API_BASE = 'https://api.frontendmasters.com/v1/kabuki'
_LOGIN_URL = 'https://frontendmasters.com/login/'
_NETRC_MACHINE = 'frontendmasters'
_QUALITIES = {
'low': {'width': 480, 'height': 360},
'mid': {'width': 1280, 'height': 720},
'high': {'width': 1920, 'height': 1080}
}
def _real_initialize(self):
self._login()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password
})
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post_url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
response = self._download_webpage(
post_url, None, 'Logging in', data=urlencode_postdata(login_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
# Successful login
if any(p in response for p in (
'wp-login.php?action=logout', '>Logout')):
return
error = self._html_search_regex(
r'class=(["\'])(?:(?!\1).)*\bMessageAlert\b(?:(?!\1).)*\1[^>]*>(?P<error>[^<]+)<',
response, 'error message', default=None, group='error')
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
class FrontendMastersPageBaseIE(FrontendMastersBaseIE):
def _download_course(self, course_name, url):
return self._download_json(
'%s/courses/%s' % (self._API_BASE, course_name), course_name,
'Downloading course JSON', headers={'Referer': url})
@staticmethod
def _extract_chapters(course):
chapters = []
lesson_elements = course.get('lessonElements')
if isinstance(lesson_elements, list):
chapters = [url_or_none(e) for e in lesson_elements if url_or_none(e)]
return chapters
@staticmethod
def _extract_lesson(chapters, lesson_id, lesson):
title = lesson.get('title') or lesson_id
display_id = lesson.get('slug')
description = lesson.get('description')
thumbnail = lesson.get('thumbnail')
chapter_number = None
index = lesson.get('index')
element_index = lesson.get('elementIndex')
if (isinstance(index, int) and isinstance(element_index, int)
and index < element_index):
chapter_number = element_index - index
chapter = (chapters[chapter_number - 1]
if chapter_number - 1 < len(chapters) else None)
duration = None
timestamp = lesson.get('timestamp')
if isinstance(timestamp, compat_str):
mobj = re.search(
r'(?P<start>\d{1,2}:\d{1,2}:\d{1,2})\s*-(?P<end>\s*\d{1,2}:\d{1,2}:\d{1,2})',
timestamp)
if mobj:
duration = parse_duration(mobj.group('end')) - parse_duration(
mobj.group('start'))
return {
'_type': 'url_transparent',
'url': 'frontendmasters:%s' % lesson_id,
'ie_key': FrontendMastersIE.ie_key(),
'id': lesson_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'chapter': chapter,
'chapter_number': chapter_number,
}
class FrontendMastersIE(FrontendMastersBaseIE):
_VALID_URL = r'(?:frontendmasters:|https?://api\.frontendmasters\.com/v\d+/kabuki/video/)(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://api.frontendmasters.com/v1/kabuki/video/a2qogef6ba',
'md5': '7f161159710d6b7016a4f4af6fcb05e2',
'info_dict': {
'id': 'a2qogef6ba',
'ext': 'mp4',
'title': 'a2qogef6ba',
},
'skip': 'Requires FrontendMasters account credentials',
}, {
'url': 'frontendmasters:a2qogef6ba',
'only_matching': True,
}]
def _real_extract(self, url):
lesson_id = self._match_id(url)
source_url = '%s/video/%s/source' % (self._API_BASE, lesson_id)
formats = []
for ext in ('webm', 'mp4'):
for quality in ('low', 'mid', 'high'):
resolution = self._QUALITIES[quality].copy()
format_id = '%s-%s' % (ext, quality)
format_url = self._download_json(
source_url, lesson_id,
'Downloading %s source JSON' % format_id, query={
'f': ext,
'r': resolution['height'],
}, headers={
'Referer': url,
}, fatal=False)['url']
if not format_url:
continue
f = resolution.copy()
f.update({
'url': format_url,
'ext': ext,
'format_id': format_id,
})
formats.append(f)
self._sort_formats(formats)
subtitles = {
'en': [{
'url': '%s/transcripts/%s.vtt' % (self._API_BASE, lesson_id),
}]
}
return {
'id': lesson_id,
'title': lesson_id,
'formats': formats,
'subtitles': subtitles
}
class FrontendMastersLessonIE(FrontendMastersPageBaseIE):
_VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<course_name>[^/]+)/(?P<lesson_name>[^/]+)'
_TEST = {
'url': 'https://frontendmasters.com/courses/web-development/tools',
'info_dict': {
'id': 'a2qogef6ba',
'display_id': 'tools',
'ext': 'mp4',
'title': 'Tools',
'description': 'md5:82c1ea6472e88ed5acd1829fe992e4f7',
'thumbnail': r're:^https?://.*\.jpg$',
'chapter': 'Introduction',
'chapter_number': 1,
},
'params': {
'skip_download': True,
},
'skip': 'Requires FrontendMasters account credentials',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
course_name, lesson_name = mobj.group('course_name', 'lesson_name')
course = self._download_course(course_name, url)
lesson_id, lesson = next(
(video_id, data)
for video_id, data in course['lessonData'].items()
if data.get('slug') == lesson_name)
chapters = self._extract_chapters(course)
return self._extract_lesson(chapters, lesson_id, lesson)
class FrontendMastersCourseIE(FrontendMastersPageBaseIE):
_VALID_URL = r'https?://(?:www\.)?frontendmasters\.com/courses/(?P<id>[^/]+)'
_TEST = {
'url': 'https://frontendmasters.com/courses/web-development/',
'info_dict': {
'id': 'web-development',
'title': 'Introduction to Web Development',
'description': 'md5:9317e6e842098bf725d62360e52d49a6',
},
'playlist_count': 81,
'skip': 'Requires FrontendMasters account credentials',
}
@classmethod
def suitable(cls, url):
return False if FrontendMastersLessonIE.suitable(url) else super(
FrontendMastersBaseIE, cls).suitable(url)
def _real_extract(self, url):
course_name = self._match_id(url)
course = self._download_course(course_name, url)
chapters = self._extract_chapters(course)
lessons = sorted(
course['lessonData'].values(), key=lambda data: data['index'])
entries = []
for lesson in lessons:
lesson_name = lesson.get('slug')
if not lesson_name:
continue
lesson_id = lesson.get('hash') or lesson.get('statsId')
entries.append(self._extract_lesson(chapters, lesson_id, lesson))
title = course.get('title')
description = course.get('description')
return self.playlist_result(entries, course_name, title, description)
# coding: utf-8
from __future__ import unicode_literals
import random
import string
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
int_or_none,
js_to_json,
ExtractorError,
urlencode_postdata
)
class FunimationIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
_NETRC_MACHINE = 'funimation'
_TOKEN = None
_TESTS = [{
'url': 'https://www.funimation.com/shows/hacksign/role-play/',
'info_dict': {
'id': '91144',
'display_id': 'role-play',
'ext': 'mp4',
'title': '.hack//SIGN - Role Play',
'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
'thumbnail': r're:https?://.*\.jpg',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
'info_dict': {
'id': '210051',
'display_id': 'broadcast-dub-preview',
'ext': 'mp4',
'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
'only_matching': True,
}]
def _login(self):
username, password = self._get_login_info()
if username is None:
return
try:
data = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
None, 'Logging in', data=urlencode_postdata({
'username': username,
'password': password,
}))
self._TOKEN = data['token']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
error = self._parse_json(e.cause.read().decode(), None)['error']
raise ExtractorError(error, expected=True)
raise
def _real_initialize(self):
self._login()
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
def _search_kane(name):
return self._search_regex(
r"KANE_customdimensions\.%s\s*=\s*'([^']+)';" % name,
webpage, name, default=None)
title_data = self._parse_json(self._search_regex(
r'TITLE_DATA\s*=\s*({[^}]+})',
webpage, 'title data', default=''),
display_id, js_to_json, fatal=False) or {}
video_id = title_data.get('id') or self._search_regex([
r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
r'<iframe[^>]+src="/player/(\d+)',
], webpage, 'video_id', default=None)
if not video_id:
player_url = self._html_search_meta([
'al:web:url',
'og:video:url',
'og:video:secure_url',
], webpage, fatal=True)
video_id = self._search_regex(r'/player/(\d+)', player_url, 'video id')
title = episode = title_data.get('title') or _search_kane('videoTitle') or self._og_search_title(webpage)
series = _search_kane('showName')
if series:
title = '%s - %s' % (series, title)
description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
try:
headers = {}
if self._TOKEN:
headers['Authorization'] = 'Token %s' % self._TOKEN
sources = self._download_json(
'https://www.funimation.com/api/showexperience/%s/' % video_id,
video_id, headers=headers, query={
'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]),
})['items']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read(), video_id)['errors'][0]
raise ExtractorError('%s said: %s' % (
self.IE_NAME, error.get('detail') or error.get('title')), expected=True)
raise
formats = []
for source in sources:
source_url = source.get('src')
if not source_url:
continue
source_type = source.get('videoType') or determine_ext(source_url)
if source_type == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4',
m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': source_type,
'url': source_url,
})
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': self._og_search_thumbnail(webpage),
'series': series,
'season_number': int_or_none(title_data.get('seasonNum') or _search_kane('season')),
'episode_number': int_or_none(title_data.get('episodeNum')),
'episode': episode,
'season_id': title_data.get('seriesId'),
'formats': formats,
}
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .nexx import NexxIE
from ..utils import (
int_or_none,
str_or_none,
)
class FunkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funk\.net/(?:channel|playlist)/[^/]+/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.funk.net/channel/ba-793/die-lustigsten-instrumente-aus-dem-internet-teil-2-1155821',
'md5': '8dd9d9ab59b4aa4173b3197f2ea48e81',
'info_dict': {
'id': '1155821',
'ext': 'mp4',
'title': 'Die LUSTIGSTEN INSTRUMENTE aus dem Internet - Teil 2',
'description': 'md5:a691d0413ef4835588c5b03ded670c1f',
'timestamp': 1514507395,
'upload_date': '20171229',
},
}, {
'url': 'https://www.funk.net/playlist/neuesteVideos/kameras-auf-dem-fusion-festival-1618699',
'only_matching': True,
}]
def _real_extract(self, url):
display_id, nexx_id = re.match(self._VALID_URL, url).groups()
video = self._download_json(
'https://www.funk.net/api/v4.0/videos/' + nexx_id, nexx_id)
return {
'_type': 'url_transparent',
'url': 'nexx:741:' + nexx_id,
'ie_key': NexxIE.ie_key(),
'id': nexx_id,
'title': video.get('title'),
'description': video.get('description'),
'duration': int_or_none(video.get('duration')),
'channel_id': str_or_none(video.get('channelId')),
'display_id': display_id,
'tags': video.get('tags'),
'thumbnail': video.get('imageUrlLandscape'),
}
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
mimetype2ext,
parse_iso8601,
)
class FusionIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fusion\.(?:net|tv)/(?:video/|show/.+?\bvideo=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://fusion.tv/video/201781/u-s-and-panamanian-forces-work-together-to-stop-a-vessel-smuggling-drugs/',
'info_dict': {
'id': '3145868',
'ext': 'mp4',
'title': 'U.S. and Panamanian forces work together to stop a vessel smuggling drugs',
'description': 'md5:0cc84a9943c064c0f46b128b41b1b0d7',
'duration': 140.0,
'timestamp': 1442589635,
'uploader': 'UNIVISON',
'upload_date': '20150918',
},
'params': {
'skip_download': True,
},
'add_ie': ['Anvato'],
}, {
'url': 'http://fusion.tv/video/201781',
'only_matching': True,
}, {
'url': 'https://fusion.tv/show/food-exposed-with-nelufar-hedayat/?ancla=full-episodes&video=588644',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'https://platform.fusion.net/wp-json/fusiondotnet/v1/video/' + video_id, video_id)
info = {
'id': video_id,
'title': video['title'],
'description': video.get('excerpt'),
'timestamp': parse_iso8601(video.get('published')),
'series': video.get('show'),
}
formats = []
src = video.get('src') or {}
for f_id, f in src.items():
for q_id, q in f.items():
q_url = q.get('url')
if not q_url:
continue
ext = determine_ext(q_url, mimetype2ext(q.get('type')))
if ext == 'smil':
formats.extend(self._extract_smil_formats(q_url, video_id, fatal=False))
elif f_id == 'm3u8-variant' or (ext == 'm3u8' and q_id == 'Variant'):
formats.extend(self._extract_m3u8_formats(
q_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': '-'.join([f_id, q_id]),
'url': q_url,
'width': int_or_none(q.get('width')),
'height': int_or_none(q.get('height')),
'tbr': int_or_none(self._search_regex(r'_(\d+)\.m(?:p4|3u8)', q_url, 'bitrate')),
'ext': 'mp4' if ext == 'm3u8' else ext,
'protocol': 'm3u8_native' if ext == 'm3u8' else 'https',
})
if formats:
self._sort_formats(formats)
info['formats'] = formats
else:
info.update({
'_type': 'url',
'url': 'anvato:uni:' + video['video_ids']['anvato'],
'ie_key': 'Anvato',
})
return info
# coding: utf-8
from __future__ import unicode_literals
from .adobepass import AdobePassIE
from ..utils import (
extract_attributes,
int_or_none,
parse_age_limit,
smuggle_url,
update_url_query,
)
class FXNetworksIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?(?:fxnetworks|simpsonsworld)\.com/video/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.fxnetworks.com/video/1032565827847',
'md5': '8d99b97b4aa7a202f55b6ed47ea7e703',
'info_dict': {
'id': 'dRzwHC_MMqIv',
'ext': 'mp4',
'title': 'First Look: Better Things - Season 2',
'description': 'Because real life is like a fart. Watch this FIRST LOOK to see what inspired the new season of Better Things.',
'age_limit': 14,
'uploader': 'NEWA-FNG-FX',
'upload_date': '20170825',
'timestamp': 1503686274,
'episode_number': 0,
'season_number': 2,
'series': 'Better Things',
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.simpsonsworld.com/video/716094019682',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if 'The content you are trying to access is not available in your region.' in webpage:
self.raise_geo_restricted()
video_data = extract_attributes(self._search_regex(
r'(<a.+?rel="https?://link\.theplatform\.com/s/.+?</a>)', webpage, 'video data'))
player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None)
release_url = video_data['rel']
title = video_data['data-title']
rating = video_data.get('data-rating')
query = {
'mbr': 'true',
}
if player_type == 'movies':
query.update({
'manifest': 'm3u',
})
else:
query.update({
'switch': 'http',
})
if video_data.get('data-req-auth') == '1':
resource = self._get_mvpd_resource(
video_data['data-channel'], title,
video_data.get('data-guid'), rating)
query['auth'] = self._extract_mvpd_auth(url, video_id, 'fx', resource)
return {
'_type': 'url_transparent',
'id': video_id,
'title': title,
'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
'series': video_data.get('data-show-title'),
'episode_number': int_or_none(video_data.get('data-episode')),
'season_number': int_or_none(video_data.get('data-season')),
'thumbnail': video_data.get('data-large-thumb'),
'age_limit': parse_age_limit(rating),
'ie_key': 'ThePlatform',
}
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import (
ExtractorError,
int_or_none,
str_or_none,
strip_or_none,
try_get,
urlencode_postdata,
)
class GaiaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)'
_TESTS = [{
'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature',
'info_dict': {
'id': '89356',
'ext': 'mp4',
'title': 'Connecting with Universal Consciousness',
'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
'upload_date': '20151116',
'timestamp': 1447707266,
'duration': 936,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview',
'info_dict': {
'id': '89351',
'ext': 'mp4',
'title': 'Connecting with Universal Consciousness',
'description': 'md5:844e209ad31b7d31345f5ed689e3df6f',
'upload_date': '20151116',
'timestamp': 1447707266,
'duration': 53,
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
_NETRC_MACHINE = 'gaia'
_jwt = None
def _real_initialize(self):
auth = self._get_cookies('https://www.gaia.com/').get('auth')
if auth:
auth = self._parse_json(
compat_urllib_parse_unquote(auth.value),
None, fatal=False)
if not auth:
username, password = self._get_login_info()
if username is None:
return
auth = self._download_json(
'https://auth.gaia.com/v1/login',
None, data=urlencode_postdata({
'username': username,
'password': password
}))
if auth.get('success') is False:
raise ExtractorError(', '.join(auth['messages']), expected=True)
if auth:
self._jwt = auth.get('jwt')
def _real_extract(self, url):
display_id, vtype = re.search(self._VALID_URL, url).groups()
node_id = self._download_json(
'https://brooklyn.gaia.com/pathinfo', display_id, query={
'path': 'video/' + display_id,
})['id']
node = self._download_json(
'https://brooklyn.gaia.com/node/%d' % node_id, node_id)
vdata = node[vtype]
media_id = compat_str(vdata['nid'])
title = node['title']
headers = None
if self._jwt:
headers = {'Authorization': 'Bearer ' + self._jwt}
media = self._download_json(
'https://brooklyn.gaia.com/media/' + media_id,
media_id, headers=headers)
formats = self._extract_m3u8_formats(
media['mediaUrls']['bcHLS'], media_id, 'mp4')
self._sort_formats(formats)
subtitles = {}
text_tracks = media.get('textTracks', {})
for key in ('captions', 'subtitles'):
for lang, sub_url in text_tracks.get(key, {}).items():
subtitles.setdefault(lang, []).append({
'url': sub_url,
})
fivestar = node.get('fivestar', {})
fields = node.get('fields', {})
def get_field_value(key, value_key='value'):
return try_get(fields, lambda x: x[key][0][value_key])
return {
'id': media_id,
'display_id': display_id,
'title': title,
'formats': formats,
'description': strip_or_none(get_field_value('body') or get_field_value('teaser')),
'timestamp': int_or_none(node.get('created')),
'subtitles': subtitles,
'duration': int_or_none(vdata.get('duration')),
'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])),
'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])),
'comment_count': int_or_none(node.get('comment_count')),
'series': try_get(node, lambda x: x['series']['title'], compat_str),
'season_number': int_or_none(get_field_value('season')),
'season_id': str_or_none(get_field_value('series_nid', 'nid')),
'episode_number': int_or_none(get_field_value('episode')),
}
# coding: utf-8
from __future__ import unicode_literals
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_class,
get_element_by_id,
)
class GameInformerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>[^.?&#]+)'
_TESTS = [{
# normal Brightcove embed code extracted with BrightcoveNewIE._extract_url
'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx',
'md5': '292f26da1ab4beb4c9099f1304d2b071',
'info_dict': {
'id': '4515472681001',
'ext': 'mp4',
'title': 'Replay - Animal Crossing',
'description': 'md5:2e211891b215c85d061adc7a4dd2d930',
'timestamp': 1443457610,
'upload_date': '20150928',
'uploader_id': '694940074001',
},
}, {
# Brightcove id inside unique element with field--name-field-brightcove-video-id class
'url': 'https://www.gameinformer.com/video-feature/new-gameplay-today/2019/07/09/new-gameplay-today-streets-of-rogue',
'info_dict': {
'id': '6057111913001',
'ext': 'mp4',
'title': 'New Gameplay Today – Streets Of Rogue',
'timestamp': 1562699001,
'upload_date': '20190709',
'uploader_id': '694940074001',
},
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(
url, display_id, headers=self.geo_verification_headers())
brightcove_id = clean_html(get_element_by_class('field--name-field-brightcove-video-id', webpage) or get_element_by_id('video-source-content', webpage))
brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id if brightcove_id else BrightcoveNewIE._extract_url(self, webpage)
return self.url_result(brightcove_url, 'BrightcoveNew', brightcove_id)
from __future__ import unicode_literals
import re
from .once import OnceIE
from ..compat import (
compat_urllib_parse_unquote,
)
from ..utils import (
unescapeHTML,
url_basename,
dict_get,
)
class GameSpotIE(OnceIE):
_VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
'info_dict': {
'id': 'gs-2300-6410818',
'ext': 'mp4',
'title': 'Arma 3 - Community Guide: SITREP I',
'description': 'Check out this video where some of the basics of Arma 3 is explained.',
},
}, {
'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
'info_dict': {
'id': 'gs-2300-6424837',
'ext': 'mp4',
'title': 'Now Playing - The Witcher 3: Wild Hunt',
'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
},
'params': {
'skip_download': True, # m3u8 downloads
},
}, {
'url': 'https://www.gamespot.com/videos/embed/6439218/',
'only_matching': True,
}, {
'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
'only_matching': True,
}, {
'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
'only_matching': True,
}]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
data_video_json = self._search_regex(
r'data-video=["\'](.*?)["\']', webpage, 'data video')
data_video = self._parse_json(unescapeHTML(data_video_json), page_id)
streams = data_video['videoStreams']
manifest_url = None
formats = []
f4m_url = streams.get('f4m_stream')
if f4m_url:
manifest_url = f4m_url
formats.extend(self._extract_f4m_formats(
f4m_url + '?hdcore=3.7.0', page_id, f4m_id='hds', fatal=False))
m3u8_url = dict_get(streams, ('m3u8_stream', 'adaptive_stream'))
if m3u8_url:
manifest_url = m3u8_url
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, page_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
progressive_url = dict_get(
streams, ('progressive_hd', 'progressive_high', 'progressive_low', 'other_lr'))
if progressive_url and manifest_url:
qualities_basename = self._search_regex(
r'/([^/]+)\.csmil/',
manifest_url, 'qualities basename', default=None)
if qualities_basename:
QUALITIES_RE = r'((,\d+)+,?)'
qualities = self._search_regex(
QUALITIES_RE, qualities_basename,
'qualities', default=None)
if qualities:
qualities = list(map(lambda q: int(q), qualities.strip(',').split(',')))
qualities.sort()
http_template = re.sub(QUALITIES_RE, r'%d', qualities_basename)
http_url_basename = url_basename(progressive_url)
if m3u8_formats:
self._sort_formats(m3u8_formats)
m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none', m3u8_formats))
if len(qualities) == len(m3u8_formats):
for q, m3u8_format in zip(qualities, m3u8_formats):
f = m3u8_format.copy()
f.update({
'url': progressive_url.replace(
http_url_basename, http_template % q),
'format_id': f['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
formats.append(f)
else:
for q in qualities:
formats.append({
'url': progressive_url.replace(
http_url_basename, http_template % q),
'ext': 'mp4',
'format_id': 'http-%d' % q,
'tbr': q,
})
onceux_json = self._search_regex(
r'data-onceux-options=["\'](.*?)["\']', webpage, 'data video', default=None)
if onceux_json:
onceux_url = self._parse_json(unescapeHTML(onceux_json), page_id).get('metadataUri')
if onceux_url:
formats.extend(self._extract_once_formats(re.sub(
r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url),
http_formats_preference=-1))
if not formats:
for quality in ['sd', 'hd']:
# It's actually a link to a flv file
flv_url = streams.get('f4m_{0}'.format(quality))
if flv_url is not None:
formats.append({
'url': flv_url,
'ext': 'flv',
'format_id': quality,
})
self._sort_formats(formats)
return {
'id': data_video['guid'],
'display_id': page_id,
'title': compat_urllib_parse_unquote(data_video['title']),
'formats': formats,
'description': self._html_search_meta('description', webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
remove_end,
)
class GameStarIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?game(?P<site>pro|star)\.de/videos/.*,(?P<id>[0-9]+)\.html'
_TESTS = [{
'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
'md5': 'ee782f1f8050448c95c5cacd63bc851c',
'info_dict': {
'id': '76110',
'ext': 'mp4',
'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1406542380,
'upload_date': '20140728',
'duration': 17,
}
}, {
'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
'only_matching': True,
}, {
'url': 'http://www.gamestar.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
site = mobj.group('site')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
# TODO: there are multiple ld+json objects in the webpage,
# while _search_json_ld finds only the first one
json_ld = self._parse_json(self._search_regex(
r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
webpage, 'JSON-LD', group='json_ld'), video_id)
info_dict = self._json_ld(json_ld, video_id)
info_dict['title'] = remove_end(
info_dict['title'], ' - Game%s' % site.title())
view_count = int_or_none(json_ld.get('interactionCount'))
comment_count = int_or_none(self._html_search_regex(
r'<span>Kommentare</span>\s*<span[^>]+class=["\']count[^>]+>\s*\(\s*([0-9]+)',
webpage, 'comment count', fatal=False))
info_dict.update({
'id': video_id,
'url': 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id,
'ext': 'mp4',
'view_count': view_count,
'comment_count': comment_count
})
return info_dict
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
unified_strdate,
)
class GaskrankIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.htm'
_TESTS = [{
'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
'md5': '1ae88dbac97887d85ebd1157a95fc4f9',
'info_dict': {
'id': '201601/26955',
'ext': 'mp4',
'title': 'Strike! Einparken können nur Männer - Flurschaden hält sich in Grenzen *lol*',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['motorrad-fun'],
'display_id': 'strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden',
'uploader_id': 'Bikefun',
'upload_date': '20170110',
'uploader_url': None,
}
}, {
'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm',
'md5': 'c33ee32c711bc6c8224bfcbe62b23095',
'info_dict': {
'id': '201106/15920',
'ext': 'mp4',
'title': 'Isle of Man - Michael Dunlop vs Guy Martin - schwindelig kucken',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['racing'],
'display_id': 'isle-of-man-tt-2011-michael-du-15920',
'uploader_id': 'IOM',
'upload_date': '20170523',
'uploader_url': 'www.iomtt.com',
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = self._og_search_title(
webpage, default=None) or self._html_search_meta(
'title', webpage, fatal=True)
categories = [re.match(self._VALID_URL, url).group('categories')]
mobj = re.search(
r'Video von:\s*(?P<uploader_id>[^|]*?)\s*\|\s*vom:\s*(?P<upload_date>[0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])',
webpage)
if mobj is not None:
uploader_id = mobj.groupdict().get('uploader_id')
upload_date = unified_strdate(mobj.groupdict().get('upload_date'))
uploader_url = self._search_regex(
r'Homepage:\s*<[^>]*>(?P<uploader_url>[^<]*)',
webpage, 'uploader_url', default=None)
tags = re.findall(
r'/tv/tags/[^/]+/"\s*>(?P<tag>[^<]*?)<',
webpage)
view_count = self._search_regex(
r'class\s*=\s*"gkRight"(?:[^>]*>\s*<[^>]*)*icon-eye-open(?:[^>]*>\s*<[^>]*)*>\s*(?P<view_count>[0-9\.]*)',
webpage, 'view_count', default=None)
if view_count:
view_count = int_or_none(view_count.replace('.', ''))
average_rating = self._search_regex(
r'itemprop\s*=\s*"ratingValue"[^>]*>\s*(?P<average_rating>[0-9,]+)',
webpage, 'average_rating')
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
video_id = self._search_regex(
r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4',
webpage, 'video id', default=display_id)
entry = self._parse_html5_media_entries(url, webpage, video_id)[0]
entry.update({
'id': video_id,
'title': title,
'categories': categories,
'display_id': display_id,
'uploader_id': uploader_id,
'upload_date': upload_date,
'uploader_url': uploader_url,
'tags': tags,
'view_count': view_count,
'average_rating': average_rating,
})
self._sort_formats(entry['formats'])
return entry
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class GazetaIE(InfoExtractor):
_VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:main/)*(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
_TESTS = [{
'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml',
'md5': 'd49c9bdc6e5a7888f27475dc215ee789',
'info_dict': {
'id': '205566',
'ext': 'mp4',
'title': '«70–80 процентов гражданских в Донецке на грани голода»',
'description': 'md5:38617526050bd17b234728e7f9620a71',
'thumbnail': r're:^https?://.*\.jpg',
},
'skip': 'video not found',
}, {
'url': 'http://www.gazeta.ru/lifestyle/video/2015/03/08/master-klass_krasivoi_byt._delaem_vesennii_makiyazh.shtml',
'only_matching': True,
}, {
'url': 'http://www.gazeta.ru/video/main/main/2015/06/22/platit_ili_ne_platit_po_isku_yukosa.shtml',
'md5': '37f19f78355eb2f4256ee1688359f24c',
'info_dict': {
'id': '252048',
'ext': 'mp4',
'title': '"Если по иску ЮКОСа придется платить, это будет большой удар по бюджету"',
},
'add_ie': ['EaglePlatform'],
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
embed_url = '%s?p=embed' % mobj.group('url')
embed_page = self._download_webpage(
embed_url, display_id, 'Downloading embed page')
video_id = self._search_regex(
r'<div[^>]*?class="eagleplayer"[^>]*?data-id="([^"]+)"', embed_page, 'video id')
return self.url_result(
'eagleplatform:gazeta.media.eagleplatform.com:%s' % video_id, 'EaglePlatform')
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
HEADRequest,
sanitized_Request,
smuggle_url,
urlencode_postdata,
)
class GDCVaultIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)(?:/(?P<name>[\w-]+))?'
_NETRC_MACHINE = 'gdcvault'
_TESTS = [
{
'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
'md5': '7ce8388f544c88b7ac11c7ab1b593704',
'info_dict': {
'id': '201311826596_AWNY',
'display_id': 'Doki-Doki-Universe-Sweet-Simple',
'ext': 'mp4',
'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
}
},
{
'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
'info_dict': {
'id': '201203272_1330951438328RSXR',
'display_id': 'Embracing-the-Dark-Art-of',
'ext': 'flv',
'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
},
'params': {
'skip_download': True, # Requires rtmpdump
}
},
{
'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
'md5': 'a5eb77996ef82118afbbe8e48731b98e',
'info_dict': {
'id': '1015301',
'display_id': 'Thexder-Meets-Windows-95-or',
'ext': 'flv',
'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
},
'skip': 'Requires login',
},
{
'url': 'http://gdcvault.com/play/1020791/',
'only_matching': True,
},
{
# Hard-coded hostname
'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface',
'md5': 'a8efb6c31ed06ca8739294960b2dbabd',
'info_dict': {
'id': '840376_BQRC',
'ext': 'mp4',
'display_id': 'Tenacious-Design-and-The-Interface',
'title': 'Tenacious Design and The Interface of \'Destiny\'',
},
},
{
# Multiple audios
'url': 'http://www.gdcvault.com/play/1014631/Classic-Game-Postmortem-PAC',
'info_dict': {
'id': '12396_1299111843500GMPX',
'ext': 'mp4',
'title': 'How to Create a Good Game - From My Experience of Designing Pac-Man',
},
# 'params': {
# 'skip_download': True, # Requires rtmpdump
# 'format': 'jp', # The japanese audio
# }
},
{
# gdc-player.html
'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo',
'info_dict': {
'id': '9350_1238021887562UHXB',
'display_id': 'An-American-engine-in-Tokyo',
'ext': 'mp4',
'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT',
},
},
{
# Kaltura Embed
'url': 'https://www.gdcvault.com/play/1026180/Mastering-the-Apex-of-Scaling',
'info_dict': {
'id': '0_h1fg8j3p',
'ext': 'mp4',
'title': 'Mastering the Apex of Scaling Game Servers (Presented by Multiplay)',
'timestamp': 1554401811,
'upload_date': '20190404',
'uploader_id': 'joe@blazestreaming.com',
},
'params': {
'format': 'mp4-408',
},
},
]
def _login(self, webpage_url, display_id):
username, password = self._get_login_info()
if username is None or password is None:
self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
return None
mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
login_url = mobj.group('root_url') + 'api/login.php'
logout_url = mobj.group('root_url') + 'logout'
login_form = {
'email': username,
'password': password,
}
request = sanitized_Request(login_url, urlencode_postdata(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')
self._download_webpage(logout_url, display_id, 'Logging out')
return start_page
def _real_extract(self, url):
video_id, name = re.match(self._VALID_URL, url).groups()
display_id = name or video_id
webpage_url = 'http://www.gdcvault.com/play/' + video_id
start_page = self._download_webpage(webpage_url, display_id)
direct_url = self._search_regex(
r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
start_page, 'url', default=None)
if direct_url:
title = self._html_search_regex(
r'<td><strong>Session Name:?</strong></td>\s*<td>(.*?)</td>',
start_page, 'title')
video_url = 'http://www.gdcvault.com' + direct_url
# resolve the url so that we can detect the correct extension
video_url = self._request_webpage(
HEADRequest(video_url), video_id).geturl()
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
}
embed_url = KalturaIE._extract_url(start_page)
if embed_url:
embed_url = smuggle_url(embed_url, {'source_url': url})
ie_key = 'Kaltura'
else:
PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>'
xml_root = self._html_search_regex(
PLAYER_REGEX, start_page, 'xml root', default=None)
if xml_root is None:
# Probably need to authenticate
login_res = self._login(webpage_url, display_id)
if login_res is None:
self.report_warning('Could not login.')
else:
start_page = login_res
# Grab the url from the authenticated page
xml_root = self._html_search_regex(
PLAYER_REGEX, start_page, 'xml root')
xml_name = self._html_search_regex(
r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>',
start_page, 'xml filename')
embed_url = '%s/xml/%s' % (xml_root, xml_name)
ie_key = 'DigitallySpeaking'
return {
'_type': 'url_transparent',
'id': video_id,
'display_id': display_id,
'url': embed_url,
'ie_key': ie_key,
}
# coding: utf-8
from __future__ import unicode_literals
import os
import re
import sys
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
compat_etree_fromstring,
compat_str,
compat_urllib_parse_unquote,
compat_urlparse,
compat_xml_parse_error,
)
from ..utils import (
determine_ext,
ExtractorError,
float_or_none,
HEADRequest,
is_html,
js_to_json,
KNOWN_EXTENSIONS,
merge_dicts,
mimetype2ext,
orderedSet,
sanitized_Request,
smuggle_url,
unescapeHTML,
unified_strdate,
unsmuggle_url,
UnsupportedError,
xpath_text,
)
from .commonprotocols import RtmpIE
from .brightcove import (
BrightcoveLegacyIE,
BrightcoveNewIE,
)
from .nexx import (
NexxIE,
NexxEmbedIE,
)
from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
from .tvc import TVCIE
from .sportbox import SportBoxIE
from .smotri import SmotriIE
from .myvi import MyviIE
from .condenast import CondeNastIE
from .udn import UDNEmbedIE
from .senateisvp import SenateISVPIE
from .svt import SVTIE
from .pornhub import PornHubIE
from .xhamster import XHamsterEmbedIE
from .tnaflix import TNAFlixNetworkEmbedIE
from .drtuber import DrTuberIE
from .redtube import RedTubeIE
from .tube8 import Tube8IE
from .mofosex import MofosexEmbedIE
from .spankwire import SpankwireIE
from .youporn import YouPornIE
from .vimeo import VimeoIE
from .dailymotion import DailymotionIE
from .dailymail import DailyMailIE
from .onionstudios import OnionStudiosIE
from .viewlift import ViewLiftEmbedIE
from .mtv import MTVServicesEmbeddedIE
from .pladform import PladformIE
from .videomore import VideomoreIE
from .webcaster import WebcasterFeedIE
from .googledrive import GoogleDriveIE
from .jwplatform import JWPlatformIE
from .digiteka import DigitekaIE
from .arkena import ArkenaIE
from .instagram import InstagramIE
from .liveleak import LiveLeakIE
from .threeqsdn import ThreeQSDNIE
from .theplatform import ThePlatformIE
from .kaltura import KalturaIE
from .eagleplatform import EaglePlatformIE
from .facebook import FacebookIE
from .soundcloud import SoundcloudEmbedIE
from .tunein import TuneInBaseIE
from .vbox7 import Vbox7IE
from .dbtv import DBTVIE
from .piksel import PikselIE
from .videa import VideaIE
from .twentymin import TwentyMinutenIE
from .ustream import UstreamIE
from .videopress import VideoPressIE
from .rutube import RutubeIE
from .limelight import LimelightBaseIE
from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
from .wistia import WistiaIE
from .mediaset import MediasetIE
from .joj import JojIE
from .megaphone import MegaphoneIE
from .vzaar import VzaarIE
from .channel9 import Channel9IE
from .vshare import VShareIE
from .mediasite import MediasiteIE
from .springboardplatform import SpringboardPlatformIE
from .yapfiles import YapFilesIE
from .vice import ViceIE
from .xfileshare import XFileShareIE
from .cloudflarestream import CloudflareStreamIE
from .peertube import PeerTubeIE
from .teachable import TeachableIE
from .indavideo import IndavideoEmbedIE
from .apa import APAIE
from .foxnews import FoxNewsIE
from .viqeo import ViqeoIE
from .expressen import ExpressenIE
from .zype import ZypeIE
from .odnoklassniki import OdnoklassnikiIE
from .kinja import KinjaEmbedIE
class GenericIE(InfoExtractor):
IE_DESC = 'Generic downloader that works on some sites'
_VALID_URL = r'.*'
IE_NAME = 'generic'
_TESTS = [
# Direct link to a video
{
'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
'md5': '67d406c2bcb6af27fa886f31aa934bbe',
'info_dict': {
'id': 'trailer',
'ext': 'mp4',
'title': 'trailer',
'upload_date': '20100513',
}
},
# Direct link to media delivered compressed (until Accept-Encoding is *)
{
'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
'md5': '128c42e68b13950268b648275386fc74',
'info_dict': {
'id': 'FictionJunction-Parallel_Hearts',
'ext': 'flac',
'title': 'FictionJunction-Parallel_Hearts',
'upload_date': '20140522',
},
'expected_warnings': [
'URL could be a direct video link, returning it as such.'
],
'skip': 'URL invalid',
},
# Direct download with broken HEAD
{
'url': 'http://ai-radio.org:8000/radio.opus',
'info_dict': {
'id': 'radio',
'ext': 'opus',
'title': 'radio',
},
'params': {
'skip_download': True, # infinite live stream
},
'expected_warnings': [
r'501.*Not Implemented',
r'400.*Bad Request',
],
},
# Direct link with incorrect MIME type
{
'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
'md5': '4ccbebe5f36706d85221f204d7eb5913',
'info_dict': {
'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
'id': '5_Lennart_Poettering_-_Systemd',
'ext': 'webm',
'title': '5_Lennart_Poettering_-_Systemd',
'upload_date': '20141120',
},
'expected_warnings': [
'URL could be a direct video link, returning it as such.'
]
},
# RSS feed
{
'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
'info_dict': {
'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
'title': 'Zero Punctuation',
'description': 're:.*groundbreaking video review series.*'
},
'playlist_mincount': 11,
},
# RSS feed with enclosure
{
'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
'info_dict': {
'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
'ext': 'm4v',
'upload_date': '20150228',
'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
}
},
# RSS feed with enclosures and unsupported link URLs
{
'url': 'http://www.hellointernet.fm/podcast?format=rss',
'info_dict': {
'id': 'http://www.hellointernet.fm/podcast?format=rss',
'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
'title': 'Hello Internet',
},
'playlist_mincount': 100,
},
# SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
{
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
'info_dict': {
'id': 'smil',
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'upload_date': '20130627',
'formats': 'mincount:16',
'subtitles': 'mincount:1',
},
'params': {
'force_generic_extractor': True,
'skip_download': True,
},
},
# SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
{
'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
'info_dict': {
'id': 'hds',
'ext': 'flv',
'title': 'hds',
'formats': 'mincount:1',
},
'params': {
'skip_download': True,
},
},
# SMIL from https://www.restudy.dk/video/play/id/1637
{
'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
'info_dict': {
'id': 'video_1637',
'ext': 'flv',
'title': 'video_1637',
'formats': 'mincount:3',
},
'params': {
'skip_download': True,
},
},
# SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
{
'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
'info_dict': {
'id': 'smil-service',
'ext': 'flv',
'title': 'smil-service',
'formats': 'mincount:1',
},
'params': {
'skip_download': True,
},
},
# SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
{
'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
'info_dict': {
'id': '4719370',
'ext': 'mp4',
'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
'formats': 'mincount:3',
},
'params': {
'skip_download': True,
},
},
# XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
{
'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
'info_dict': {
'id': 'mZlp2ctYIUEB',
'ext': 'mp4',
'title': 'Tikibad ontruimd wegens brand',
'description': 'md5:05ca046ff47b931f9b04855015e163a4',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 33,
},
'params': {
'skip_download': True,
},
},
# MPD from http://dash-mse-test.appspot.com/media.html
{
'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
'info_dict': {
'id': 'car-20120827-manifest',
'ext': 'mp4',
'title': 'car-20120827-manifest',
'formats': 'mincount:9',
'upload_date': '20130904',
},
'params': {
'format': 'bestvideo',
},
},
# m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
{
'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
'info_dict': {
'id': 'content',
'ext': 'mp4',
'title': 'content',
'formats': 'mincount:8',
},
'params': {
# m3u8 downloads
'skip_download': True,
},
'skip': 'video gone',
},
# m3u8 served with Content-Type: text/plain
{
'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
'info_dict': {
'id': 'index',
'ext': 'mp4',
'title': 'index',
'upload_date': '20140720',
'formats': 'mincount:11',
},
'params': {
# m3u8 downloads
'skip_download': True,
},
'skip': 'video gone',
},
# google redirect
{
'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
'info_dict': {
'id': 'cmQHVoWB5FY',
'ext': 'mp4',
'upload_date': '20130224',
'uploader_id': 'TheVerge',
'description': r're:^Chris Ziegler takes a look at the\.*',
'uploader': 'The Verge',
'title': 'First Firefox OS phones side-by-side',
},
'params': {
'skip_download': False,
}
},
{
# redirect in Refresh HTTP header
'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
'info_dict': {
'id': 'pO8h3EaFRdo',
'ext': 'mp4',
'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
'upload_date': '20150917',
'uploader_id': 'brtvofficial',
'uploader': 'Boiler Room',
},
'params': {
'skip_download': False,
},
},
{
'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
'info_dict': {
'id': '13601338388002',
'ext': 'mp4',
'uploader': 'www.hodiho.fr',
'title': 'R\u00e9gis plante sa Jeep',
}
},
# bandcamp page with custom domain
{
'add_ie': ['Bandcamp'],
'url': 'http://bronyrock.com/track/the-pony-mash',
'info_dict': {
'id': '3235767654',
'ext': 'mp3',
'title': 'The Pony Mash',
'uploader': 'M_Pallante',
},
'skip': 'There is a limit of 200 free downloads / month for the test song',
},
{
# embedded brightcove video
# it also tests brightcove videos that need to set the 'Referer'
# in the http requests
'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
'info_dict': {
'id': '2765128793001',
'ext': 'mp4',
'title': 'Le cours de bourse : l’analyse technique',
'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
'uploader': 'BFM BUSINESS',
},
'params': {
'skip_download': True,
},
},
{
# embedded with itemprop embedURL and video id spelled as `idVideo`
'add_id': ['BrightcoveLegacy'],
'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
'info_dict': {
'id': '5255628253001',
'ext': 'mp4',
'title': 'md5:37c519b1128915607601e75a87995fc0',
'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
'uploader': 'BFM BUSINESS',
'uploader_id': '876450612001',
'timestamp': 1482255315,
'upload_date': '20161220',
},
'params': {
'skip_download': True,
},
},
{
# https://github.com/ytdl-org/youtube-dl/issues/2253
'url': 'http://bcove.me/i6nfkrc3',
'md5': '0ba9446db037002366bab3b3eb30c88c',
'info_dict': {
'id': '3101154703001',
'ext': 'mp4',
'title': 'Still no power',
'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': ['BrightcoveLegacy'],
'skip': 'video gone',
},
{
'url': 'http://www.championat.com/video/football/v/87/87499.html',
'md5': 'fb973ecf6e4a78a67453647444222983',
'info_dict': {
'id': '3414141473001',
'ext': 'mp4',
'title': 'Видео. Удаление Дзагоева (ЦСКА)',
'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
'uploader': 'Championat',
},
},
{
# https://github.com/ytdl-org/youtube-dl/issues/3541
'add_ie': ['BrightcoveLegacy'],
'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
'info_dict': {
'id': '3866516442001',
'ext': 'mp4',
'title': 'Leer mij vrouwen kennen: Aflevering 1',
'description': 'Leer mij vrouwen kennen: Aflevering 1',
'uploader': 'SBS Broadcasting',
},
'skip': 'Restricted to Netherlands',
'params': {
'skip_download': True, # m3u8 download
},
},
{
# Brightcove video in <iframe>
'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
'md5': '36d74ef5e37c8b4a2ce92880d208b968',
'info_dict': {
'id': '5360463607001',
'ext': 'mp4',
'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼（Zade Dirani）在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》（HEARTBEAT），为受到六年冲突影响的叙利亚儿童发出强烈呐喊，呼吁世界做出共同努力，使叙利亚儿童重新获得享有正常童年生活的权利。',
'uploader': 'United Nations',
'uploader_id': '1362235914001',
'timestamp': 1489593889,
'upload_date': '20170315',
},
'add_ie': ['BrightcoveLegacy'],
},
{
# Brightcove with alternative playerID key
'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
'info_dict': {
'id': 'nmeth.2062_SV1',
'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
},
'playlist': [{
'info_dict': {
'id': '2228375078001',
'ext': 'mp4',
'title': 'nmeth.2062-sv1',
'description': 'nmeth.2062-sv1',
'timestamp': 1363357591,
'upload_date': '20130315',
'uploader': 'Nature Publishing Group',
'uploader_id': '1964492299001',
},
}],
},
{
# Brightcove with UUID in videoPlayer
'url': 'http://www8.hp.com/cn/zh/home.html',
'info_dict': {
'id': '5255815316001',
'ext': 'mp4',
'title': 'Sprocket Video - China',
'description': 'Sprocket Video - China',
'uploader': 'HP-Video Gallery',
'timestamp': 1482263210,
'upload_date': '20161220',
'uploader_id': '1107601872001',
},
'params': {
'skip_download': True, # m3u8 download
},
'skip': 'video rotates...weekly?',
},
{
# Brightcove:new type [2].
'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
'md5': '2b35148fcf48da41c9fb4591650784f3',
'info_dict': {
'id': '5348741021001',
'ext': 'mp4',
'upload_date': '20170306',
'uploader_id': '4191638492001',
'timestamp': 1488769918,
'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
},
},
{
# Alternative brightcove <video> attributes
'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
'info_dict': {
'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
},
'playlist': [{
'md5': '732d22ba3d33f2f3fc253c39f8f36523',
'info_dict': {
'id': '5311302538001',
'ext': 'mp4',
'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
'timestamp': 1486321708,
'upload_date': '20170205',
'uploader_id': '800000640001',
},
'only_matching': True,
}],
},
{
# Brightcove with UUID in videoPlayer
'url': 'http://www8.hp.com/cn/zh/home.html',
'info_dict': {
'id': '5255815316001',
'ext': 'mp4',
'title': 'Sprocket Video - China',
'description': 'Sprocket Video - China',
'uploader': 'HP-Video Gallery',
'timestamp': 1482263210,
'upload_date': '20161220',
'uploader_id': '1107601872001',
},
'params': {
'skip_download': True, # m3u8 download
},
},
# ooyala video
{
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
'md5': '166dd577b433b4d4ebfee10b0824d8ff',
'info_dict': {
'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
'ext': 'mp4',
'title': '2cc213299525360.mov', # that's what we get
'duration': 238.231,
},
'add_ie': ['Ooyala'],
},
{
# ooyala video embedded with http://player.ooyala.com/iframe.js
'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
'info_dict': {
'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
'ext': 'mp4',
'title': '"Steve Jobs: Man in the Machine" trailer',
'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
'duration': 135.427,
},
'params': {
'skip_download': True,
},
'skip': 'movie expired',
},
# ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
{
'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
'info_dict': {
'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
'ext': 'mp4',
'title': 'Steampunk Fest Comes to Honesdale',
'duration': 43.276,
},
'params': {
'skip_download': True,
}
},
# embed.ly video
{
'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
'info_dict': {
'id': '9ODmcdjQcHQ',
'ext': 'mp4',
'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
'upload_date': '20140225',
'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
'uploader': 'Tested',
'uploader_id': 'testedcom',
},
# No need to test YoutubeIE here
'params': {
'skip_download': True,
},
},
# funnyordie embed
{
'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
'info_dict': {
'id': '18e820ec3f',
'ext': 'mp4',
'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
},
# HEAD requests lead to endless 301, while GET is OK
'expected_warnings': ['301'],
},
# RUTV embed
{
'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
'info_dict': {
'id': '776940',
'ext': 'mp4',
'title': 'Охотское море стало целиком российским',
'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
# TVC embed
{
'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
'info_dict': {
'id': '55304',
'ext': 'mp4',
'title': 'Дошкольное воспитание',
},
},
# SportBox embed
{
'url': 'http://www.vestifinance.ru/articles/25753',
'info_dict': {
'id': '25753',
'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
},
'playlist': [{
'info_dict': {
'id': '370908',
'title': 'Госзаказ. День 3',
'ext': 'mp4',
}
}, {
'info_dict': {
'id': '370905',
'title': 'Госзаказ. День 2',
'ext': 'mp4',
}
}, {
'info_dict': {
'id': '370902',
'title': 'Госзаказ. День 1',
'ext': 'mp4',
}
}],
'params': {
# m3u8 download
'skip_download': True,
},
},
# Myvi.ru embed
{
'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
'info_dict': {
'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
'ext': 'mp4',
'title': 'Ужастики, русский трейлер (2015)',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 153,
}
},
# XHamster embed
{
'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
'info_dict': {
'id': 'showthread',
'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
},
'playlist_mincount': 7,
# This forum does not allow <iframe> syntaxes anymore
# Now HTML tags are displayed as-is
'skip': 'No videos on this page',
},
# Embedded TED video
{
'url': 'http://en.support.wordpress.com/videos/ted-talks/',
'md5': '65fdff94098e4a607385a60c5177c638',
'info_dict': {
'id': '1969',
'ext': 'mp4',
'title': 'Hidden miracles of the natural world',
'uploader': 'Louie Schwartzberg',
'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
}
},
# nowvideo embed hidden behind percent encoding
{
'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
'md5': '2baf4ddd70f697d94b1c18cf796d5107',
'info_dict': {
'id': '06e53103ca9aa',
'ext': 'flv',
'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
'description': 'No description',
},
},
# arte embed
{
'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
'md5': '7653032cbb25bf6c80d80f217055fa43',
'info_dict': {
'id': '048195-004_PLUS7-F',
'ext': 'flv',
'title': 'X:enius',
'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
'upload_date': '20140320',
},
'params': {
'skip_download': 'Requires rtmpdump'
},
'skip': 'video gone',
},
# francetv embed
{
'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
'info_dict': {
'id': 'EV_30231',
'ext': 'mp4',
'title': 'Alcaline, le concert avec Calogero',
'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
'upload_date': '20150226',
'timestamp': 1424989860,
'duration': 5400,
},
'params': {
# m3u8 downloads
'skip_download': True,
},
'expected_warnings': [
'Forbidden'
]
},
# Condé Nast embed
{
'url': 'http://www.wired.com/2014/04/honda-asimo/',
'md5': 'ba0dfe966fa007657bd1443ee672db0f',
'info_dict': {
'id': '53501be369702d3275860000',
'ext': 'mp4',
'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
}
},
# Dailymotion embed
{
'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
'md5': '441aeeb82eb72c422c7f14ec533999cd',
'info_dict': {
'id': 'k2mm4bCdJ6CQ2i7c8o2',
'ext': 'mp4',
'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
'uploader': 'Spi0n',
'uploader_id': 'xgditw',
'upload_date': '20140425',
'timestamp': 1398441542,
},
'add_ie': ['Dailymotion'],
},
# DailyMail embed
{
'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
'info_dict': {
'id': '1495629',
'ext': 'mp4',
'title': 'Care worker punches elderly dementia patient in head 11 times',
'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
},
'add_ie': ['DailyMail'],
'params': {
'skip_download': True,
},
},
# YouTube embed
{
'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
'info_dict': {
'id': 'FXRb4ykk4S0',
'ext': 'mp4',
'title': 'The NBL Auction 2014',
'uploader': 'BADMINTON England',
'uploader_id': 'BADMINTONEvents',
'upload_date': '20140603',
'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
},
'add_ie': ['Youtube'],
'params': {
'skip_download': True,
}
},
# MTVSercices embed
{
'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
'md5': 'ca1aef97695ef2c1d6973256a57e5252',
'info_dict': {
'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
'ext': 'mp4',
'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
'description': 'Two valets share their love for movie star Liam Neesons.',
'timestamp': 1349922600,
'upload_date': '20121011',
},
},
# YouTube embed via <data-embed-url="">
{
'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
'info_dict': {
'id': '4vAffPZIT44',
'ext': 'mp4',
'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
'uploader': 'Gameloft',
'uploader_id': 'gameloft',
'upload_date': '20140828',
'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
},
'params': {
'skip_download': True,
}
},
# YouTube <object> embed
{
'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
'md5': '516718101ec834f74318df76259fb3cc',
'info_dict': {
'id': 'msN87y-iEx0',
'ext': 'webm',
'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
'upload_date': '20080526',
'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
'uploader': 'Christopher Sykes',
'uploader_id': 'ChristopherJSykes',
},
'add_ie': ['Youtube'],
},
# Camtasia studio
{
'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
'playlist': [{
'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
'info_dict': {
'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
'ext': 'flv',
'duration': 2235.90,
}
}, {
'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
'info_dict': {
'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
'ext': 'flv',
'duration': 2235.93,
}
}],
'info_dict': {
'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
}
},
# Flowplayer
{
'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
'md5': '9d65602bf31c6e20014319c7d07fba27',
'info_dict': {
'id': '5123ea6d5e5a7',
'ext': 'mp4',
'age_limit': 18,
'uploader': 'www.handjobhub.com',
'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
}
},
# Multiple brightcove videos
# https://github.com/ytdl-org/youtube-dl/issues/2283
{
'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
'info_dict': {
'id': 'always-never',
'title': 'Always / Never - The New Yorker',
},
'playlist_count': 3,
'params': {
'extract_flat': False,
'skip_download': True,
}
},
# MLB embed
{
'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
'md5': '96f09a37e44da40dd083e12d9a683327',
'info_dict': {
'id': '33322633',
'ext': 'mp4',
'title': 'Ump changes call to ball',
'description': 'md5:71c11215384298a172a6dcb4c2e20685',
'duration': 48,
'timestamp': 1401537900,
'upload_date': '20140531',
'thumbnail': r're:^https?://.*\.jpg$',
},
},
# Wistia embed
{
'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
'info_dict': {
'id': '6e2wtrbdaf',
'ext': 'mov',
'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
'description': 'a Paywall Videos video from Remilon',
'duration': 644.072,
'uploader': 'study.com',
'timestamp': 1459678540,
'upload_date': '20160403',
'filesize': 24687186,
},
},
{
'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
'info_dict': {
'id': 'uxjb0lwrcz',
'ext': 'mp4',
'title': 'Conversation about Hexagonal Rails Part 1',
'description': 'a Martin Fowler video from ThoughtWorks',
'duration': 1715.0,
'uploader': 'thoughtworks.wistia.com',
'timestamp': 1401832161,
'upload_date': '20140603',
},
},
# Wistia standard embed (async)
{
'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
'info_dict': {
'id': '807fafadvk',
'ext': 'mp4',
'title': 'Drip Brennan Dunn Workshop',
'description': 'a JV Webinars video from getdrip-1',
'duration': 4986.95,
'timestamp': 1463607249,
'upload_date': '20160518',
},
'params': {
'skip_download': True,
}
},
# Soundcloud embed
{
'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
'info_dict': {
'id': '174391317',
'ext': 'mp3',
'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
'uploader': 'Sophos Security',
'title': 'Chet Chat 171 - Oct 29, 2014',
'upload_date': '20141029',
}
},
# Soundcloud multiple embeds
{
'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
'info_dict': {
'id': '52809',
'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
},
'playlist_mincount': 7,
},
# TuneIn station embed
{
'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
'info_dict': {
'id': '204146',
'ext': 'mp3',
'title': 'CNRV',
'location': 'Paris, France',
'is_live': True,
},
'params': {
# Live stream
'skip_download': True,
},
},
# Livestream embed
{
'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
'info_dict': {
'id': '67864563',
'ext': 'flv',
'upload_date': '20141112',
'title': 'Rosetta #CometLanding webcast HL 10',
}
},
# Another Livestream embed, without 'new.' in URL
{
'url': 'https://www.freespeech.org/',
'info_dict': {
'id': '123537347',
'ext': 'mp4',
'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
},
'params': {
# Live stream
'skip_download': True,
},
},
# LazyYT
{
'url': 'https://skiplagged.com/',
'info_dict': {
'id': 'skiplagged',
'title': 'Skiplagged: The smart way to find cheap flights',
},
'playlist_mincount': 1,
'add_ie': ['Youtube'],
},
# Cinchcast embed
{
'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
'info_dict': {
'id': '7141703',
'ext': 'mp3',
'upload_date': '20141126',
'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
}
},
# Cinerama player
{
'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
'info_dict': {
'id': '730m_DandD_1901_512k',
'ext': 'mp4',
'uploader': 'www.abc.net.au',
'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
}
},
# embedded viddler video
{
'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
'info_dict': {
'id': '4d03aad9',
'ext': 'mp4',
'uploader': 'deadspin',
'title': 'WALL-TO-GORTAT',
'timestamp': 1422285291,
'upload_date': '20150126',
},
'add_ie': ['Viddler'],
},
# Libsyn embed
{
'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
'info_dict': {
'id': '3377616',
'ext': 'mp3',
'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
'description': 'md5:601cb790edd05908957dae8aaa866465',
'upload_date': '20150220',
},
'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
},
# jwplayer YouTube
{
'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
'info_dict': {
'id': 'Mrj4DVp2zeA',
'ext': 'mp4',
'upload_date': '20150212',
'uploader': 'The National Archives UK',
'description': 'md5:8078af856dca76edc42910b61273dbbf',
'uploader_id': 'NationalArchives08',
'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
},
},
# jwplayer rtmp
{
'url': 'http://www.suffolk.edu/sjc/live.php',
'info_dict': {
'id': 'live',
'ext': 'flv',
'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
'uploader': 'www.suffolk.edu',
},
'params': {
'skip_download': True,
},
'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
},
# Complex jwplayer
{
'url': 'http://www.indiedb.com/games/king-machine/videos',
'info_dict': {
'id': 'videos',
'ext': 'mp4',
'title': 'king machine trailer 1',
'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
'thumbnail': r're:^https?://.*\.jpg$',
},
},
{
# JWPlayer config passed as variable
'url': 'http://www.txxx.com/videos/3326530/ariele/',
'info_dict': {
'id': '3326530_hq',
'ext': 'mp4',
'title': 'ARIELE | Tube Cup',
'uploader': 'www.txxx.com',
'age_limit': 18,
},
'params': {
'skip_download': True,
}
},
{
# JWPlatform iframe
'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
'info_dict': {
'id': 'O0c5JcKT',
'ext': 'mp4',
'upload_date': '20171122',
'timestamp': 1511366290,
'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
},
'add_ie': [JWPlatformIE.ie_key()],
},
{
# Video.js embed, multiple formats
'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
'info_dict': {
'id': 'yygqldloqIk',
'ext': 'mp4',
'title': 'SolidWorks. Урок 6 Настройка чертежа',
'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
'upload_date': '20130314',
'uploader': 'PROстое3D',
'uploader_id': 'PROstoe3D',
},
'params': {
'skip_download': True,
},
},
{
# Video.js embed, single format
'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
'info_dict': {
'id': 'watch',
'ext': 'mp4',
'title': 'Step 1 - Good Foundation',
'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
},
'params': {
'skip_download': True,
},
},
# rtl.nl embed
{
'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
'playlist_mincount': 5,
'info_dict': {
'id': 'aanslagen-kopenhagen',
'title': 'Aanslagen Kopenhagen',
}
},
# Zapiks embed
{
'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
'info_dict': {
'id': '118046',
'ext': 'mp4',
'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
}
},
# Kaltura embed (different embed code)
{
'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
'info_dict': {
'id': '1_a52wc67y',
'ext': 'flv',
'upload_date': '20150127',
'uploader_id': 'PremierMedia',
'timestamp': int,
'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
},
},
# Kaltura embed with single quotes
{
'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
'info_dict': {
'id': '0_izeg5utt',
'ext': 'mp4',
'title': '35871',
'timestamp': 1355743100,
'upload_date': '20121217',
'uploader_id': 'cplapp@learn360.com',
},
'add_ie': ['Kaltura'],
},
{
# Kaltura embedded via quoted entry_id
'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
'info_dict': {
'id': '0_utuok90b',
'ext': 'mp4',
'title': '06_matthew_brender_raj_dutt',
'timestamp': 1466638791,
'upload_date': '20160622',
},
'add_ie': ['Kaltura'],
'expected_warnings': [
'Could not send HEAD request'
],
'params': {
'skip_download': True,
}
},
{
# Kaltura embedded, some fileExt broken (#11480)
'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
'info_dict': {
'id': '1_sgtvehim',
'ext': 'mp4',
'title': 'Our "Standard Models" of particle physics and cosmology',
'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
'timestamp': 1321158993,
'upload_date': '20111113',
'uploader_id': 'kps1',
},
'add_ie': ['Kaltura'],
},
{
# Kaltura iframe embed
'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
'info_dict': {
'id': '0_f2cfbpwy',
'ext': 'mp4',
'title': 'I. M. Pei: A Centennial Celebration',
'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
'upload_date': '20170403',
'uploader_id': 'batchUser',
'timestamp': 1491232186,
},
'add_ie': ['Kaltura'],
},
{
# Kaltura iframe embed, more sophisticated
'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
'info_dict': {
'id': '1_9gzouybz',
'ext': 'mp4',
'title': 'lecture-05sep2017',
'description': 'md5:40f347d91fd4ba047e511c5321064b49',
'upload_date': '20170913',
'uploader_id': 'eps2',
'timestamp': 1505340777,
},
'params': {
'skip_download': True,
},
'add_ie': ['Kaltura'],
},
{
# meta twitter:player
'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
'info_dict': {
'id': '0_01b42zps',
'ext': 'mp4',
'title': 'Main Twerk (Video)',
'upload_date': '20171208',
'uploader_id': 'sebastian.salinas@thechive.com',
'timestamp': 1512713057,
},
'params': {
'skip_download': True,
},
'add_ie': ['Kaltura'],
},
# referrer protected EaglePlatform embed
{
'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
'info_dict': {
'id': '582306',
'ext': 'mp4',
'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 3382,
'view_count': int,
},
'params': {
'skip_download': True,
},
},
# ClipYou (EaglePlatform) embed (custom URL)
{
'url': 'http://muz-tv.ru/play/7129/',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
'info_dict': {
'id': '12820',
'ext': 'mp4',
'title': "'O Sole Mio",
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 216,
'view_count': int,
},
'params': {
'skip_download': True,
},
'skip': 'This video is unavailable.',
},
# Pladform embed
{
'url': 'http://muz-tv.ru/kinozal/view/7400/',
'info_dict': {
'id': '100183293',
'ext': 'mp4',
'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 694,
'age_limit': 0,
},
'skip': 'HTTP Error 404: Not Found',
},
# Playwire embed
{
'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
'info_dict': {
'id': '3519514',
'ext': 'mp4',
'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
'thumbnail': r're:^https?://.*\.png$',
'duration': 45.115,
},
},
# 5min embed
{
'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
'info_dict': {
'id': '518726732',
'ext': 'mp4',
'title': 'Facebook Creates "On This Day" | Crunch Report',
'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
'timestamp': 1427237531,
'uploader': 'Crunch Report',
'upload_date': '20150324',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
# Crooks and Liars embed
{
'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
'info_dict': {
'id': '8RUoRhRi',
'ext': 'mp4',
'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
},
},
# Crooks and Liars external embed
{
'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
'info_dict': {
'id': 'MTE3MjUtMzQ2MzA',
'ext': 'mp4',
'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
'timestamp': 1265032391,
'upload_date': '20100201',
'uploader': 'Heather',
},
},
# NBC Sports vplayer embed
{
'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
'info_dict': {
'id': 'ln7x1qSThw4k',
'ext': 'flv',
'title': "PFT Live: New leader in the 'new-look' defense",
'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
'uploader': 'NBCU-SPORTS',
'upload_date': '20140107',
'timestamp': 1389118457,
},
'skip': 'Invalid Page URL',
},
# NBC News embed
{
'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
'md5': '1aa589c675898ae6d37a17913cf68d66',
'info_dict': {
'id': 'x_dtl_oa_LettermanliftPR_160608',
'ext': 'mp4',
'title': 'David Letterman: A Preview',
'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
'upload_date': '20160609',
'timestamp': 1465431544,
'uploader': 'NBCU-NEWS',
},
},
# UDN embed
{
'url': 'https://video.udn.com/news/300346',
'md5': 'fd2060e988c326991037b9aff9df21a6',
'info_dict': {
'id': '300346',
'ext': 'mp4',
'title': '中一中男師變性 全校師生力挺',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Failed to parse JSON Expecting value'],
},
# Brightcove URL in single quotes
{
'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
'md5': '4ae374f1f8b91c889c4b9203c8c752af',
'info_dict': {
'id': '4255764656001',
'ext': 'mp4',
'title': 'SN Presents: Russell Martin, World Citizen',
'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
'uploader': 'Rogers Sportsnet',
'uploader_id': '1704050871',
'upload_date': '20150525',
'timestamp': 1432570283,
},
},
# Kinja embed
{
'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
'info_dict': {
'id': '106351',
'ext': 'mp4',
'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
'description': 'Migrated from OnionStudios',
'thumbnail': r're:^https?://.*\.jpe?g$',
'uploader': 'clickhole',
'upload_date': '20150527',
'timestamp': 1432744860,
}
},
# SnagFilms embed
{
'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
'info_dict': {
'id': '74849a00-85a9-11e1-9660-123139220831',
'ext': 'mp4',
'title': '#whilewewatch',
}
},
# AdobeTVVideo embed
{
'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
'md5': '43662b577c018ad707a63766462b1e87',
'info_dict': {
'id': '2456',
'ext': 'mp4',
'title': 'New experience with Acrobat DC',
'description': 'New experience with Acrobat DC',
'duration': 248.667,
},
},
# 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,
},
},
# Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
# This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
{
'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
'info_dict': {
'id': '4785848093001',
'ext': 'mp4',
'title': 'The Cardinal Pell Interview',
'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
'uploader': 'GlobeCast Australia - GlobeStream',
'uploader_id': '2733773828001',
'upload_date': '20160304',
'timestamp': 1457083087,
},
'params': {
# m3u8 downloads
'skip_download': True,
},
},
{
# Brightcove embed with whitespace around attribute names
'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
'info_dict': {
'id': '3167554373001',
'ext': 'mp4',
'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
'description': 'md5:57bacb0e0f29349de4972bfda3191713',
'uploader_id': '1079349493',
'upload_date': '20140207',
'timestamp': 1391810548,
},
'params': {
'skip_download': True,
},
},
# Another form of arte.tv embed
{
'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
'md5': '850bfe45417ddf221288c88a0cffe2e2',
'info_dict': {
'id': '030273-562_PLUS7-F',
'ext': 'mp4',
'title': 'ARTE Reportage - Nulle part, en France',
'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
'upload_date': '20160409',
},
},
# LiveLeak embed
{
'url': 'http://www.wykop.pl/link/3088787/',
'md5': '7619da8c820e835bef21a1efa2a0fc71',
'info_dict': {
'id': '874_1459135191',
'ext': 'mp4',
'title': 'Man shows poor quality of new apartment building',
'description': 'The wall is like a sand pile.',
'uploader': 'Lake8737',
},
'add_ie': [LiveLeakIE.ie_key()],
},
# Another LiveLeak embed pattern (#13336)
{
'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
'info_dict': {
'id': '2eb_1496309988',
'ext': 'mp4',
'title': 'Thief robs place where everyone was armed',
'description': 'md5:694d73ee79e535953cf2488562288eee',
'uploader': 'brazilwtf',
},
'add_ie': [LiveLeakIE.ie_key()],
},
# Duplicated embedded video URLs
{
'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
'info_dict': {
'id': '149298443_480_16c25b74_2',
'ext': 'mp4',
'title': 'vs. Blue Orange Spring Game',
'uploader': 'www.hudl.com',
},
},
# twitter:player:stream embed
{
'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
'info_dict': {
'id': 'master',
'ext': 'mp4',
'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
'uploader': 'www.rtl.be',
},
'params': {
# m3u8 downloads
'skip_download': True,
},
},
# twitter:player embed
{
'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
'md5': 'a3e0df96369831de324f0778e126653c',
'info_dict': {
'id': '4909620399001',
'ext': 'mp4',
'title': 'What Do Black Holes Sound Like?',
'description': 'what do black holes sound like',
'upload_date': '20160524',
'uploader_id': '29913724001',
'timestamp': 1464107587,
'uploader': 'TheAtlantic',
},
'add_ie': ['BrightcoveLegacy'],
},
# Facebook <iframe> embed
{
'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
'md5': 'fbcde74f534176ecb015849146dd3aee',
'info_dict': {
'id': '599637780109885',
'ext': 'mp4',
'title': 'Facebook video #599637780109885',
},
},
# Facebook <iframe> embed, plugin video
{
'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
'info_dict': {
'id': '1754168231264132',
'ext': 'mp4',
'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
'uploader': 'Tariq Ramadan (official)',
'timestamp': 1496758379,
'upload_date': '20170606',
},
'params': {
'skip_download': True,
},
},
# Facebook API embed
{
'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
'md5': 'a47372ee61b39a7b90287094d447d94e',
'info_dict': {
'id': '10153467542406923',
'ext': 'mp4',
'title': 'Facebook video #10153467542406923',
},
},
# Wordpress "YouTube Video Importer" plugin
{
'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
'md5': 'd16797741b560b485194eddda8121b48',
'info_dict': {
'id': 'HNTXWDXV9Is',
'ext': 'mp4',
'title': 'Blue Devils Drumline Stanford lot 2016',
'upload_date': '20160627',
'uploader_id': 'GENOCIDE8GENERAL10',
'uploader': 'cylus cyrus',
},
},
{
# video stored on custom kaltura server
'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
'md5': '537617d06e64dfed891fa1593c4b30cc',
'info_dict': {
'id': '0_1iotm5bh',
'ext': 'mp4',
'title': 'Elecciones británicas: 5 lecciones para Rajoy',
'description': 'md5:435a89d68b9760b92ce67ed227055f16',
'uploader_id': 'videos.expansion@el-mundo.net',
'upload_date': '20150429',
'timestamp': 1430303472,
},
'add_ie': ['Kaltura'],
},
{
# multiple kaltura embeds, nsfw
'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
'info_dict': {
'id': 'kamila-avec-video-jaime-sadomie',
'title': "Kamila avec vídeo “J'aime sadomie”",
},
'playlist_count': 8,
},
{
# Non-standard Vimeo embed
'url': 'https://openclassrooms.com/courses/understanding-the-web',
'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
'info_dict': {
'id': '148867247',
'ext': 'mp4',
'title': 'Understanding the web - Teaser',
'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
'upload_date': '20151214',
'uploader': 'OpenClassrooms',
'uploader_id': 'openclassrooms',
},
'add_ie': ['Vimeo'],
},
{
# generic vimeo embed that requires original URL passed as Referer
'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
'only_matching': True,
},
{
'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
'info_dict': {
'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
'ext': 'mp4',
'title': 'Big Buck Bunny',
'description': 'Royalty free test video',
'timestamp': 1432816365,
'upload_date': '20150528',
'is_live': False,
},
'params': {
'skip_download': True,
},
'add_ie': [ArkenaIE.ie_key()],
},
{
'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
'info_dict': {
'id': '1c7141f46c',
'ext': 'mp4',
'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
},
'params': {
'skip_download': True,
},
'add_ie': [Vbox7IE.ie_key()],
},
{
# DBTV embeds
'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
'info_dict': {
'id': '43254897',
'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
},
'playlist_mincount': 3,
},
{
# Videa embeds
'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
'info_dict': {
'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
},
'playlist_mincount': 2,
},
{
# 20 minuten embed
'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
'info_dict': {
'id': '523629',
'ext': 'mp4',
'title': 'So kommen Sie bei Eis und Schnee sicher an',
'description': 'md5:117c212f64b25e3d95747e5276863f7d',
},
'params': {
'skip_download': True,
},
'add_ie': [TwentyMinutenIE.ie_key()],
},
{
# VideoPress embed
'url': 'https://en.support.wordpress.com/videopress/',
'info_dict': {
'id': 'OcobLTqC',
'ext': 'm4v',
'title': 'IMG_5786',
'timestamp': 1435711927,
'upload_date': '20150701',
},
'params': {
'skip_download': True,
},
'add_ie': [VideoPressIE.ie_key()],
},
{
# Rutube embed
'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
'info_dict': {
'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
'ext': 'flv',
'title': 'Магаззино: Казань 2',
'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
'uploader': 'Магаззино',
'upload_date': '20170228',
'uploader_id': '996642',
},
'params': {
'skip_download': True,
},
'add_ie': [RutubeIE.ie_key()],
},
{
# ThePlatform embedded with whitespaces in URLs
'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
'only_matching': True,
},
{
# Senate ISVP iframe https
'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
'md5': 'fb8c70b0b515e5037981a2492099aab8',
'info_dict': {
'id': 'govtaff020316',
'ext': 'mp4',
'title': 'Integrated Senate Video Player',
},
'add_ie': [SenateISVPIE.ie_key()],
},
{
# Limelight embeds (1 channel embed + 4 media embeds)
'url': 'http://www.sedona.com/FacilitatorTraining2017',
'info_dict': {
'id': 'FacilitatorTraining2017',
'title': 'Facilitator Training 2017',
},
'playlist_mincount': 5,
},
{
# Limelight embed (LimelightPlayerUtil.embed)
'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
'info_dict': {
'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
'ext': 'mp4',
'title': '07448641',
'timestamp': 1499890639,
'upload_date': '20170712',
},
'params': {
'skip_download': True,
},
'add_ie': ['LimelightMedia'],
},
{
'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
'info_dict': {
'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
'title': 'Standoff with Walnut Creek murder suspect ends',
'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
},
'playlist_mincount': 4,
},
{
# WashingtonPost embed
'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
'info_dict': {
'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
'ext': 'mp4',
'title': "No one has seen the drama series based on Trump's life \u2014 until now",
'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
'timestamp': 1455216756,
'uploader': 'The Washington Post',
'upload_date': '20160211',
},
'add_ie': [WashingtonPostIE.ie_key()],
},
{
# Mediaset embed
'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
'info_dict': {
'id': '720642',
'ext': 'mp4',
'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
},
'params': {
'skip_download': True,
},
'add_ie': [MediasetIE.ie_key()],
},
{
# JOJ.sk embeds
'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
'info_dict': {
'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
'title': 'Slovenskom sa prehnala vlna silných búrok',
},
'playlist_mincount': 5,
'add_ie': [JojIE.ie_key()],
},
{
# AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
'url': 'https://tvrain.ru/amp/418921/',
'md5': 'cc00413936695987e8de148b67d14f1d',
'info_dict': {
'id': '418921',
'ext': 'mp4',
'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
},
},
{
# vzaar embed
'url': 'http://help.vzaar.com/article/165-embedding-video',
'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
'info_dict': {
'id': '8707641',
'ext': 'mp4',
'title': 'Building A Business Online: Principal Chairs Q & A',
},
},
{
# multiple HTML5 videos on one page
'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
'info_dict': {
'id': 'keyscenarios',
'title': 'Rescue Kit 14 Free Edition - Getting started',
},
'playlist_count': 4,
},
{
# vshare embed
'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
'md5': '17b39f55b5497ae8b59f5fbce8e35886',
'info_dict': {
'id': '0f64ce6',
'title': 'vl14062007715967',
'ext': 'mp4',
}
},
{
'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
'md5': 'aecd089f55b1cb5a59032cb049d3a356',
'info_dict': {
'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
'ext': 'mp4',
'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
'timestamp': 1474354800,
'upload_date': '20160920',
}
},
{
'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
'info_dict': {
'id': '1731611',
'ext': 'mp4',
'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
'description': 'md5:eb5f23826a027ba95277d105f248b825',
'timestamp': 1516100691,
'upload_date': '20180116',
},
'params': {
'skip_download': True,
},
'add_ie': [SpringboardPlatformIE.ie_key()],
},
{
'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
'info_dict': {
'id': 'uPDB5I9wfp8',
'ext': 'webm',
'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
'upload_date': '20160219',
'uploader': 'Pocoyo - Português (BR)',
'uploader_id': 'PocoyoBrazil',
},
'add_ie': [YoutubeIE.ie_key()],
'params': {
'skip_download': True,
},
},
{
'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
'info_dict': {
'id': 'vMDE4NzI1Mjgt690b',
'ext': 'mp4',
'title': 'Котята',
},
'add_ie': [YapFilesIE.ie_key()],
'params': {
'skip_download': True,
},
},
{
# CloudflareStream embed
'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
'info_dict': {
'id': '31c9291ab41fac05471db4e73aa11717',
'ext': 'mp4',
'title': '31c9291ab41fac05471db4e73aa11717',
},
'add_ie': [CloudflareStreamIE.ie_key()],
'params': {
'skip_download': True,
},
},
{
# PeerTube embed
'url': 'https://joinpeertube.org/fr/home/',
'info_dict': {
'id': 'home',
'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
},
'playlist_count': 2,
},
{
# Indavideo embed
'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
'info_dict': {
'id': '1693903',
'ext': 'mp4',
'title': 'Így kell otthon hamburgert sütni',
'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
'timestamp': 1426330212,
'upload_date': '20150314',
'uploader': 'StreetKitchen',
'uploader_id': '546363',
},
'add_ie': [IndavideoEmbedIE.ie_key()],
'params': {
'skip_download': True,
},
},
{
# APA embed via JWPlatform embed
'url': 'http://www.vol.at/blue-man-group/5593454',
'info_dict': {
'id': 'jjv85FdZ',
'ext': 'mp4',
'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 254,
'timestamp': 1519211149,
'upload_date': '20180221',
},
'params': {
'skip_download': True,
},
},
{
'url': 'http://share-videos.se/auto/video/83645793?uid=13',
'md5': 'b68d276de422ab07ee1d49388103f457',
'info_dict': {
'id': '83645793',
'title': 'Lock up and get excited',
'ext': 'mp4'
},
'skip': 'TODO: fix nested playlists processing in tests',
},
{
# Viqeo embeds
'url': 'https://viqeo.tv/',
'info_dict': {
'id': 'viqeo',
'title': 'All-new video platform',
},
'playlist_count': 6,
},
{
# Squarespace video embed, 2019-08-28
'url': 'http://ootboxford.com',
'info_dict': {
'id': 'Tc7b_JGdZfw',
'title': 'Out of the Blue, at Childish Things 10',
'ext': 'mp4',
'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
'uploader_id': 'helendouglashouse',
'uploader': 'Helen & Douglas House',
'upload_date': '20140328',
},
'params': {
'skip_download': True,
},
},
{
# Zype embed
'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
'info_dict': {
'id': '5b400b834b32992a310622b9',
'ext': 'mp4',
'title': 'Smoky Barbecue Favorites',
'thumbnail': r're:^https?://.*\.jpe?g',
'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
'upload_date': '20170909',
'timestamp': 1504915200,
},
'add_ie': [ZypeIE.ie_key()],
'params': {
'skip_download': True,
},
},
{
# videojs embed
'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
'info_dict': {
'id': 'shell',
'ext': 'mp4',
'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Failed to download MPD manifest'],
},
{
# DailyMotion embed with DM.player
'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
'info_dict': {
'id': 'k6aKkGHd9FJs4mtJN39',
'ext': 'mp4',
'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
'description': 'This video is private.',
'uploader_id': 'x1jf30l',
'uploader': 'beIN SPORTS USA',
'upload_date': '20190528',
'timestamp': 1559062971,
},
'params': {
'skip_download': True,
},
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
# 'url': 'https://flipagram.com/f/nyvTSJMKId',
# 'md5': '888dcf08b7ea671381f00fab74692755',
# 'info_dict': {
# 'id': 'nyvTSJMKId',
# 'ext': 'mp4',
# 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
# 'description': '#love for cats.',
# 'timestamp': 1461244995,
# 'upload_date': '20160421',
# },
# 'params': {
# 'force_generic_extractor': True,
# },
# }
]
def report_following_redirect(self, new_url):
"""Report information extraction."""
self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
def _extract_rss(self, url, video_id, doc):
playlist_title = doc.find('./channel/title').text
playlist_desc_el = doc.find('./channel/description')
playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
entries = []
for it in doc.findall('./channel/item'):
next_url = None
enclosure_nodes = it.findall('./enclosure')
for e in enclosure_nodes:
next_url = e.attrib.get('url')
if next_url:
break
if not next_url:
next_url = xpath_text(it, 'link', fatal=False)
if not next_url:
continue
entries.append({
'_type': 'url_transparent',
'url': next_url,
'title': it.find('title').text,
})
return {
'_type': 'playlist',
'id': url,
'title': playlist_title,
'description': playlist_desc,
'entries': entries,
}
def _extract_camtasia(self, url, video_id, webpage):
""" Returns None if no camtasia video can be found. """
camtasia_cfg = self._search_regex(
r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
webpage, 'camtasia configuration file', default=None)
if camtasia_cfg is None:
return None
title = self._html_search_meta('DC.title', webpage, fatal=True)
camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
camtasia_cfg = self._download_xml(
camtasia_url, video_id,
note='Downloading camtasia configuration',
errnote='Failed to download camtasia configuration')
fileset_node = camtasia_cfg.find('./playlist/array/fileset')
entries = []
for n in fileset_node.getchildren():
url_n = n.find('./uri')
if url_n is None:
continue
entries.append({
'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
'title': '%s - %s' % (title, n.tag),
'url': compat_urlparse.urljoin(url, url_n.text),
'duration': float_or_none(n.find('./duration').text),
})
return {
'_type': 'playlist',
'entries': entries,
'title': title,
}
def _real_extract(self, url):
if url.startswith('//'):
return self.url_result(self.http_scheme() + url)
parsed_url = compat_urlparse.urlparse(url)
if not parsed_url.scheme:
default_search = self._downloader.params.get('default_search')
if default_search is None:
default_search = 'fixup_error'
if default_search in ('auto', 'auto_warning', 'fixup_error'):
if re.match(r'^[^\s/]+\.[^\s/]+/', url):
self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
return self.url_result('http://' + url)
elif default_search != 'fixup_error':
if default_search == 'auto_warning':
if re.match(r'^(?:url|URL)$', url):
raise ExtractorError(
'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
expected=True)
else:
self._downloader.report_warning(
'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
return self.url_result('ytsearch:' + url)
if default_search in ('error', 'fixup_error'):
raise ExtractorError(
'%r is not a valid URL. '
'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
% (url, url), expected=True)
else:
if ':' not in default_search:
default_search += ':'
return self.url_result(default_search + url)
url, smuggled_data = unsmuggle_url(url)
force_videoid = None
is_intentional = smuggled_data and smuggled_data.get('to_generic')
if smuggled_data and 'force_videoid' in smuggled_data:
force_videoid = smuggled_data['force_videoid']
video_id = force_videoid
else:
video_id = self._generic_id(url)
self.to_screen('%s: Requesting header' % video_id)
head_req = HEADRequest(url)
head_response = self._request_webpage(
head_req, video_id,
note=False, errnote='Could not send HEAD request to %s' % url,
fatal=False)
if head_response is not False:
# Check for redirect
new_url = head_response.geturl()
if url != new_url:
self.report_following_redirect(new_url)
if force_videoid:
new_url = smuggle_url(
new_url, {'force_videoid': force_videoid})
return self.url_result(new_url)
full_response = None
if head_response is False:
request = sanitized_Request(url)
request.add_header('Accept-Encoding', '*')
full_response = self._request_webpage(request, video_id)
head_response = full_response
info_dict = {
'id': video_id,
'title': self._generic_title(url),
'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
}
# Check for direct link to a video
content_type = head_response.headers.get('Content-Type', '').lower()
m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
if m:
format_id = compat_str(m.group('format_id'))
if format_id.endswith('mpegurl'):
formats = self._extract_m3u8_formats(url, video_id, 'mp4')
elif format_id == 'f4m':
formats = self._extract_f4m_formats(url, video_id)
else:
formats = [{
'format_id': format_id,
'url': url,
'vcodec': 'none' if m.group('type') == 'audio' else None
}]
info_dict['direct'] = True
self._sort_formats(formats)
info_dict['formats'] = formats
return info_dict
if not self._downloader.params.get('test', False) and not is_intentional:
force = self._downloader.params.get('force_generic_extractor', False)
self._downloader.report_warning(
'%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
if not full_response:
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
# that will always result in downloading the whole file that is not desirable.
# Therefore for extraction pass we have to override Accept-Encoding to any in order
# to accept raw bytes and being able to download only a chunk.
# It may probably better to solve this by checking Content-Type for application/octet-stream
# after HEAD request finishes, but not sure if we can rely on this.
request.add_header('Accept-Encoding', '*')
full_response = self._request_webpage(request, video_id)
first_bytes = full_response.read(512)
# Is it an M3U playlist?
if first_bytes.startswith(b'#EXTM3U'):
info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
self._sort_formats(info_dict['formats'])
return info_dict
# Maybe it's a direct link to a video?
# Be careful not to download the whole thing!
if not is_html(first_bytes):
self._downloader.report_warning(
'URL could be a direct video link, returning it as such.')
info_dict.update({
'direct': True,
'url': url,
})
return info_dict
webpage = self._webpage_read_content(
full_response, url, video_id, prefix=first_bytes)
self.report_extraction(video_id)
# Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
try:
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
elif doc.tag == 'SmoothStreamingMedia':
info_dict['formats'] = self._parse_ism_formats(doc, url)
self._sort_formats(info_dict['formats'])
return info_dict
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
smil = self._parse_smil(doc, url, video_id)
self._sort_formats(smil['formats'])
return smil
elif doc.tag == '{http://xspf.org/ns/0/}playlist':
return self.playlist_result(
self._parse_xspf(
doc, video_id, xspf_url=url,
xspf_base_url=full_response.geturl()),
video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc,
mpd_base_url=full_response.geturl().rpartition('/')[0],
mpd_url=url)
self._sort_formats(info_dict['formats'])
return info_dict
elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
self._sort_formats(info_dict['formats'])
return info_dict
except compat_xml_parse_error:
pass
# Is it a Camtasia project?
camtasia_res = self._extract_camtasia(url, video_id, webpage)
if camtasia_res is not None:
return camtasia_res
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way
webpage = compat_urllib_parse_unquote(webpage)
# Unescape squarespace embeds to be detected by generic extractor,
# see https://github.com/ytdl-org/youtube-dl/issues/21294
webpage = re.sub(
r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
lambda x: unescapeHTML(x.group(0)), webpage)
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
video_title = self._og_search_title(
webpage, default=None) or self._html_search_regex(
r'(?s)<title>(.*?)</title>', webpage, 'video title',
default='video')
# Try to detect age limit automatically
age_limit = self._rta_search(webpage)
# And then there are the jokers who advertise that they use RTA,
# but actually don't.
AGE_LIMIT_MARKERS = [
r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
]
if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
age_limit = 18
# video uploader is domain name
video_uploader = self._search_regex(
r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
video_description = self._og_search_description(webpage, default=None)
video_thumbnail = self._og_search_thumbnail(webpage, default=None)
info_dict.update({
'title': video_title,
'description': video_description,
'thumbnail': video_thumbnail,
'age_limit': age_limit,
})
# Look for Brightcove Legacy Studio embeds
bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
entries = [{
'_type': 'url',
'url': smuggle_url(bc_url, {'Referer': url}),
'ie_key': 'BrightcoveLegacy'
} for bc_url in bc_urls]
return {
'_type': 'playlist',
'title': video_title,
'id': video_id,
'entries': entries,
}
# Look for Brightcove New Studio embeds
bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
if bc_urls:
return self.playlist_from_matches(
bc_urls, video_id, video_title,
getter=lambda x: smuggle_url(x, {'referrer': url}),
ie='BrightcoveNew')
# Look for Nexx embeds
nexx_urls = NexxIE._extract_urls(webpage)
if nexx_urls:
return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
# Look for Nexx iFrame embeds
nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
if nexx_embed_urls:
return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
# Look for ThePlatform embeds
tp_urls = ThePlatformIE._extract_urls(webpage)
if tp_urls:
return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
# Look for embedded rtl.nl player
matches = re.findall(
r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
webpage)
if matches:
return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
vimeo_urls = VimeoIE._extract_urls(url, webpage)
if vimeo_urls:
return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
vid_me_embed_url = self._search_regex(
r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
webpage, 'vid.me embed', default=None)
if vid_me_embed_url is not None:
return self.url_result(vid_me_embed_url, 'Vidme')
# Look for YouTube embeds
youtube_urls = YoutubeIE._extract_urls(webpage)
if youtube_urls:
return self.playlist_from_matches(
youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
matches = DailymotionIE._extract_urls(webpage)
if matches:
return self.playlist_from_matches(matches, video_id, video_title)
# Look for embedded Dailymotion playlist player (#3822)
m = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
if m:
playlists = re.findall(
r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
if playlists:
return self.playlist_from_matches(
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
# Look for DailyMail embeds
dailymail_urls = DailyMailIE._extract_urls(webpage)
if dailymail_urls:
return self.playlist_from_matches(
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
# Look for Teachable embeds, must be before Wistia
teachable_url = TeachableIE._extract_url(webpage, url)
if teachable_url:
return self.url_result(teachable_url)
# Look for embedded Wistia player
wistia_urls = WistiaIE._extract_urls(webpage)
if wistia_urls:
playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
for entry in playlist['entries']:
entry.update({
'_type': 'url_transparent',
'uploader': video_uploader,
})
return playlist
# Look for SVT player
svt_url = SVTIE._extract_url(webpage)
if svt_url:
return self.url_result(svt_url, 'SVT')
# Look for Bandcamp pages with custom domain
mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
if mobj is not None:
burl = unescapeHTML(mobj.group(1))
# Don't set the extractor because it can be a track url or an album
return self.url_result(burl)
# Look for embedded Vevo player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for embedded Viddler player
mobj = re.search(
r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for NYTimes player
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for Libsyn player
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for Ooyala videos
mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
if mobj is not None:
embed_token = self._search_regex(
r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
webpage, 'ooyala embed token', default=None)
return OoyalaIE._build_url_result(smuggle_url(
mobj.group('ec'), {
'domain': url,
'embed_token': embed_token,
}))
# Look for multiple Ooyala embeds on SBN network websites
mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
if mobj is not None:
embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
if embeds:
return self.playlist_from_matches(
embeds, video_id, video_title,
getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
# Look for Aparat videos
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
if mobj is not None:
return self.url_result(mobj.group(1), 'Aparat')
# Look for MPORA videos
mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
if mobj is not None:
return self.url_result(mobj.group(1), 'Mpora')
# Look for embedded Facebook player
facebook_urls = FacebookIE._extract_urls(webpage)
if facebook_urls:
return self.playlist_from_matches(facebook_urls, video_id, video_title)
# Look for embedded VK player
mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'VK')
# Look for embedded Odnoklassniki player
odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
if odnoklassniki_url:
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
# Look for embedded ivi player
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Ivi')
# Look for embedded Huffington Post player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'HuffPost')
# Look for embed.ly
mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
if mobj is not None:
return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
# Look for funnyordie embed
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
if matches:
return self.playlist_from_matches(
matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
# Look for BBC iPlayer embed
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
if matches:
return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
# Look for embedded RUTV player
rutv_url = RUTVIE._extract_url(webpage)
if rutv_url:
return self.url_result(rutv_url, 'RUTV')
# Look for embedded TVC player
tvc_url = TVCIE._extract_url(webpage)
if tvc_url:
return self.url_result(tvc_url, 'TVC')
# Look for embedded SportBox player
sportbox_urls = SportBoxIE._extract_urls(webpage)
if sportbox_urls:
return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
# Look for embedded XHamster player
xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
if xhamster_urls:
return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
# Look for embedded TNAFlixNetwork player
tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
if tnaflix_urls:
return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
# Look for embedded PornHub player
pornhub_urls = PornHubIE._extract_urls(webpage)
if pornhub_urls:
return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
# Look for embedded DrTuber player
drtuber_urls = DrTuberIE._extract_urls(webpage)
if drtuber_urls:
return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
# Look for embedded RedTube player
redtube_urls = RedTubeIE._extract_urls(webpage)
if redtube_urls:
return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
# Look for embedded Tube8 player
tube8_urls = Tube8IE._extract_urls(webpage)
if tube8_urls:
return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
# Look for embedded Mofosex player
mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
if mofosex_urls:
return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
# Look for embedded Spankwire player
spankwire_urls = SpankwireIE._extract_urls(webpage)
if spankwire_urls:
return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
# Look for embedded YouPorn player
youporn_urls = YouPornIE._extract_urls(webpage)
if youporn_urls:
return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
# Look for embedded Tvigle player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Tvigle')
# Look for embedded TED player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'TED')
# Look for embedded Ustream videos
ustream_url = UstreamIE._extract_url(webpage)
if ustream_url:
return self.url_result(ustream_url, UstreamIE.ie_key())
# Look for embedded arte.tv player
mobj = re.search(
r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'ArteTVEmbed')
# Look for embedded francetv player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for embedded smotri.com player
smotri_url = SmotriIE._extract_url(webpage)
if smotri_url:
return self.url_result(smotri_url, 'Smotri')
# Look for embedded Myvi.ru player
myvi_url = MyviIE._extract_url(webpage)
if myvi_url:
return self.url_result(myvi_url)
# Look for embedded soundcloud player
soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
if soundcloud_urls:
return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
# Look for tunein player
tunein_urls = TuneInBaseIE._extract_urls(webpage)
if tunein_urls:
return self.playlist_from_matches(tunein_urls, video_id, video_title)
# Look for embedded mtvservices player
mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
if mtvservices_url:
return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
# Look for embedded yahoo player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Yahoo')
# Look for embedded sbs.com.au player
mobj = re.search(
r'''(?x)
(?:
<meta\s+property="og:video"\s+content=|
<iframe[^>]+?src=
)
(["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'SBS')
# Look for embedded Cinchcast player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Cinchcast')
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
webpage)
if not mobj:
mobj = re.search(
r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'MLB')
mobj = re.search(
r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
webpage)
if mobj is not None:
return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
mobj = re.search(
r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Livestream')
# Look for Zapiks embed
mobj = re.search(
r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Zapiks')
# Look for Kaltura embeds
kaltura_urls = KalturaIE._extract_urls(webpage)
if kaltura_urls:
return self.playlist_from_matches(
kaltura_urls, video_id, video_title,
getter=lambda x: smuggle_url(x, {'source_url': url}),
ie=KalturaIE.ie_key())
# Look for EaglePlatform embeds
eagleplatform_url = EaglePlatformIE._extract_url(webpage)
if eagleplatform_url:
return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
# Look for ClipYou (uses EaglePlatform) embeds
mobj = re.search(
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
if mobj is not None:
return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
# Look for Pladform embeds
pladform_url = PladformIE._extract_url(webpage)
if pladform_url:
return self.url_result(pladform_url)
# Look for Videomore embeds
videomore_url = VideomoreIE._extract_url(webpage)
if videomore_url:
return self.url_result(videomore_url)
# Look for Webcaster embeds
webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
if webcaster_url:
return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
# Look for Playwire embeds
mobj = re.search(
r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for 5min embeds
mobj = re.search(
r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
if mobj is not None:
return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
# Look for Crooks and Liars embeds
mobj = re.search(
r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for NBC Sports VPlayer embeds
nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
if nbc_sports_url:
return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
# Look for NBC News embeds
nbc_news_embed_url = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
if nbc_news_embed_url:
return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
# Look for Google Drive embeds
google_drive_url = GoogleDriveIE._extract_url(webpage)
if google_drive_url:
return self.url_result(google_drive_url, 'GoogleDrive')
# Look for UDN embeds
mobj = re.search(
r'<iframe[^>]+src="(?:https?:)?(?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')
# Look for Senate ISVP iframe
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
return self.url_result(senate_isvp_url, 'SenateISVP')
# Look for Kinja embeds
kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
if kinja_embed_urls:
return self.playlist_from_matches(
kinja_embed_urls, video_id, video_title)
# Look for OnionStudios embeds
onionstudios_url = OnionStudiosIE._extract_url(webpage)
if onionstudios_url:
return self.url_result(onionstudios_url)
# Look for ViewLift embeds
viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
if viewlift_url:
return self.url_result(viewlift_url)
# Look for JWPlatform embeds
jwplatform_urls = JWPlatformIE._extract_urls(webpage)
if jwplatform_urls:
return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
# Look for Digiteka embeds
digiteka_url = DigitekaIE._extract_url(webpage)
if digiteka_url:
return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
# Look for Arkena embeds
arkena_url = ArkenaIE._extract_url(webpage)
if arkena_url:
return self.url_result(arkena_url, ArkenaIE.ie_key())
# Look for Piksel embeds
piksel_url = PikselIE._extract_url(webpage)
if piksel_url:
return self.url_result(piksel_url, PikselIE.ie_key())
# Look for Limelight embeds
limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
if limelight_urls:
return self.playlist_result(
limelight_urls, video_id, video_title, video_description)
# Look for Anvato embeds
anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
if anvato_urls:
return self.playlist_result(
anvato_urls, video_id, video_title, video_description)
# Look for AdobeTVVideo embeds
mobj = re.search(
r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
webpage)
if mobj is not None:
return self.url_result(
self._proto_relative_url(unescapeHTML(mobj.group(1))),
'AdobeTVVideo')
# Look for Vine embeds
mobj = re.search(
r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
webpage)
if mobj is not None:
return self.url_result(
self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
# Look for VODPlatform embeds
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
webpage)
if mobj is not None:
return self.url_result(
self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
# Look for Mangomolo embeds
mobj = re.search(
r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
(?:
admin\.mangomolo\.com/analytics/index\.php/customers/embed|
player\.mangomolo\.com/v1
)/
(?:
video\?.*?\bid=(?P<video_id>\d+)|
(?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
).+?)\1''', webpage)
if mobj is not None:
info = {
'_type': 'url_transparent',
'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
'title': video_title,
'description': video_description,
'thumbnail': video_thumbnail,
'uploader': video_uploader,
}
video_id = mobj.group('video_id')
if video_id:
info.update({
'ie_key': 'MangomoloVideo',
'id': video_id,
})
else:
info.update({
'ie_key': 'MangomoloLive',
'id': mobj.group('channel_id'),
})
return info
# Look for Instagram embeds
instagram_embed_url = InstagramIE._extract_embed_url(webpage)
if instagram_embed_url is not None:
return self.url_result(
self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
# Look for LiveLeak embeds
liveleak_urls = LiveLeakIE._extract_urls(webpage)
if liveleak_urls:
return self.playlist_from_matches(liveleak_urls, video_id, video_title)
# Look for 3Q SDN embeds
threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
if threeqsdn_url:
return {
'_type': 'url_transparent',
'ie_key': ThreeQSDNIE.ie_key(),
'url': self._proto_relative_url(threeqsdn_url),
'title': video_title,
'description': video_description,
'thumbnail': video_thumbnail,
'uploader': video_uploader,
}
# Look for VBOX7 embeds
vbox7_url = Vbox7IE._extract_url(webpage)
if vbox7_url:
return self.url_result(vbox7_url, Vbox7IE.ie_key())
# Look for DBTV embeds
dbtv_urls = DBTVIE._extract_urls(webpage)
if dbtv_urls:
return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
# Look for Videa embeds
videa_urls = VideaIE._extract_urls(webpage)
if videa_urls:
return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
# Look for 20 minuten embeds
twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
if twentymin_urls:
return self.playlist_from_matches(
twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
# Look for VideoPress embeds
videopress_urls = VideoPressIE._extract_urls(webpage)
if videopress_urls:
return self.playlist_from_matches(
videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
# Look for Rutube embeds
rutube_urls = RutubeIE._extract_urls(webpage)
if rutube_urls:
return self.playlist_from_matches(
rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
# Look for WashingtonPost embeds
wapo_urls = WashingtonPostIE._extract_urls(webpage)
if wapo_urls:
return self.playlist_from_matches(
wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
# Look for Mediaset embeds
mediaset_urls = MediasetIE._extract_urls(self, webpage)
if mediaset_urls:
return self.playlist_from_matches(
mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
# Look for JOJ.sk embeds
joj_urls = JojIE._extract_urls(webpage)
if joj_urls:
return self.playlist_from_matches(
joj_urls, video_id, video_title, ie=JojIE.ie_key())
# Look for megaphone.fm embeds
mpfn_urls = MegaphoneIE._extract_urls(webpage)
if mpfn_urls:
return self.playlist_from_matches(
mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
# Look for vzaar embeds
vzaar_urls = VzaarIE._extract_urls(webpage)
if vzaar_urls:
return self.playlist_from_matches(
vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
channel9_urls = Channel9IE._extract_urls(webpage)
if channel9_urls:
return self.playlist_from_matches(
channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
vshare_urls = VShareIE._extract_urls(webpage)
if vshare_urls:
return self.playlist_from_matches(
vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
# Look for Mediasite embeds
mediasite_urls = MediasiteIE._extract_urls(webpage)
if mediasite_urls:
entries = [
self.url_result(smuggle_url(
compat_urlparse.urljoin(url, mediasite_url),
{'UrlReferrer': url}), ie=MediasiteIE.ie_key())
for mediasite_url in mediasite_urls]
return self.playlist_result(entries, video_id, video_title)
springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
if springboardplatform_urls:
return self.playlist_from_matches(
springboardplatform_urls, video_id, video_title,
ie=SpringboardPlatformIE.ie_key())
yapfiles_urls = YapFilesIE._extract_urls(webpage)
if yapfiles_urls:
return self.playlist_from_matches(
yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
vice_urls = ViceIE._extract_urls(webpage)
if vice_urls:
return self.playlist_from_matches(
vice_urls, video_id, video_title, ie=ViceIE.ie_key())
xfileshare_urls = XFileShareIE._extract_urls(webpage)
if xfileshare_urls:
return self.playlist_from_matches(
xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
if cloudflarestream_urls:
return self.playlist_from_matches(
cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
peertube_urls = PeerTubeIE._extract_urls(webpage, url)
if peertube_urls:
return self.playlist_from_matches(
peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
if indavideo_urls:
return self.playlist_from_matches(
indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
apa_urls = APAIE._extract_urls(webpage)
if apa_urls:
return self.playlist_from_matches(
apa_urls, video_id, video_title, ie=APAIE.ie_key())
foxnews_urls = FoxNewsIE._extract_urls(webpage)
if foxnews_urls:
return self.playlist_from_matches(
foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
webpage)]
if sharevideos_urls:
return self.playlist_from_matches(
sharevideos_urls, video_id, video_title)
viqeo_urls = ViqeoIE._extract_urls(webpage)
if viqeo_urls:
return self.playlist_from_matches(
viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
expressen_urls = ExpressenIE._extract_urls(webpage)
if expressen_urls:
return self.playlist_from_matches(
expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
zype_urls = ZypeIE._extract_urls(webpage)
if zype_urls:
return self.playlist_from_matches(
zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
# Look for HTML5 media
entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
if entries:
if len(entries) == 1:
entries[0].update({
'id': video_id,
'title': video_title,
})
else:
for num, entry in enumerate(entries, start=1):
entry.update({
'id': '%s-%s' % (video_id, num),
'title': '%s (%d)' % (video_title, num),
})
for entry in entries:
self._sort_formats(entry['formats'])
return self.playlist_result(entries, video_id, video_title)
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
if jwplayer_data:
try:
info = self._parse_jwplayer_data(
jwplayer_data, video_id, require_title=False, base_url=url)
return merge_dicts(info, info_dict)
except ExtractorError:
# See https://github.com/ytdl-org/youtube-dl/pull/16735
pass
# Video.js embed
mobj = re.search(
r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
webpage)
if mobj is not None:
sources = self._parse_json(
mobj.group(1), video_id, transform_source=js_to_json,
fatal=False) or []
if not isinstance(sources, list):
sources = [sources]
formats = []
for source in sources:
src = source.get('src')
if not src or not isinstance(src, compat_str):
continue
src = compat_urlparse.urljoin(url, src)
src_type = source.get('type')
if isinstance(src_type, compat_str):
src_type = src_type.lower()
ext = determine_ext(src).lower()
if src_type == 'video/youtube':
return self.url_result(src, YoutubeIE.ie_key())
if src_type == 'application/dash+xml' or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
src, video_id, mpd_id='dash', fatal=False))
elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
src, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': src,
'ext': (mimetype2ext(src_type)
or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
})
if formats:
self._sort_formats(formats)
info_dict['formats'] = formats
return info_dict
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')
if json_ld.get('url'):
return merge_dicts(json_ld, info_dict)
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
if RtmpIE.suitable(vurl):
return True
vpath = compat_urlparse.urlparse(vurl).path
vext = determine_ext(vpath)
return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
def filter_video(urls):
return list(filter(check_video, urls))
# Start with something easy: JW Player in SWFObject
found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
if not found:
# Look for gorilla-vid style embedding
found = filter_video(re.findall(r'''(?sx)
(?:
jw_plugins|
JWPlayerOptions|
jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
)
.*?
['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
if not found:
# Broaden the search a little bit
found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
if not found:
# Broaden the findall a little bit: JWPlayer JS loader
found = filter_video(re.findall(
r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
if not found:
# Flow player
found = filter_video(re.findall(r'''(?xs)
flowplayer\("[^"]+",\s*
\{[^}]+?\}\s*,
\s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
["']?url["']?\s*:\s*["']([^"']+)["']
''', webpage))
if not found:
# Cinerama player
found = re.findall(
r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
if not found:
# Try to find twitter cards info
# twitter:player:stream should be checked before twitter:player since
# it is expected to contain a raw stream (see
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
found = filter_video(re.findall(
r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
if not found:
# We look for Open Graph info:
# We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
if m_video_type is not None:
found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
if not found:
REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
found = re.search(
r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
webpage)
if not found:
# Look also in Refresh HTTP header
refresh_header = head_response.headers.get('Refresh')
if refresh_header:
# In python 2 response HTTP headers are bytestrings
if sys.version_info < (3, 0) and isinstance(refresh_header, str):
refresh_header = refresh_header.decode('iso-8859-1')
found = re.search(REDIRECT_REGEX, refresh_header)
if found:
new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
if new_url != url:
self.report_following_redirect(new_url)
return {
'_type': 'url',
'url': new_url,
}
else:
found = None
if not found:
# twitter:player is a https URL to iframe player that may or may not
# be supported by youtube-dl thus this is checked the very last (see
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
embed_url = self._html_search_meta('twitter:player', webpage, default=None)
if embed_url and embed_url != url:
return self.url_result(embed_url)
if not found:
raise UnsupportedError(url)
entries = []
for video_url in orderedSet(found):
video_url = unescapeHTML(video_url)
video_url = video_url.replace('\\/', '/')
video_url = compat_urlparse.urljoin(url, video_url)
video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
# Sometimes, jwplayer extraction will result in a YouTube URL
if YoutubeIE.suitable(video_url):
entries.append(self.url_result(video_url, 'Youtube'))
continue
# 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,
}
if RtmpIE.suitable(video_url):
entry_info_dict.update({
'_type': 'url_transparent',
'ie_key': RtmpIE.ie_key(),
'url': video_url,
})
entries.append(entry_info_dict)
continue
ext = determine_ext(video_url)
if ext == 'smil':
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')
elif ext == 'mpd':
entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
elif ext == 'f4m':
entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
# Just matching .ism/manifest is not enough to be reliably sure
# whether it's actually an ISM manifest or some other streaming
# manifest since there are various streaming URL formats
# possible (see [1]) as well as some other shenanigans like
# .smil/manifest URLs that actually serve an ISM (see [2]) and
# so on.
# Thus the most reasonable way to solve this is to delegate
# to generic extractor in order to look into the contents of
# the manifest itself.
# 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
# 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
entry_info_dict = self.url_result(
smuggle_url(video_url, {'to_generic': True}),
GenericIE.ie_key())
else:
entry_info_dict['url'] = video_url
if entry_info_dict.get('formats'):
self._sort_formats(entry_info_dict['formats'])
entries.append(entry_info_dict)
if len(entries) == 1:
return entries[0]
else:
for num, e in enumerate(entries, start=1):
# 'url' results don't have a title
if e.get('title') is not None:
e['title'] = '%s (%d)' % (e['title'], num)
return {
'_type': 'playlist',
'entries': entries,
}
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
float_or_none,
qualities,
ExtractorError,
)
class GfycatIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\.]+)'
_TESTS = [{
'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
'info_dict': {
'id': 'DeadlyDecisiveGermanpinscher',
'ext': 'mp4',
'title': 'Ghost in the Shell',
'timestamp': 1410656006,
'upload_date': '20140914',
'uploader': 'anonymous',
'duration': 10.4,
'view_count': int,
'like_count': int,
'dislike_count': int,
'categories': list,
'age_limit': 0,
}
}, {
'url': 'http://gfycat.com/ifr/JauntyTimelyAmazontreeboa',
'info_dict': {
'id': 'JauntyTimelyAmazontreeboa',
'ext': 'mp4',
'title': 'JauntyTimelyAmazontreeboa',
'timestamp': 1411720126,
'upload_date': '20140926',
'uploader': 'anonymous',
'duration': 3.52,
'view_count': int,
'like_count': int,
'dislike_count': int,
'categories': list,
'age_limit': 0,
}
}, {
'url': 'https://gfycat.com/ru/RemarkableDrearyAmurstarfish',
'only_matching': True
}, {
'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull',
'only_matching': True
}, {
'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
'only_matching': True
}, {
'url': 'https://thumbs.gfycat.com/acceptablehappygoluckyharborporpoise-size_restricted.gif',
'only_matching': True
}, {
'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4',
'only_matching': True
}]
def _real_extract(self, url):
video_id = self._match_id(url)
gfy = self._download_json(
'https://api.gfycat.com/v1/gfycats/%s' % video_id,
video_id, 'Downloading video info')
if 'error' in gfy:
raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
gfy = gfy['gfyItem']
title = gfy.get('title') or gfy['gfyName']
description = gfy.get('description')
timestamp = int_or_none(gfy.get('createDate'))
uploader = gfy.get('userName')
view_count = int_or_none(gfy.get('views'))
like_count = int_or_none(gfy.get('likes'))
dislike_count = int_or_none(gfy.get('dislikes'))
age_limit = 18 if gfy.get('nsfw') == '1' else 0
width = int_or_none(gfy.get('width'))
height = int_or_none(gfy.get('height'))
fps = int_or_none(gfy.get('frameRate'))
num_frames = int_or_none(gfy.get('numFrames'))
duration = float_or_none(num_frames, fps) if num_frames and fps else None
categories = gfy.get('tags') or gfy.get('extraLemmas') or []
FORMATS = ('gif', 'webm', 'mp4')
quality = qualities(FORMATS)
formats = []
for format_id in FORMATS:
video_url = gfy.get('%sUrl' % format_id)
if not video_url:
continue
filesize = int_or_none(gfy.get('%sSize' % format_id))
formats.append({
'url': video_url,
'format_id': format_id,
'width': width,
'height': height,
'fps': fps,
'filesize': filesize,
'quality': quality(format_id),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'categories': categories,
'age_limit': age_limit,
'formats': formats,
}
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
qualities,
unescapeHTML,
)
class GiantBombIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?giantbomb\.com/(?:videos|shows)/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
_TESTS = [{
'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/',
'md5': '132f5a803e7e0ab0e274d84bda1e77ae',
'info_dict': {
'id': '2300-9782',
'display_id': 'quick-look-destiny-the-dark-below',
'ext': 'mp4',
'title': 'Quick Look: Destiny: The Dark Below',
'description': 'md5:0aa3aaf2772a41b91d44c63f30dfad24',
'duration': 2399,
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'url': 'https://www.giantbomb.com/shows/ben-stranding/2970-20212',
'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')
webpage = self._download_webpage(url, display_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
video = json.loads(unescapeHTML(self._search_regex(
r'data-video="([^"]+)"', webpage, 'data-video')))
duration = int_or_none(video.get('lengthSeconds'))
quality = qualities([
'f4m_low', 'progressive_low', 'f4m_high',
'progressive_high', 'f4m_hd', 'progressive_hd'])
formats = []
for format_id, video_url in video['videoStreams'].items():
if format_id == 'f4m_stream':
continue
ext = determine_ext(video_url)
if ext == 'f4m':
f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.3.1', display_id)
if f4m_formats:
f4m_formats[0]['quality'] = quality(format_id)
formats.extend(f4m_formats)
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, display_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': video_url,
'format_id': format_id,
'quality': quality(format_id),
})
if not formats:
youtube_id = video.get('youtubeID')
if youtube_id:
return self.url_result(youtube_id, 'Youtube')
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}
# coding: utf-8
from __future__ import unicode_literals
import itertools
from .common import InfoExtractor
from ..utils import (
qualities,
compat_str,
parse_duration,
parse_iso8601,
str_to_int,
)
class GigaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?giga\.de/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.giga.de/filme/anime-awesome/trailer/anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss/',
'md5': '6bc5535e945e724640664632055a584f',
'info_dict': {
'id': '2622086',
'display_id': 'anime-awesome-chihiros-reise-ins-zauberland-das-beste-kommt-zum-schluss',
'ext': 'mp4',
'title': 'Anime Awesome: Chihiros Reise ins Zauberland – Das Beste kommt zum Schluss',
'description': 'md5:afdf5862241aded4718a30dff6a57baf',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 578,
'timestamp': 1414749706,
'upload_date': '20141031',
'uploader': 'Robin Schweiger',
'view_count': int,
},
}, {
'url': 'http://www.giga.de/games/channel/giga-top-montag/giga-topmontag-die-besten-serien-2014/',
'only_matching': True,
}, {
'url': 'http://www.giga.de/extra/netzkultur/videos/giga-games-tom-mats-robin-werden-eigene-wege-gehen-eine-ankuendigung/',
'only_matching': True,
}, {
'url': 'http://www.giga.de/tv/jonas-liest-spieletitel-eingedeutscht-episode-2/',
'only_matching': 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-video-id="(\d+)"', r'/api/video/jwplayer/#v=(\d+)'],
webpage, 'video id')
playlist = self._download_json(
'http://www.giga.de/api/syndication/video/video_id/%s/playlist.json?content=syndication/key/368b5f151da4ae05ced7fa296bdff65a/'
% video_id, video_id)[0]
quality = qualities(['normal', 'hd720'])
formats = []
for format_id in itertools.count(0):
fmt = playlist.get(compat_str(format_id))
if not fmt:
break
formats.append({
'url': fmt['src'],
'format_id': '%s-%s' % (fmt['quality'], fmt['type'].split('/')[-1]),
'quality': quality(fmt['quality']),
})
self._sort_formats(formats)
title = self._html_search_meta(
'title', webpage, 'title', fatal=True)
description = self._html_search_meta(
'description', webpage, 'description')
thumbnail = self._og_search_thumbnail(webpage)
duration = parse_duration(self._search_regex(
r'(?s)(?:data-video-id="{0}"|data-video="[^"]*/api/video/jwplayer/#v={0}[^"]*")[^>]*>.+?<span class="duration">([^<]+)</span>'.format(video_id),
webpage, 'duration', fatal=False))
timestamp = parse_iso8601(self._search_regex(
r'datetime="([^"]+)"', webpage, 'upload date', fatal=False))
uploader = self._search_regex(
r'class="author">([^<]+)</a>', webpage, 'uploader', fatal=False)
view_count = str_to_int(self._search_regex(
r'<span class="views"><strong>([\d.,]+)</strong>',
webpage, 'view count', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'uploader': uploader,
'view_count': view_count,
'formats': formats,
}
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
urlencode_postdata,
)
class GigyaBaseIE(InfoExtractor):
def _gigya_login(self, auth_data):
auth_info = self._download_json(
'https://accounts.eu1.gigya.com/accounts.login', None,
note='Logging in', errnote='Unable to log in',
data=urlencode_postdata(auth_data))
error_message = auth_info.get('errorDetails') or auth_info.get('errorMessage')
if error_message:
raise ExtractorError(
'Unable to login: %s' % error_message, expected=True)
return auth_info
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class GlideIE(InfoExtractor):
IE_DESC = 'Glide mobile video messages (glide.me)'
_VALID_URL = r'https?://share\.glide\.me/(?P<id>[A-Za-z0-9\-=_+]+)'
_TEST = {
'url': 'http://share.glide.me/UZF8zlmuQbe4mr+7dCiQ0w==',
'md5': '4466372687352851af2d131cfaa8a4c7',
'info_dict': {
'id': 'UZF8zlmuQbe4mr+7dCiQ0w==',
'ext': 'mp4',
'title': "Damon's Glide message",
'thumbnail': r're:^https?://.*?\.cloudfront\.net/.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<title>(.+?)</title>', webpage,
'title', default=None) or self._og_search_title(webpage)
video_url = self._proto_relative_url(self._search_regex(
r'<source[^>]+src=(["\'])(?P<url>.+?)\1',
webpage, 'video URL', default=None,
group='url')) or self._og_search_video_url(webpage)
thumbnail = self._proto_relative_url(self._search_regex(
r'<img[^>]+id=["\']video-thumbnail["\'][^>]+src=(["\'])(?P<url>.+?)\1',
webpage, 'thumbnail url', default=None,
group='url')) or self._og_search_thumbnail(webpage)
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumbnail,
}
# coding: utf-8
from __future__ import unicode_literals
import base64
import hashlib
import json
import random
import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
)
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
orderedSet,
str_or_none,
)
class GloboIE(InfoExtractor):
_VALID_URL = r'(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
_NETRC_MACHINE = 'globo'
_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://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://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,
}, {
'url': 'globo:3607726',
'only_matching': True,
}]
def _real_initialize(self):
email, password = self._get_login_info()
if email is None:
return
try:
glb_id = (self._download_json(
'https://login.globo.com/api/authentication', None, data=json.dumps({
'payload': {
'email': email,
'password': password,
'serviceId': 4654,
},
}).encode(), headers={
'Content-Type': 'application/json; charset=utf-8',
}) or {}).get('glbId')
if glb_id:
self._set_cookie('.globo.com', 'GLBID', glb_id)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
resp = self._parse_json(e.cause.read(), None)
raise ExtractorError(resp.get('userMessage') or resp['id'], expected=True)
raise
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://api.globovideos.com/videos/%s/playlist' % video_id,
video_id)['videos'][0]
if video.get('encrypted') is True:
raise ExtractorError('This video is DRM protected.', expected=True)
title = video['title']
formats = []
subtitles = {}
for resource in video['resources']:
resource_id = resource.get('_id')
resource_url = resource.get('url')
resource_type = resource.get('type')
if not resource_url or (resource_type == 'media' and not resource_id) or resource_type not in ('subtitle', 'media'):
continue
if resource_type == 'subtitle':
subtitles.setdefault(resource.get('language') or 'por', []).append({
'url': resource_url,
})
continue
security = self._download_json(
'http://security.video.globo.com/videos/%s/hash' % video_id,
video_id, 'Downloading security hash for %s' % resource_id, query={
'player': 'desktop',
'version': '5.19.1',
'resource_id': resource_id,
})
security_hash = security.get('hash')
if not security_hash:
message = security.get('message')
if message:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, message), expected=True)
continue
hash_code = security_hash[:2]
padding = '%010d' % random.randint(1, 10000000000)
if hash_code in ('04', '14'):
received_time = security_hash[3:13]
received_md5 = security_hash[24:]
hash_prefix = security_hash[:23]
elif hash_code in ('02', '12', '03', '13'):
received_time = security_hash[2:12]
received_md5 = security_hash[22:]
padding += '1'
hash_prefix = '05' + security_hash[:22]
padded_sign_time = compat_str(int(received_time) + 86400) + padding
md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode()
signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=')
signed_hash = hash_prefix + padded_sign_time + signed_md5
signed_url = '%s?h=%s&k=html5&a=%s&u=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A', security.get('user') or '')
if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(
signed_url, resource_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif resource_id.endswith('mpd') or resource_url.endswith('.mpd'):
formats.extend(self._extract_mpd_formats(
signed_url, resource_id, mpd_id='dash', fatal=False))
elif resource_id.endswith('manifest') or resource_url.endswith('/manifest'):
formats.extend(self._extract_ism_formats(
signed_url, resource_id, ism_id='mss', fatal=False))
else:
formats.append({
'url': signed_url,
'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)
uploader = video.get('channel')
uploader_id = str_or_none(video.get('channel_id'))
return {
'id': video_id,
'title': title,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats,
'subtitles': subtitles,
}
class GloboArticleIE(InfoExtractor):
_VALID_URL = r'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',
'info_dict': {
'id': 'novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes',
'title': 'Novidade na fiscalização de bagagem pela Receita provoca discussões',
'description': 'md5:c3c4b4d4c30c32fce460040b1ac46b12',
},
'playlist_count': 1,
}, {
'url': 'http://g1.globo.com/pr/parana/noticia/2016/09/mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato.html',
'info_dict': {
'id': 'mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato',
'title': "Lula era o 'comandante máximo' do esquema da Lava Jato, diz MPF",
'description': 'md5:8aa7cc8beda4dc71cc8553e00b77c54c',
},
'playlist_count': 6,
}, {
'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,
}, {
'url': 'http://oglobo.globo.com/rio/a-amizade-entre-um-entregador-de-farmacia-um-piano-19946271',
'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_ids = []
for video_regex in self._VIDEOID_REGEXES:
video_ids.extend(re.findall(video_regex, webpage))
entries = [
self.url_result('globo:%s' % video_id, GloboIE.ie_key())
for video_id in orderedSet(video_ids)]
title = self._og_search_title(webpage, fatal=False)
description = self._html_search_meta('description', webpage)
return self.playlist_result(entries, display_id, title, description)
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
parse_iso8601,
)
class GodTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)'
_TESTS = [
{
'url': 'https://www.godtube.com/watch/?v=0C0CNNNU',
'md5': '77108c1e4ab58f48031101a1a2119789',
'info_dict': {
'id': '0C0CNNNU',
'ext': 'mp4',
'title': 'Woman at the well.',
'duration': 159,
'timestamp': 1205712000,
'uploader': 'beverlybmusic',
'upload_date': '20080317',
'thumbnail': r're:^https?://.*\.jpg$',
},
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
config = self._download_xml(
'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(),
video_id, 'Downloading player config XML')
video_url = config.find('file').text
uploader = config.find('author').text
timestamp = parse_iso8601(config.find('date').text)
duration = parse_duration(config.find('duration').text)
thumbnail = config.find('image').text
media = self._download_xml(
'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML')
title = media.find('title').text
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'duration': duration,
}
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
determine_ext,
)
class GolemIE(InfoExtractor):
_VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
_TEST = {
'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
'info_dict': {
'id': '14095',
'format_id': 'high',
'ext': 'mp4',
'title': 'iPhone 6 und 6 Plus - Test',
'duration': 300.44,
'filesize': 65309548,
}
}
_PREFIX = 'http://video.golem.de'
def _real_extract(self, url):
video_id = self._match_id(url)
config = self._download_xml(
'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)
info = {
'id': video_id,
'title': config.findtext('./title', 'golem'),
'duration': self._float(config.findtext('./playtime'), 'duration'),
}
formats = []
for e in config:
url = e.findtext('./url')
if not url:
continue
formats.append({
'format_id': compat_str(e.tag),
'url': compat_urlparse.urljoin(self._PREFIX, url),
'height': self._int(e.get('height'), 'height'),
'width': self._int(e.get('width'), 'width'),
'filesize': self._int(e.findtext('filesize'), 'filesize'),
'ext': determine_ext(e.findtext('./filename')),
})
self._sort_formats(formats)
info['formats'] = formats
thumbnails = []
for e in config.findall('.//teaser'):
url = e.findtext('./url')
if not url:
continue
thumbnails.append({
'url': compat_urlparse.urljoin(self._PREFIX, url),
'width': self._int(e.get('width'), 'thumbnail width'),
'height': self._int(e.get('height'), 'thumbnail height'),
})
info['thumbnails'] = thumbnails
return info
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
lowercase_escape,
update_url_query,
)
class GoogleDriveIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
(?:docs|drive)\.google\.com/
(?:
(?:uc|open)\?.*?id=|
file/d/
)|
video\.google\.com/get_player\?.*?docid=
)
(?P<id>[a-zA-Z0-9_-]{28,})
'''
_TESTS = [{
'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
'md5': '5c602afbbf2c1db91831f5d82f678554',
'info_dict': {
'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
'ext': 'mp4',
'title': 'Big Buck Bunny.mp4',
'duration': 45,
}
}, {
# video can't be watched anonymously due to view count limit reached,
# but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046)
'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
'info_dict': {
'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
'ext': 'mp4',
'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
}
}, {
# video id is longer than 28 characters
'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
'info_dict': {
'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
'ext': 'mp4',
'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
'duration': 189,
},
'only_matching': True,
}, {
'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
'only_matching': True,
}, {
'url': 'https://drive.google.com/uc?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
'only_matching': True,
}]
_FORMATS_EXT = {
'5': 'flv',
'6': 'flv',
'13': '3gp',
'17': '3gp',
'18': 'mp4',
'22': 'mp4',
'34': 'flv',
'35': 'flv',
'36': '3gp',
'37': 'mp4',
'38': 'mp4',
'43': 'webm',
'44': 'webm',
'45': 'webm',
'46': 'webm',
'59': 'mp4',
}
_BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
_CAPTIONS_ENTRY_TAG = {
'subtitles': 'track',
'automatic_captions': 'target',
}
_caption_formats_ext = []
_captions_xml = None
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
webpage)
if mobj:
return 'https://drive.google.com/file/d/%s' % mobj.group('id')
def _download_subtitles_xml(self, video_id, subtitles_id, hl):
if self._captions_xml:
return
self._captions_xml = self._download_xml(
self._BASE_URL_CAPTIONS, video_id, query={
'id': video_id,
'vid': subtitles_id,
'hl': hl,
'v': video_id,
'type': 'list',
'tlangs': '1',
'fmts': '1',
'vssids': '1',
}, note='Downloading subtitles XML',
errnote='Unable to download subtitles XML', fatal=False)
if self._captions_xml:
for f in self._captions_xml.findall('format'):
if f.attrib.get('fmt_code') and not f.attrib.get('default'):
self._caption_formats_ext.append(f.attrib['fmt_code'])
def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
origin_lang_code=None):
if not subtitles_id or not caption_type:
return
captions = {}
for caption_entry in self._captions_xml.findall(
self._CAPTIONS_ENTRY_TAG[caption_type]):
caption_lang_code = caption_entry.attrib.get('lang_code')
if not caption_lang_code:
continue
caption_format_data = []
for caption_format in self._caption_formats_ext:
query = {
'vid': subtitles_id,
'v': video_id,
'fmt': caption_format,
'lang': (caption_lang_code if origin_lang_code is None
else origin_lang_code),
'type': 'track',
'name': '',
'kind': '',
}
if origin_lang_code is not None:
query.update({'tlang': caption_lang_code})
caption_format_data.append({
'url': update_url_query(self._BASE_URL_CAPTIONS, query),
'ext': caption_format,
})
captions[caption_lang_code] = caption_format_data
return captions
def _get_subtitles(self, video_id, subtitles_id, hl):
if not subtitles_id or not hl:
return
self._download_subtitles_xml(video_id, subtitles_id, hl)
if not self._captions_xml:
return
return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
def _get_automatic_captions(self, video_id, subtitles_id, hl):
if not subtitles_id or not hl:
return
self._download_subtitles_xml(video_id, subtitles_id, hl)
if not self._captions_xml:
return
track = self._captions_xml.find('track')
if track is None:
return
origin_lang_code = track.attrib.get('lang_code')
if not origin_lang_code:
return
return self._get_captions_by_type(
video_id, subtitles_id, 'automatic_captions', origin_lang_code)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://docs.google.com/file/d/%s' % video_id, video_id)
title = self._search_regex(
r'"title"\s*,\s*"([^"]+)', webpage, 'title',
default=None) or self._og_search_title(webpage)
duration = int_or_none(self._search_regex(
r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
default=None))
formats = []
fmt_stream_map = self._search_regex(
r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
'fmt stream map', default='').split(',')
fmt_list = self._search_regex(
r'"fmt_list"\s*,\s*"([^"]+)', webpage,
'fmt_list', default='').split(',')
if fmt_stream_map and fmt_list:
resolutions = {}
for fmt in fmt_list:
mobj = re.search(
r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
if mobj:
resolutions[mobj.group('format_id')] = (
int(mobj.group('width')), int(mobj.group('height')))
for fmt_stream in fmt_stream_map:
fmt_stream_split = fmt_stream.split('|')
if len(fmt_stream_split) < 2:
continue
format_id, format_url = fmt_stream_split[:2]
f = {
'url': lowercase_escape(format_url),
'format_id': format_id,
'ext': self._FORMATS_EXT[format_id],
}
resolution = resolutions.get(format_id)
if resolution:
f.update({
'width': resolution[0],
'height': resolution[1],
})
formats.append(f)
source_url = update_url_query(
'https://drive.google.com/uc', {
'id': video_id,
'export': 'download',
})
def request_source_file(source_url, kind):
return self._request_webpage(
source_url, video_id, note='Requesting %s file' % kind,
errnote='Unable to request %s file' % kind, fatal=False)
urlh = request_source_file(source_url, 'source')
if urlh:
def add_source_format(urlh):
formats.append({
# Use redirect URLs as download URLs in order to calculate
# correct cookies in _calc_cookies.
# Using original URLs may result in redirect loop due to
# google.com's cookies mistakenly used for googleusercontent.com
# redirect URLs (see #23919).
'url': urlh.geturl(),
'ext': determine_ext(title, 'mp4').lower(),
'format_id': 'source',
'quality': 1,
})
if urlh.headers.get('Content-Disposition'):
add_source_format(urlh)
else:
confirmation_webpage = self._webpage_read_content(
urlh, url, video_id, note='Downloading confirmation page',
errnote='Unable to confirm download', fatal=False)
if confirmation_webpage:
confirm = self._search_regex(
r'confirm=([^&"\']+)', confirmation_webpage,
'confirmation code', fatal=False)
if confirm:
confirmed_source_url = update_url_query(source_url, {
'confirm': confirm,
})
urlh = request_source_file(confirmed_source_url, 'confirmed source')
if urlh and urlh.headers.get('Content-Disposition'):
add_source_format(urlh)
if not formats:
reason = self._search_regex(
r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
if reason:
raise ExtractorError(reason, expected=True)
self._sort_formats(formats)
hl = self._search_regex(
r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
subtitles_id = None
ttsurl = self._search_regex(
r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
if ttsurl:
# the video Id for subtitles will be the last value in the ttsurl
# query string
subtitles_id = ttsurl.encode('utf-8').decode(
'unicode_escape').split('=')[-1]
return {
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'duration': duration,
'formats': formats,
'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
'automatic_captions': self.extract_automatic_captions(
video_id, subtitles_id, hl),
}
# coding: utf-8
from __future__ import unicode_literals
import re
import codecs
from .common import InfoExtractor
from ..utils import unified_strdate
class GooglePlusIE(InfoExtractor):
IE_DESC = 'Google Plus'
_VALID_URL = r'https?://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
IE_NAME = 'plus.google'
_TEST = {
'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',
'info_dict': {
'id': 'ZButuJc6CtH',
'ext': 'flv',
'title': '嘆きの天使 降臨',
'upload_date': '20120613',
'uploader': '井上ヨシマサ',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
# Step 1, Retrieve post webpage to extract further information
webpage = self._download_webpage(url, video_id, 'Downloading entry webpage')
title = self._og_search_description(webpage).splitlines()[0]
upload_date = unified_strdate(self._html_search_regex(
r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*>
([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
webpage, 'upload date', fatal=False, flags=re.VERBOSE))
uploader = self._html_search_regex(
r'rel="author".*?>(.*?)</a>', webpage, 'uploader', fatal=False)
# Step 2, Simulate clicking the image box to launch video
DOMAIN = 'https://plus.google.com/'
video_page = self._search_regex(
r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
webpage, 'video page URL')
if not video_page.startswith(DOMAIN):
video_page = DOMAIN + video_page
webpage = self._download_webpage(video_page, video_id, 'Downloading video page')
def unicode_escape(s):
decoder = codecs.getdecoder('unicode_escape')
return re.sub(
r'\\u[0-9a-fA-F]{4,}',
lambda m: decoder(m.group(0))[0],
s)
# Extract video links all sizes
formats = [{
'url': unicode_escape(video_url),
'ext': 'flv',
'width': int(width),
'height': int(height),
} for width, height, video_url in re.findall(
r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent\.com.*?)"', webpage)]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'uploader': uploader,
'upload_date': upload_date,
'formats': formats,
}
from __future__ import unicode_literals
import itertools
import re
from .common import SearchInfoExtractor
class GoogleSearchIE(SearchInfoExtractor):
IE_DESC = 'Google Video search'
_MAX_RESULTS = 1000
IE_NAME = 'video.google:search'
_SEARCH_KEY = 'gvsearch'
_TEST = {
'url': 'gvsearch15:python language',
'info_dict': {
'id': 'python language',
'title': 'python language',
},
'playlist_count': 15,
}
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
entries = []
res = {
'_type': 'playlist',
'id': query,
'title': query,
}
for pagenum in itertools.count():
webpage = self._download_webpage(
'http://www.google.com/search',
'gvsearch:' + query,
note='Downloading result page %s' % (pagenum + 1),
query={
'tbm': 'vid',
'q': query,
'start': pagenum * 10,
'hl': 'en',
})
for hit_idx, mobj in enumerate(re.finditer(
r'<h3 class="r"><a href="([^"]+)"', webpage)):
# Skip playlists
if not re.search(r'id="vidthumb%d"' % (hit_idx + 1), webpage):
continue
entries.append({
'_type': 'url',
'url': mobj.group(1)
})
if (len(entries) >= n) or not re.search(r'id="pnnext"', webpage):
res['entries'] = entries[:n]
return res
# coding: utf-8
from __future__ import unicode_literals
import re
from .adobepass import AdobePassIE
from ..utils import (
int_or_none,
determine_ext,
parse_age_limit,
urlencode_postdata,
ExtractorError,
)
class GoIE(AdobePassIE):
_SITE_INFO = {
'abc': {
'brand': '001',
'requestor_id': 'ABC',
},
'freeform': {
'brand': '002',
'requestor_id': 'ABCFamily',
},
'watchdisneychannel': {
'brand': '004',
'resource_id': 'Disney',
},
'watchdisneyjunior': {
'brand': '008',
'resource_id': 'DisneyJunior',
},
'watchdisneyxd': {
'brand': '009',
'resource_id': 'DisneyXD',
},
'disneynow': {
'brand': '011',
'resource_id': 'Disney',
}
}
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?P<sub_domain>%s)\.)?go|
(?P<sub_domain_2>abc|freeform|disneynow)
)\.com/
(?:
(?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
(?:[^/]+/)*(?P<display_id>[^/?\#]+)
)
''' % '|'.join(list(_SITE_INFO.keys()))
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'info_dict': {
'id': 'VDKA3807643',
'ext': 'mp4',
'title': 'The Traitor in the White House',
'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'This content is no longer available.',
}, {
'url': 'http://watchdisneyxd.go.com/doraemon',
'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
'info_dict': {
'id': 'VDKA3609139',
'ext': 'mp4',
'title': 'This Guilty Blood',
'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
'age_limit': 14,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet',
'info_dict': {
'id': 'VDKA13435179',
'ext': 'mp4',
'title': 'The Bet',
'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404',
'age_limit': 14,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'only_matching': True,
}, {
'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
'only_matching': True,
}, {
# brand 004
'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
'only_matching': True,
}, {
# brand 008
'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}]
def _extract_videos(self, brand, video_id='-1', show_id='-1'):
display_id = video_id if video_id != '-1' else show_id
return self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
display_id)['video']
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
sub_domain = mobj.group('sub_domain') or mobj.group('sub_domain_2')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
if not video_id or not site_info:
webpage = self._download_webpage(url, display_id or video_id)
video_id = self._search_regex(
(
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)',
# https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
), webpage, 'video id', default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',
r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
default='004')
site_info = next(
si for _, si in self._SITE_INFO.items()
if si.get('brand') == brand)
if not video_id:
# show extraction works for Disney, DisneyJunior and DisneyXD
# ABC and Freeform has different layout
show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
entries = []
for video in videos:
entries.append(self.url_result(