Add support for https for rest of the exctractors.
Aleksander Nitecki
Sebastian Blunt
Matěj Cepl
+Xie Yanbo
version <unreleased>
Extractors
+* [foxgay] Fix extraction (#10480)
++ [miaopai] New extractor (#10556)
+* [gamestar] Fix metadata extraction (#10479)
+ [bilibili] Support episodes (#10190)
+ [tvnoe] New extractor (#10524)
from .metacritic import MetacriticIE
from .mgoon import MgoonIE
from .mgtv import MGTVIE
+from .miaopai import MiaoPaiIE
from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyIE,
MicrosoftVirtualAcademyCourseIE,
)
from .rice import RICEIE
from .ringtv import RingTVIE
+from .rmcdecouverte import RMCDecouverteIE
from .ro220 import Ro220IE
from .rockstargames import RockstarGamesIE
from .roosterteeth import RoosterTeethIE
from __future__ import unicode_literals
+import itertools
+
from .common import InfoExtractor
+from ..utils import (
+ get_element_by_id,
+ 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': '80d72beab5d04e1655a56ad37afe6841',
+ 'md5': '344558ccfea74d33b7adbce22e577f54',
'info_dict': {
'id': '2582',
'ext': 'mp4',
- 'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a',
- 'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf',
+ 'title': 'Fuck Turkish-style',
+ 'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
'age_limit': 18,
'thumbnail': 're:https?://.*\.jpg$',
},
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(
- r'<title>(?P<title>.*?)</title>',
- webpage, 'title', fatal=False)
- description = self._html_search_regex(
- r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>',
- webpage, 'description', fatal=False)
+ 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(
- self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'),
- video_id)
- video_url = self._html_search_regex(
- r"v_path = '(?P<vid>http://.*?)'", iframe, 'url')
- thumb_url = self._html_search_regex(
- r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False)
+ 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': 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,
- 'url': video_url,
+ 'formats': formats,
'description': description,
- 'thumbnail': thumb_url,
+ 'thumbnail': video_data.get('act_vid', {}).get('thumb'),
'age_limit': 18,
}
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
int_or_none,
- parse_duration,
- str_to_int,
- unified_strdate,
+ remove_end,
)
'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 vollständigen Trailer an.',
- 'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg',
+ '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': 're:^https?://.*\.jpg$',
+ 'timestamp': 1406542020,
'upload_date': '20140728',
'duration': 17
}
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- og_title = self._og_search_title(webpage)
- title = re.sub(r'\s*- Video (bei|-) GameStar\.de$', '', og_title)
-
url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
- description = self._og_search_description(webpage).strip()
-
- thumbnail = self._proto_relative_url(
- self._og_search_thumbnail(webpage), scheme='http:')
-
- upload_date = unified_strdate(self._html_search_regex(
- r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+) ',
- webpage, 'upload_date', fatal=False))
-
- duration = parse_duration(self._html_search_regex(
- r' Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration',
- fatal=False))
-
- view_count = str_to_int(self._html_search_regex(
- r' Zuschauer: ([0-9\.]+) ', webpage,
- 'view_count', fatal=False))
+ # 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'], ' - GameStar')
+ view_count = json_ld.get('interactionCount')
comment_count = int_or_none(self._html_search_regex(
- r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count',
+ r'([0-9]+) Kommentare</span>', webpage, 'comment_count',
fatal=False))
- return {
+ info_dict.update({
'id': video_id,
- 'title': title,
'url': url,
'ext': 'mp4',
- 'thumbnail': thumbnail,
- 'description': description,
- 'upload_date': upload_date,
- 'duration': duration,
'view_count': view_count,
'comment_count': comment_count
- }
+ })
+
+ return info_dict
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class MiaoPaiIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
+ _TEST = {
+ 'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
+ 'md5': '095ed3f1cd96b821add957bdc29f845b',
+ 'info_dict': {
+ 'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
+ 'ext': 'mp4',
+ 'title': '西游记音乐会的秒拍视频',
+ 'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
+ }
+ }
+
+ _USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(
+ url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
+
+ title = self._html_search_regex(
+ r'<title>([^<]+)</title>', webpage, 'title')
+ thumbnail = self._html_search_regex(
+ r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
+ webpage, 'thumbnail', fatal=False, group='url')
+ videos = self._parse_html5_media_entries(url, webpage, video_id)
+ info = videos[0]
+
+ info.update({
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ })
+ return info
'height': 360,
'duration': 179,
'filesize': 17822500,
- }
+ },
+ 'skip': 'Video has been removed',
},
{
'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
)
-class ProSiebenSat1IE(InfoExtractor):
+class ProSiebenSat1BaseIE(InfoExtractor):
+ def _extract_video_info(self, url, clip_id):
+ client_location = url
+
+ video = self._download_json(
+ 'http://vas.sim-technik.de/vas/live/v2/videos',
+ clip_id, 'Downloading videos JSON', query={
+ 'access_token': self._TOKEN,
+ 'client_location': client_location,
+ 'client_name': self._CLIENT_NAME,
+ 'ids': clip_id,
+ })[0]
+
+ if video.get('is_protected') is True:
+ raise ExtractorError('This video is DRM protected.', expected=True)
+
+ duration = float_or_none(video.get('duration'))
+ source_ids = [compat_str(source['id']) for source in video['sources']]
+
+ client_id = self._SALT[:2] + sha1(''.join([clip_id, self._SALT, self._TOKEN, client_location, self._SALT, self._CLIENT_NAME]).encode('utf-8')).hexdigest()
+
+ sources = self._download_json(
+ 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
+ clip_id, 'Downloading sources JSON', query={
+ 'access_token': self._TOKEN,
+ 'client_id': client_id,
+ 'client_location': client_location,
+ 'client_name': self._CLIENT_NAME,
+ })
+ server_id = sources['server_id']
+
+ def fix_bitrate(bitrate):
+ bitrate = int_or_none(bitrate)
+ if not bitrate:
+ return None
+ return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
+
+ formats = []
+ for source_id in source_ids:
+ client_id = self._SALT[:2] + sha1(''.join([self._SALT, clip_id, self._TOKEN, server_id, client_location, source_id, self._SALT, self._CLIENT_NAME]).encode('utf-8')).hexdigest()
+ urls = self._download_json(
+ 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
+ clip_id, 'Downloading urls JSON', fatal=False, query={
+ 'access_token': self._TOKEN,
+ 'client_id': client_id,
+ 'client_location': client_location,
+ 'client_name': self._CLIENT_NAME,
+ 'server_id': server_id,
+ 'source_ids': source_id,
+ })
+ if not urls:
+ continue
+ if urls.get('status_code') != 0:
+ raise ExtractorError('This video is unavailable', expected=True)
+ urls_sources = urls['sources']
+ if isinstance(urls_sources, dict):
+ urls_sources = urls_sources.values()
+ for source in urls_sources:
+ source_url = source.get('url')
+ if not source_url:
+ continue
+ protocol = source.get('protocol')
+ mimetype = source.get('mimetype')
+ if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
+ formats.extend(self._extract_f4m_formats(
+ source_url, clip_id, f4m_id='hds', fatal=False))
+ elif mimetype == 'application/x-mpegURL':
+ formats.extend(self._extract_m3u8_formats(
+ source_url, clip_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False))
+ else:
+ tbr = fix_bitrate(source['bitrate'])
+ if protocol in ('rtmp', 'rtmpe'):
+ mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
+ if not mobj:
+ continue
+ path = mobj.group('path')
+ mp4colon_index = path.rfind('mp4:')
+ app = path[:mp4colon_index]
+ play_path = path[mp4colon_index:]
+ formats.append({
+ 'url': '%s/%s' % (mobj.group('url'), app),
+ 'app': app,
+ 'play_path': play_path,
+ 'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
+ 'page_url': 'http://www.prosieben.de',
+ 'tbr': tbr,
+ 'ext': 'flv',
+ 'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
+ })
+ else:
+ formats.append({
+ 'url': source_url,
+ 'tbr': tbr,
+ 'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'duration': duration,
+ 'formats': formats,
+ }
+
+
+class ProSiebenSat1IE(ProSiebenSat1BaseIE):
IE_NAME = 'prosiebensat1'
IE_DESC = 'ProSiebenSat.1 Digital'
_VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany|7tv)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
},
]
+ _TOKEN = 'prosieben'
+ _SALT = '01!8d8F_)r9]4s[qeuXfP%'
+ _CLIENT_NAME = 'kolibri-2.0.19-splec4'
_CLIPID_REGEXES = [
r'"clip_id"\s*:\s+"(\d+)"',
r'clipid: "(\d+)"',
def _extract_clip(self, url, webpage):
clip_id = self._html_search_regex(
self._CLIPID_REGEXES, webpage, 'clip id')
-
- access_token = 'prosieben'
- client_name = 'kolibri-2.0.19-splec4'
- client_location = url
-
- video = self._download_json(
- 'http://vas.sim-technik.de/vas/live/v2/videos',
- clip_id, 'Downloading videos JSON', query={
- 'access_token': access_token,
- 'client_location': client_location,
- 'client_name': client_name,
- 'ids': clip_id,
- })[0]
-
- if video.get('is_protected') is True:
- raise ExtractorError('This video is DRM protected.', expected=True)
-
- duration = float_or_none(video.get('duration'))
- source_ids = [compat_str(source['id']) for source in video['sources']]
-
- g = '01!8d8F_)r9]4s[qeuXfP%'
- client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name]).encode('utf-8')).hexdigest()
-
- sources = self._download_json(
- 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
- clip_id, 'Downloading sources JSON', query={
- 'access_token': access_token,
- 'client_id': client_id,
- 'client_location': client_location,
- 'client_name': client_name,
- })
- server_id = sources['server_id']
-
title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
-
- def fix_bitrate(bitrate):
- bitrate = int_or_none(bitrate)
- if not bitrate:
- return None
- return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
-
- formats = []
- for source_id in source_ids:
- client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id, client_location, source_id, g, client_name]).encode('utf-8')).hexdigest()
- urls = self._download_json(
- 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
- clip_id, 'Downloading urls JSON', fatal=False, query={
- 'access_token': access_token,
- 'client_id': client_id,
- 'client_location': client_location,
- 'client_name': client_name,
- 'server_id': server_id,
- 'source_ids': source_id,
- })
- if not urls:
- continue
- if urls.get('status_code') != 0:
- raise ExtractorError('This video is unavailable', expected=True)
- urls_sources = urls['sources']
- if isinstance(urls_sources, dict):
- urls_sources = urls_sources.values()
- for source in urls_sources:
- source_url = source.get('url')
- if not source_url:
- continue
- protocol = source.get('protocol')
- mimetype = source.get('mimetype')
- if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
- formats.extend(self._extract_f4m_formats(
- source_url, clip_id, f4m_id='hds', fatal=False))
- elif mimetype == 'application/x-mpegURL':
- formats.extend(self._extract_m3u8_formats(
- source_url, clip_id, 'mp4', 'm3u8_native',
- m3u8_id='hls', fatal=False))
- else:
- tbr = fix_bitrate(source['bitrate'])
- if protocol in ('rtmp', 'rtmpe'):
- mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
- if not mobj:
- continue
- path = mobj.group('path')
- mp4colon_index = path.rfind('mp4:')
- app = path[:mp4colon_index]
- play_path = path[mp4colon_index:]
- formats.append({
- 'url': '%s/%s' % (mobj.group('url'), app),
- 'app': app,
- 'play_path': play_path,
- 'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
- 'page_url': 'http://www.prosieben.de',
- 'tbr': tbr,
- 'ext': 'flv',
- 'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
- })
- else:
- formats.append({
- 'url': source_url,
- 'tbr': tbr,
- 'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
- })
- self._sort_formats(formats)
-
+ info = self._extract_video_info(url, clip_id)
description = self._html_search_regex(
self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._html_search_regex(
self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))
- return {
+ info.update({
'id': clip_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
- 'duration': duration,
- 'formats': formats,
- }
+ })
+ return info
def _extract_playlist(self, url, webpage):
playlist_id = self._html_search_regex(
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
-from .common import InfoExtractor
+from .prosiebensat1 import ProSiebenSat1BaseIE
from ..utils import (
- ExtractorError,
unified_strdate,
- int_or_none,
+ parse_duration,
+ compat_str,
)
-class Puls4IE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?puls4\.com/video/[^/]+/play/(?P<id>[0-9]+)'
+class Puls4IE(ProSiebenSat1BaseIE):
+ _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)'
_TESTS = [{
- 'url': 'http://www.puls4.com/video/pro-und-contra/play/2716816',
- 'md5': '49f6a6629747eeec43cef6a46b5df81d',
+ 'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
+ 'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
'info_dict': {
- 'id': '2716816',
- 'ext': 'mp4',
- 'title': 'Pro und Contra vom 23.02.2015',
- 'description': 'md5:293e44634d9477a67122489994675db6',
- 'duration': 2989,
- 'upload_date': '20150224',
+ 'id': '118118',
+ 'ext': 'flv',
+ 'title': 'Tobias Homberger von myclubs im #2min2miotalk',
+ 'description': 'md5:f9def7c5e8745d6026d8885487d91955',
+ 'upload_date': '20160830',
'uploader': 'PULS_4',
},
- 'skip': 'Only works from Germany',
- }, {
- 'url': 'http://www.puls4.com/video/kult-spielfilme/play/1298106',
- 'md5': '6a48316c8903ece8dab9b9a7bf7a59ec',
- 'info_dict': {
- 'id': '1298106',
- 'ext': 'mp4',
- 'title': 'Lucky Fritz',
- },
- 'skip': 'Only works from Germany',
}]
+ _TOKEN = 'puls4'
+ _SALT = '01!kaNgaiNgah1Ie4AeSha'
+ _CLIENT_NAME = ''
def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- error_message = self._html_search_regex(
- r'<div[^>]+class="message-error"[^>]*>(.+?)</div>',
- webpage, 'error message', default=None)
- if error_message:
- raise ExtractorError(
- '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
-
- real_url = self._html_search_regex(
- r'\"fsk-button\".+?href=\"([^"]+)',
- webpage, 'fsk_button', default=None)
- if real_url:
- webpage = self._download_webpage(real_url, video_id)
-
- player = self._search_regex(
- r'p4_video_player(?:_iframe)?\("video_\d+_container"\s*,(.+?)\);\s*\}',
- webpage, 'player')
-
- player_json = self._parse_json(
- '[%s]' % player, video_id,
- transform_source=lambda s: s.replace('undefined,', ''))
-
- formats = None
- result = None
-
- for v in player_json:
- if isinstance(v, list) and not formats:
- formats = [{
- 'url': f['url'],
- 'format': 'hd' if f.get('hd') else 'sd',
- 'width': int_or_none(f.get('size_x')),
- 'height': int_or_none(f.get('size_y')),
- 'tbr': int_or_none(f.get('bitrate')),
- } for f in v]
- self._sort_formats(formats)
- elif isinstance(v, dict) and not result:
- result = {
- 'id': video_id,
- 'title': v['videopartname'].strip(),
- 'description': v.get('videotitle'),
- 'duration': int_or_none(v.get('videoduration') or v.get('episodeduration')),
- 'upload_date': unified_strdate(v.get('clipreleasetime')),
- 'uploader': v.get('channel'),
- }
-
- result['formats'] = formats
-
- return result
+ path = self._match_id(url)
+ content_path = self._download_json(
+ 'http://www.puls4.com/api/json-fe/page/' + path, path)['content'][0]['url']
+ media = self._download_json(
+ 'http://www.puls4.com' + content_path,
+ content_path)['mediaCurrent']
+ player_content = media['playerContent']
+ info = self._extract_video_info(url, player_content['id'])
+ info.update({
+ 'id': compat_str(media['objectId']),
+ 'title': player_content['title'],
+ 'description': media.get('description'),
+ 'thumbnail': media.get('previewLink'),
+ 'upload_date': unified_strdate(media.get('date')),
+ 'duration': parse_duration(player_content.get('duration')),
+ 'episode': player_content.get('episodePartName'),
+ 'show': media.get('channel'),
+ 'season_id': player_content.get('seasonId'),
+ 'uploader': player_content.get('sourceCompany'),
+ })
+ return info
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveLegacyIE
+from ..compat import (
+ compat_parse_qs,
+ compat_urlparse,
+)
+
+
+class RMCDecouverteIE(InfoExtractor):
+ _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P<id>\d+)'
+
+ _TEST = {
+ 'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=1430&title=LES%20HEROS%20DU%2088e%20ETAGE',
+ 'info_dict': {
+ 'id': '5111223049001',
+ 'ext': 'mp4',
+ 'title': ': LES HEROS DU 88e ETAGE',
+ 'description': 'Découvrez comment la bravoure de deux hommes dans la Tour Nord du World Trade Center a sauvé la vie d\'innombrables personnes le 11 septembre 2001.',
+ 'uploader_id': '1969646226001',
+ 'upload_date': '20160904',
+ 'timestamp': 1472951103,
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ },
+ 'skip': 'Only works from France',
+ }
+ BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s'
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
+ brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
+ return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
# encoding: utf-8
from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
from .brightcove import BrightcoveLegacyIE
-from ..compat import compat_parse_qs
+from ..compat import (
+ compat_parse_qs,
+ compat_urlparse,
+)
class TlcDeIE(InfoExtractor):
title = mobj.group('title')
webpage = self._download_webpage(url, title)
brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
- brightcove_id = compat_parse_qs(brightcove_legacy_url)['@videoPlayer'][0]
+ brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
projects / youtube-dl / commitdiff