Pratyush Singh
Aleksander Nitecki
Sebastian Blunt
+Matěj Cepl
+version <unreleased>
+
+Extractors
+* [gamestar] Fix metadata extraction (#10479)
++ [bilibili] Support episodes (#10190)
++ [tvnoe] New extractor (#10524)
+
+
version 2016.09.04.1
Core
youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
+### Should I add `--hls-prefer-native` into my config?
+
+When youtube-dl detects an HLS video, it can download it either with the built-in downloader or ffmpeg. Since many HLS streams are slightly invalid and ffmpeg/youtube-dl each handle some invalid cases better than the other, there is an option to switch the downloader if needed.
+
+When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
+
+In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](http://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
+
+If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
+
### Can you add support for this anime video site, or site which shows current movies for free?
As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
+++ /dev/null
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import parse_iso8601
-
-
-class Abc7NewsIE(InfoExtractor):
- _VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
- _TESTS = [
- {
- 'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
- 'info_dict': {
- 'id': '472581',
- 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
- 'ext': 'mp4',
- 'title': 'East Bay museum celebrates history of synthesized music',
- 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
- 'thumbnail': 're:^https?://.*\.jpg$',
- 'timestamp': 1421123075,
- 'upload_date': '20150113',
- 'uploader': 'Jonathan Bloom',
- },
- 'params': {
- # m3u8 download
- 'skip_download': True,
- },
- },
- {
- 'url': 'http://abc7news.com/472581',
- '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') or video_id
-
- webpage = self._download_webpage(url, display_id)
-
- m3u8 = self._html_search_meta(
- 'contentURL', webpage, 'm3u8 url', fatal=True)
-
- formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
- self._sort_formats(formats)
-
- title = self._og_search_title(webpage).strip()
- description = self._og_search_description(webpage).strip()
- thumbnail = self._og_search_thumbnail(webpage)
- timestamp = parse_iso8601(self._search_regex(
- r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
- webpage, 'upload date', fatal=False))
- uploader = self._search_regex(
- r'rel="author">([^<]+)</a>',
- webpage, 'uploader', default=None)
-
- return {
- 'id': video_id,
- 'display_id': display_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'timestamp': timestamp,
- 'uploader': uploader,
- 'formats': formats,
- }
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ parse_iso8601,
+)
+
+
+class ABCOTVSIE(InfoExtractor):
+ IE_NAME = 'abcotvs'
+ _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
+ _TESTS = [
+ {
+ 'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
+ 'info_dict': {
+ 'id': '472581',
+ 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
+ 'ext': 'mp4',
+ 'title': 'East Bay museum celebrates vintage synthesizers',
+ 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'timestamp': 1421123075,
+ 'upload_date': '20150113',
+ 'uploader': 'Jonathan Bloom',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ },
+ {
+ 'url': 'http://abc7news.com/472581',
+ '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') or video_id
+
+ webpage = self._download_webpage(url, display_id)
+
+ m3u8 = self._html_search_meta(
+ 'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
+
+ formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
+ self._sort_formats(formats)
+
+ title = self._og_search_title(webpage).strip()
+ description = self._og_search_description(webpage).strip()
+ thumbnail = self._og_search_thumbnail(webpage)
+ timestamp = parse_iso8601(self._search_regex(
+ r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
+ webpage, 'upload date', fatal=False))
+ uploader = self._search_regex(
+ r'rel="author">([^<]+)</a>',
+ webpage, 'uploader', default=None)
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ 'uploader': uploader,
+ 'formats': formats,
+ }
+
+
+class ABCOTVSClipsIE(InfoExtractor):
+ IE_NAME = 'abcotvs:clips'
+ _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'https://clips.abcotvs.com/kabc/video/214814',
+ 'info_dict': {
+ 'id': '214814',
+ 'ext': 'mp4',
+ 'title': 'SpaceX launch pad explosion destroys rocket, satellite',
+ 'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
+ 'upload_date': '20160901',
+ 'timestamp': 1472756695,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
+ title = video_data['title']
+ formats = self._extract_m3u8_formats(
+ video_data['videoURL'].split('?')[0], video_id, 'mp4')
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': video_data.get('description'),
+ 'thumbnail': video_data.get('thumbnailURL'),
+ 'duration': int_or_none(video_data.get('duration')),
+ 'timestamp': int_or_none(video_data.get('pubDate')),
+ 'formats': formats,
+ }
int_or_none,
float_or_none,
unified_timestamp,
+ urlencode_postdata,
)
class BiliBiliIE(InfoExtractor):
- _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
'skip_download': True,
},
'expected_warnings': ['upload time'],
+ }, {
+ 'url': 'http://bangumi.bilibili.com/anime/v/40068',
+ 'md5': '08d539a0884f3deb7b698fb13ba69696',
+ 'info_dict': {
+ 'id': '40068',
+ 'ext': 'mp4',
+ 'duration': 1402.357,
+ 'title': '混沌武士 : 第7集 四面楚歌 A Risky Racket',
+ 'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
+ 'thumbnail': 're:^http?://.+\.jpg',
+ },
}]
_APP_KEY = '6f90a59ac58a4123'
def _real_extract(self, url):
video_id = self._match_id(url)
-
webpage = self._download_webpage(url, video_id)
- cid = compat_parse_qs(self._search_regex(
- [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
- r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
- webpage, 'player parameters'))['cid'][0]
+ if 'anime/v' not in url:
+ cid = compat_parse_qs(self._search_regex(
+ [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
+ r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
+ webpage, 'player parameters'))['cid'][0]
+ else:
+ js = self._download_json(
+ 'http://bangumi.bilibili.com/web_api/get_source', video_id,
+ data=urlencode_postdata({'episode_id': video_id}),
+ headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+ cid = js['result']['cid']
payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
description = self._html_search_meta('description', webpage)
timestamp = unified_timestamp(self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
+ thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
# TODO 'view_count' requires deobfuscating Javascript
info = {
'title': title,
'description': description,
'timestamp': timestamp,
- 'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
+ 'thumbnail': thumbnail,
'duration': float_or_none(video_info.get('timelength'), scale=1000),
}
return self._extract_cvp_info(
'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
'secure': {
- 'media_src': 'http://apple-secure.cdn.turner.com/toon/big',
+ 'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
},
})
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class CCTVIE(InfoExtractor):
+ _VALID_URL = r'''(?x)https?://(?:.+?\.)?
+ (?:
+ cctv\.(?:com|cn)|
+ cntv\.cn
+ )/
+ (?:
+ video/[^/]+/(?P<id>[0-9a-f]{32})|
+ \d{4}/\d{2}/\d{2}/(?P<display_id>VID[0-9A-Za-z]+)
+ )'''
+ _TESTS = [{
+ 'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
+ 'md5': '819c7b49fc3927d529fb4cd555621823',
+ 'info_dict': {
+ 'id': '454368eb19ad44a1925bf1eb96140a61',
+ 'ext': 'mp4',
+ 'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1',
+ }
+ }, {
+ 'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
+ 'only_matching': True
+ }]
+
+ def _real_extract(self, url):
+ video_id, display_id = re.match(self._VALID_URL, url).groups()
+ if not video_id:
+ webpage = self._download_webpage(url, display_id)
+ video_id = self._search_regex(
+ r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})',
+ webpage, 'video_id')
+ api_data = self._download_json(
+ 'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id)
+ m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url'])
+
+ return {
+ 'id': video_id,
+ 'title': api_data['title'],
+ 'formats': self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False),
+ 'duration': float_or_none(api_data.get('video', {}).get('totalLength')),
+ }
ABCIE,
ABCIViewIE,
)
-from .abc7news import Abc7NewsIE
from .abcnews import (
AbcNewsIE,
AbcNewsVideoIE,
)
+from .abcotvs import (
+ ABCOTVSIE,
+ ABCOTVSClipsIE,
+)
from .academicearth import AcademicEarthCourseIE
from .acast import (
ACastIE,
)
from .cbssports import CBSSportsIE
from .ccc import CCCIE
+from .cctv import CCTVIE
from .cda import CDAIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
)
from .la7 import LA7IE
from .laola1tv import Laola1TvIE
+from .lci import LCIIE
from .lcp import (
LcpPlayIE,
LcpIE,
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .trollvids import TrollvidsIE
+from .trutv import TruTVIE
from .tube8 import Tube8IE
from .tubitv import TubiTvIE
from .tudou import (
)
from .tvigle import TvigleIE
from .tvland import TVLandIE
+from .tvnoe import TVNoeIE
from .tvp import (
TVPEmbedIE,
TVPIE,
# 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 LCIIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
+ _TEST = {
+ 'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html',
+ 'md5': '2fdb2538b884d4d695f9bd2bde137e6c',
+ 'info_dict': {
+ 'id': '13244802',
+ 'ext': 'mp4',
+ 'title': 'Hillary Clinton et sa quinte de toux, en plein meeting',
+ 'description': 'md5:a4363e3a960860132f8124b62f4a01c9',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ wat_id = self._search_regex(r'data-watid=[\'"](\d+)', webpage, 'wat id')
+ return self.url_result('wat:' + wat_id, 'Wat', wat_id)
'height': 360,
'duration': 179,
'filesize': 17822500,
- }
+ },
+ 'skip': 'Video has been removed',
},
{
'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
class NickDeIE(MTVServicesInfoExtractor):
IE_NAME = 'nick.de'
- _VALID_URL = r'https?://(?:www\.)?nick\.de/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+ _VALID_URL = r'https?://(?:www\.)?(?:nick\.de|nickelodeon\.nl)/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
'only_matching': True,
}, {
'url': 'http://www.nick.de/shows/342-icarly',
'only_matching': True,
+ }, {
+ 'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit',
+ 'only_matching': True,
}]
def _real_extract(self, url):
)
-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
'media_src': 'http://ht.cdn.turner.com/%s/big' % site,
},
'secure': {
- 'media_src': 'http://apple-secure.cdn.turner.com/%s/big' % site,
+ 'media_src': 'http://androidhls-secure.cdn.turner.com/%s/big' % site,
'tokenizer_src': 'http://www.%s.com/video/processors/services/token_ipadAdobe.do' % domain,
},
})
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .turner import TurnerBaseIE
+
+
+class TruTVIE(TurnerBaseIE):
+ _VALID_URL = r'https?://(?:www\.)?trutv\.com(?:(?P<path>/shows/[^/]+/videos/[^/?#]+?)\.html|/full-episodes/[^/]+/(?P<id>\d+))'
+ _TEST = {
+ 'url': 'http://www.trutv.com/shows/10-things/videos/you-wont-believe-these-sports-bets.html',
+ 'md5': '2cdc844f317579fed1a7251b087ff417',
+ 'info_dict': {
+ 'id': '/shows/10-things/videos/you-wont-believe-these-sports-bets',
+ 'ext': 'mp4',
+ 'title': 'You Won\'t Believe These Sports Bets',
+ 'description': 'Jamie Lee sits down with a bookie to discuss the bizarre world of illegal sports betting.',
+ 'upload_date': '20130305',
+ }
+ }
+
+ def _real_extract(self, url):
+ path, video_id = re.match(self._VALID_URL, url).groups()
+ if path:
+ data_src = 'http://www.trutv.com/video/cvp/v2/xml/content.xml?id=%s.xml' % path
+ else:
+ data_src = 'http://www.trutv.com/tveverywhere/services/cvpXML.do?titleId=' + video_id
+ return self._extract_cvp_info(
+ data_src, path, {
+ 'secure': {
+ 'media_src': 'http://androidhls-secure.cdn.turner.com/trutv/big',
+ 'tokenizer_src': 'http://www.trutv.com/tveverywhere/processors/services/token_ipadAdobe.do',
+ },
+ })
parse_duration,
xpath_attr,
update_url_query,
- compat_urlparse,
+ ExtractorError,
)
video_data = self._download_xml(data_src, video_id)
video_id = video_data.attrib['id']
title = xpath_text(video_data, 'headline', fatal=True)
+ content_id = xpath_text(video_data, 'contentId') or video_id
# rtmp_src = xpath_text(video_data, 'akamai/src')
# if rtmp_src:
# splited_rtmp_src = rtmp_src.split(',')
# auth = self._download_webpage(
# protected_path_data['tokenizer_src'], query={
# 'path': protected_path,
- # 'videoId': video_id,
+ # 'videoId': content_id,
# 'aifp': aifp,
# })
# token = xpath_text(auth, 'token')
auth = self._download_xml(
secure_path_data['tokenizer_src'], video_id, query={
'path': secure_path,
- 'videoId': video_id,
+ 'videoId': content_id,
})
+ error_msg = xpath_text(auth, 'error/msg')
+ if error_msg:
+ raise ExtractorError(error_msg, expected=True)
token = xpath_text(auth, 'token')
if not token:
continue
formats.extend(self._extract_smil_formats(
video_url, video_id, fatal=False))
elif ext == 'm3u8':
- m3u8_formats = self._extract_m3u8_formats(
- video_url, video_id, 'mp4', m3u8_id=format_id or 'hls',
- fatal=False)
- if m3u8_formats:
- # Sometimes final URLs inside m3u8 are unsigned, let's fix this
- # ourselves
- qs = compat_urlparse.urlparse(video_url).query
- if qs:
- query = compat_urlparse.parse_qs(qs)
- for m3u8_format in m3u8_formats:
- m3u8_format['url'] = update_url_query(m3u8_format['url'], query)
- m3u8_format['extra_param_to_segment_url'] = qs
- formats.extend(m3u8_formats)
+ formats.extend(self._extract_m3u8_formats(
+ video_url, video_id, 'mp4',
+ m3u8_id=format_id or 'hls', fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(video_url, {'hdcore': '3.7.0'}),
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+ clean_html,
+ get_element_by_class,
+ js_to_json,
+)
+
+
+class TVNoeIE(JWPlatformBaseIE):
+ _VALID_URL = r'https?://(www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.tvnoe.cz/video/10362',
+ 'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
+ 'info_dict': {
+ 'id': '10362',
+ 'ext': 'mp4',
+ 'series': 'Noční univerzita',
+ 'title': 'prof. Tomáš Halík, Th.D. - Návrat náboženství a střet civilizací',
+ 'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ iframe_url = self._search_regex(
+ r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')
+
+ ifs_page = self._download_webpage(iframe_url, video_id)
+ jwplayer_data = self._parse_json(
+ self._find_jwplayer_data(ifs_page),
+ video_id, transform_source=js_to_json)
+ info_dict = self._parse_jwplayer_data(
+ jwplayer_data, video_id, require_title=False, base_url=iframe_url)
+
+ info_dict.update({
+ 'id': video_id,
+ 'title': clean_html(get_element_by_class(
+ 'field-name-field-podnazev', webpage)),
+ 'description': clean_html(get_element_by_class(
+ 'field-name-body', webpage)),
+ 'series': clean_html(get_element_by_class('title', webpage))
+ })
+
+ return info_dict
'skip_download': True,
},
'add_ie': [TVPlayIE.ie_key()],
+ }, {
+ # with relatedClips
+ 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
+ 'info_dict': {
+ 'id': '758770',
+ 'ext': 'mp4',
+ 'title': 'Sommaren med YouTube-stjärnorna S01E01',
+ 'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
+ 'series': 'Sommaren med YouTube-stjärnorna',
+ 'season': 'Säsong 1',
+ 'season_number': 1,
+ 'duration': 1326,
+ 'timestamp': 1470905572,
+ 'upload_date': '20160811',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': [TVPlayIE.ie_key()],
}, {
'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
'only_matching': True,
webpage = self._download_webpage(url, video_id)
- video_id = self._search_regex(
- r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](?P<id>\d{6,})',
- webpage, 'video id')
+ video_id = None
+
+ thumbnail = self._og_search_thumbnail(webpage, default=None)
+ if thumbnail:
+ video_id = self._search_regex(
+ r'https?://[^/]+/imagecache/(?:[^/]+/)+seasons/\d+/(\d{6,})/',
+ thumbnail, 'video id', default=None)
+
+ if not video_id:
+ video_id = self._search_regex(
+ r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
+ webpage, 'video id')
return self.url_result('mtg:%s' % video_id, TVPlayIE.ie_key())
def extract_url(path_template, url_type):
req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id)
- head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type)
- red_url = head.geturl()
- if req_url == red_url:
- raise ExtractorError(
- '%s said: Sorry, this video is not available from your country.' % self.IE_NAME,
- expected=True)
- return red_url
+ head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type, fatal=False)
+ if head:
+ red_url = head.geturl()
+ if req_url != red_url:
+ return red_url
+ return None
+
+ def remove_bitrate_limit(manifest_url):
+ return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url)
formats = []
try:
- http_url = extract_url('android5/%s.mp4', 'http')
- m3u8_url = extract_url('ipad/%s.m3u8', 'm3u8')
- m3u8_formats = self._extract_m3u8_formats(
- m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
- formats.extend(m3u8_formats)
- formats.extend(self._extract_f4m_formats(
- m3u8_url.replace('ios.', 'web.').replace('.m3u8', '.f4m'),
- video_id, f4m_id='hds', fatal=False))
- for m3u8_format in m3u8_formats:
- vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr')
- if not vbr or not abr:
- continue
- format_id = m3u8_format['format_id'].replace('hls', 'http')
- fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url)
- if self._is_valid_url(fmt_url, video_id, format_id):
- f = m3u8_format.copy()
- f.update({
- 'url': fmt_url,
- 'format_id': format_id,
- 'protocol': 'http',
- })
- formats.append(f)
+ manifest_urls = self._download_json(
+ 'http://www.wat.tv/get/webhtml/' + video_id, video_id)
+ m3u8_url = manifest_urls.get('hls')
+ if m3u8_url:
+ m3u8_url = remove_bitrate_limit(m3u8_url)
+ m3u8_formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+ if m3u8_formats:
+ formats.extend(m3u8_formats)
+ formats.extend(self._extract_f4m_formats(
+ m3u8_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
+ video_id, f4m_id='hds', fatal=False))
+ http_url = extract_url('android5/%s.mp4', 'http')
+ if http_url:
+ for m3u8_format in m3u8_formats:
+ vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr')
+ if not vbr or not abr:
+ continue
+ format_id = m3u8_format['format_id'].replace('hls', 'http')
+ fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url)
+ if self._is_valid_url(fmt_url, video_id, format_id):
+ f = m3u8_format.copy()
+ f.update({
+ 'url': fmt_url,
+ 'format_id': format_id,
+ 'protocol': 'http',
+ })
+ formats.append(f)
+ mpd_url = manifest_urls.get('mpd')
+ if mpd_url:
+ formats.extend(self._extract_mpd_formats(remove_bitrate_limit(
+ mpd_url), video_id, mpd_id='dash', fatal=False))
self._sort_formats(formats)
except ExtractorError:
abr = 64
projects / youtube-dl / commitdiff