from hashlib import sha1
from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlencode
from ..utils import (
- compat_urllib_parse,
- unified_strdate,
ExtractorError,
+ determine_ext,
+ float_or_none,
+ int_or_none,
+ unified_strdate,
)
class ProSiebenSat1IE(InfoExtractor):
IE_NAME = 'prosiebensat1'
IE_DESC = 'ProSiebenSat.1 Digital'
- _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)'
+ _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany|7tv)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
_TESTS = [
{
+ # Tests changes introduced in https://github.com/rg3/youtube-dl/pull/6242
+ # in response to fixing https://github.com/rg3/youtube-dl/issues/6215:
+ # - malformed f4m manifest support
+ # - proper handling of URLs starting with `https?://` in 2.0 manifests
+ # - recursive child f4m manifests extraction
'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
'info_dict': {
'id': '2104602',
- 'ext': 'mp4',
- 'title': 'Staffel 2, Episode 18 - Jahresrückblick',
+ 'ext': 'flv',
+ 'title': 'Episode 18 - Staffel 2',
'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
'upload_date': '20131231',
'duration': 5845.04,
'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
'info_dict': {
'id': '2572814',
- 'ext': 'mp4',
+ 'ext': 'flv',
'title': 'Andreas Kümmert: Rocket Man',
'description': 'md5:6ddb02b0781c6adf778afea606652e38',
'upload_date': '20131017',
'duration': 469.88,
},
'params': {
- # rtmp download
'skip_download': True,
},
},
'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html',
'info_dict': {
'id': '2156342',
- 'ext': 'mp4',
+ 'ext': 'flv',
'title': 'Kurztrips zum Valentinstag',
- 'description': 'Romantischer Kurztrip zum Valentinstag? Wir verraten, was sich hier wirklich lohnt.',
+ 'description': 'Romantischer Kurztrip zum Valentinstag? Nina Heinemann verrät, was sich hier wirklich lohnt.',
'duration': 307.24,
},
'params': {
- # rtmp download
'skip_download': True,
},
},
'info_dict': {
'id': '439664',
'title': 'Episode 8 - Ganze Folge - Playlist',
- 'description': 'Das finale und härteste Duell aller Zeiten ist vorbei! Der Weltmeister für dieses Jahr steht! Alle packenden Duelle der achten Episode von "Joko gegen Klaas - das Duell um die Welt" seht ihr hier noch einmal in voller Länge!',
+ 'description': 'md5:63b8963e71f481782aeea877658dec84',
},
'playlist_count': 2,
},
+ {
+ 'url': 'http://www.7tv.de/circus-halligalli/615-best-of-circus-halligalli-ganze-folge',
+ 'info_dict': {
+ 'id': '4187506',
+ 'ext': 'flv',
+ 'title': 'Best of Circus HalliGalli',
+ 'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9',
+ 'upload_date': '20151229',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
]
_CLIPID_REGEXES = [
r'"clip_id"\s*:\s+"(\d+)"',
r'clipid: "(\d+)"',
r'clip[iI]d=(\d+)',
+ r'clip[iI]d\s*=\s*["\'](\d+)',
r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)",
]
_TITLE_REGEXES = [
r'<header class="clearfix">\s*<h3>(.+?)</h3>',
r'<!-- start video -->\s*<h1>(.+?)</h1>',
r'<h1 class="att-name">\s*(.+?)</h1>',
+ r'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
+ r'<h2 class="video-title" itemprop="name">\s*(.+?)</h2>',
+ r'<div[^>]+id="veeseoTitle"[^>]*>(.+?)</div>',
]
_DESCRIPTION_REGEXES = [
r'<p itemprop="description">\s*(.+?)</p>',
r'<div class="videoDecription">\s*<p><strong>Beschreibung</strong>: (.+?)</p>',
r'<div class="g-plusone" data-size="medium"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>',
r'<p class="att-description">\s*(.+?)\s*</p>',
+ r'<p class="video-description" itemprop="description">\s*(.+?)</p>',
+ r'<div[^>]+id="veeseoDescription"[^>]*>(.+?)</div>',
]
_UPLOAD_DATE_REGEXES = [
r'<meta property="og:published_time" content="(.+?)">',
r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>',
r'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>',
]
- _ITEM_TYPE_REGEXES = [
+ _PAGE_TYPE_REGEXES = [
+ r'<meta name="page_type" content="([^"]+)">',
r"'itemType'\s*:\s*'([^']*)'",
]
- _ITEM_ID_REGEXES = [
+ _PLAYLIST_ID_REGEXES = [
+ r'content[iI]d=(\d+)',
r"'itemId'\s*:\s*'([^']*)'",
]
- _PLAYLIST_CLIPS_REGEXES = [
- r'data-qvt=.+?<a href="([^"]+)"',
+ _PLAYLIST_CLIP_REGEXES = [
+ r'
(?s)data-qvt=.+?<a href="([^"]+)"',
]
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- item_type = self._html_search_regex(self._ITEM_TYPE_REGEXES, webpage, 'item type', default='CLIP')
- if item_type == 'CLIP':
- return self._clip_extract(url, webpage)
- elif item_type == 'PLAYLIST':
- playlist_id = self._html_search_regex(self._ITEM_ID_REGEXES, webpage, 'playlist id')
-
- for regex in self._PLAYLIST_CLIPS_REGEXES:
- playlist_clips = re.findall(regex, webpage, re.DOTALL)
- if playlist_clips:
- title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
- description = self._html_search_regex(self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
- root_url = re.match('(.+?//.+?)/', url).group(1)
-
- return {
- '_type': 'playlist',
- 'id': playlist_id,
- 'title': title,
- 'description': description,
- 'entries': [self._clip_extract(root_url + clip_path) for clip_path in playlist_clips]
- }
- else:
- raise ExtractorError('Unknown item type "%s"' % item_type)
-
- def _clip_extract(self, url, webpage=None):
- if webpage is None:
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
+ def _extract_clip(self, url, webpage):
clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id')
- access_token = 'testclient'
- client_name = 'kolibri-1.2.5'
+ access_token = 'prosieben'
+ client_name = 'kolibri-2.0.19-splec4'
client_location = url
- videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse.urlencode({
+ videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse_urlencode({
'access_token': access_token,
'client_location': client_location,
'client_name': client_name,
'ids': clip_id,
})
- videos = self._download_json(videos_api_url, clip_id, 'Downloading videos JSON')
+ video = self._download_json(videos_api_url, clip_id, 'Downloading videos JSON')[0]
+
+ if video.get('is_protected') is True:
+ raise ExtractorError('This video is DRM protected.', expected=True)
- duration = float(videos[0]['duration'])
- source_ids = [source['id'] for source in videos[0]['sources']]
+ duration = float_or_none(video.get('duration'))
+ source_ids = [source['id'] for source in video['sources']]
source_ids_str = ','.join(map(str, source_ids))
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_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources?%s' % (clip_id, compat_urllib_parse.urlencode({
+ sources_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources?%s' % (clip_id, compat_urllib_parse_urlencode({
'access_token': access_token,
'client_id': client_id,
'client_location': client_location,
client_location, source_ids_str, g, client_name])
.encode('utf-8')).hexdigest()
- url_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url?%s' % (clip_id, compat_urllib_parse.urlencode({
+ url_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url?%s' % (clip_id, compat_urllib_parse_urlencode({
'access_token': access_token,
'client_id': client_id,
'client_location': client_location,
urls_sources = urls_sources.values()
def fix_bitrate(bitrate):
+ bitrate = int_or_none(bitrate)
+ if not bitrate:
+ return None
return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
for source in urls_sources:
protocol = source['protocol']
+ source_url = source['url']
if protocol == 'rtmp' or protocol == 'rtmpe':
- mobj = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', source['url'])
+ mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', 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': mobj.group('url'),
- 'app': mobj.group('app'),
- 'play_path': mobj.group('playpath'),
+ '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',
'vbr': fix_bitrate(source['bitrate']),
'ext': 'mp4',
'format_id': '%s_%s' % (source['cdn'], source['bitrate']),
})
+ elif 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
+ formats.extend(self._extract_f4m_formats(source_url, clip_id))
else:
formats.append({
- 'url': source['url'],
+ 'url': source_url,
'vbr': fix_bitrate(source['bitrate']),
})
'duration': duration,
'formats': formats,
}
+
+ def _extract_playlist(self, url, webpage):
+ playlist_id = self._html_search_regex(
+ self._PLAYLIST_ID_REGEXES, webpage, 'playlist id')
+ for regex in self._PLAYLIST_CLIP_REGEXES:
+ playlist_clips = re.findall(regex, webpage)
+ if playlist_clips:
+ title = self._html_search_regex(
+ self._TITLE_REGEXES, webpage, 'title')
+ description = self._html_search_regex(
+ self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
+ entries = [
+ self.url_result(
+ re.match('(.+?//.+?)/', url).group(1) + clip_path,
+ 'ProSiebenSat1')
+ for clip_path in playlist_clips]
+ return self.playlist_result(entries, playlist_id, title, description)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ page_type = self._search_regex(
+ self._PAGE_TYPE_REGEXES, webpage,
+ 'page type', default='clip').lower()
+ if page_type == 'clip':
+ return self._extract_clip(url, webpage)
+ elif page_type == 'playlist':
+ return self._extract_playlist(url, webpage)
projects / youtube-dl / blobdiff