]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/prosiebensat1.py
2 from __future__
import unicode_literals
6 from hashlib
import sha1
7 from .common
import InfoExtractor
18 class ProSiebenSat1IE(InfoExtractor
):
19 IE_NAME
= 'prosiebensat1'
20 IE_DESC
= 'ProSiebenSat.1 Digital'
21 _VALID_URL
= r
'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)'
25 'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
29 'title': 'Episode 18 - Staffel 2',
30 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
31 'upload_date': '20131231',
36 'skip_download': True,
40 'url': 'http://www.prosieben.de/videokatalog/Gesellschaft/Leben/Trends/video-Lady-Umstyling-f%C3%BCr-Audrina-Rebekka-Audrina-Fergen-billig-aussehen-Battal-Modica-700544.html',
44 'title': 'Lady-Umstyling für Audrina',
45 'description': 'md5:4c16d0c17a3461a0d43ea4084e96319d',
46 'upload_date': '20131014',
51 'skip_download': True,
53 'skip': 'Seems to be broken',
56 'url': 'http://www.prosiebenmaxx.de/tv/experience/video/144-countdown-fuer-die-autowerkstatt-ganze-folge',
60 'title': 'Countdown für die Autowerkstatt',
61 'description': 'md5:809fc051a457b5d8666013bc40698817',
62 'upload_date': '20140223',
67 'skip_download': True,
71 'url': 'http://www.sixx.de/stars-style/video/sexy-laufen-in-ugg-boots-clip',
75 'title': 'Sexy laufen in Ugg Boots',
76 'description': 'md5:edf42b8bd5bc4e5da4db4222c5acb7d6',
77 'upload_date': '20140122',
82 'skip_download': True,
86 'url': 'http://www.sat1.de/film/der-ruecktritt/video/im-interview-kai-wiesinger-clip',
90 'title': 'Im Interview: Kai Wiesinger',
91 'description': 'md5:e4e5370652ec63b95023e914190b4eb9',
92 'upload_date': '20140203',
97 'skip_download': True,
101 'url': 'http://www.kabeleins.de/tv/rosins-restaurants/videos/jagd-auf-fertigkost-im-elsthal-teil-2-ganze-folge',
105 'title': 'Jagd auf Fertigkost im Elsthal - Teil 2',
106 'description': 'md5:2669cde3febe9bce13904f701e774eb6',
107 'upload_date': '20141014',
112 'skip_download': True,
116 'url': 'http://www.ran.de/fussball/bundesliga/video/schalke-toennies-moechte-raul-zurueck-ganze-folge',
120 'title': 'Schalke: Tönnies möchte Raul zurück',
121 'description': 'md5:4b5b271d9bcde223b54390754c8ece3f',
122 'upload_date': '20140226',
127 'skip_download': True,
131 'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
135 'title': 'Andreas Kümmert: Rocket Man',
136 'description': 'md5:6ddb02b0781c6adf778afea606652e38',
137 'upload_date': '20131017',
142 'skip_download': True,
146 'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html',
150 'title': 'Kurztrips zum Valentinstag',
151 'description': 'Romantischer Kurztrip zum Valentinstag? Wir verraten, was sich hier wirklich lohnt.',
156 'skip_download': True,
160 'url': 'http://www.prosieben.de/tv/joko-gegen-klaas/videos/playlists/episode-8-ganze-folge-playlist',
163 'title': 'Episode 8 - Ganze Folge - Playlist',
164 'description': 'md5:63b8963e71f481782aeea877658dec84',
171 r
'"clip_id"\s*:\s+"(\d+)"',
174 r
"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)",
177 r
'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',
178 r
'<header class="clearfix">\s*<h3>(.+?)</h3>',
179 r
'<!-- start video -->\s*<h1>(.+?)</h1>',
180 r
'<h1 class="att-name">\s*(.+?)</h1>',
181 r
'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
183 _DESCRIPTION_REGEXES
= [
184 r
'<p itemprop="description">\s*(.+?)</p>',
185 r
'<div class="videoDecription">\s*<p><strong>Beschreibung</strong>: (.+?)</p>',
186 r
'<div class="g-plusone" data-size="medium"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>',
187 r
'<p class="att-description">\s*(.+?)\s*</p>',
189 _UPLOAD_DATE_REGEXES
= [
190 r
'<meta property="og:published_time" content="(.+?)">',
191 r
'<span>\s*(\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}) \|\s*<span itemprop="duration"',
192 r
'<footer>\s*(\d{2}\.\d{2}\.\d{4}) \d{2}:\d{2} Uhr',
193 r
'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>',
194 r
'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>',
196 _PAGE_TYPE_REGEXES
= [
197 r
'<meta name="page_type" content="([^"]+)">',
198 r
"'itemType'\s*:\s*'([^']*)'",
200 _PLAYLIST_ID_REGEXES
= [
201 r
'content[iI]d=(\d+)',
202 r
"'itemId'\s*:\s*'([^']*)'",
204 _PLAYLIST_CLIP_REGEXES
= [
205 r
'(?s)data-qvt=.+?<a href="([^"]+)"',
208 def _extract_clip(self
, url
, webpage
):
209 clip_id
= self
._html
_search
_regex
(self
._CLIPID
_REGEXES
, webpage
, 'clip id')
211 access_token
= 'prosieben'
212 client_name
= 'kolibri-2.0.19-splec4'
213 client_location
= url
215 videos_api_url
= 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse
.urlencode({
216 'access_token': access_token
,
217 'client_location': client_location
,
218 'client_name': client_name
,
222 videos
= self
._download
_json
(videos_api_url
, clip_id
, 'Downloading videos JSON')
224 duration
= float(videos
[0]['duration'])
225 source_ids
= [source
['id'] for source
in videos
[0]['sources']]
226 source_ids_str
= ','.join(map(str, source_ids
))
228 g
= '01!8d8F_)r9]4s[qeuXfP%'
230 client_id
= g
[:2] + sha1(''.join([clip_id
, g
, access_token
, client_location
, g
, client_name
])
231 .encode('utf-8')).hexdigest()
233 sources_api_url
= 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources?%s' % (clip_id
, compat_urllib_parse
.urlencode({
234 'access_token': access_token
,
235 'client_id': client_id
,
236 'client_location': client_location
,
237 'client_name': client_name
,
240 sources
= self
._download
_json
(sources_api_url
, clip_id
, 'Downloading sources JSON')
241 server_id
= sources
['server_id']
243 client_id
= g
[:2] + sha1(''.join([g
, clip_id
, access_token
, server_id
,
244 client_location
, source_ids_str
, g
, client_name
])
245 .encode('utf-8')).hexdigest()
247 url_api_url
= 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url?%s' % (clip_id
, compat_urllib_parse
.urlencode({
248 'access_token': access_token
,
249 'client_id': client_id
,
250 'client_location': client_location
,
251 'client_name': client_name
,
252 'server_id': server_id
,
253 'source_ids': source_ids_str
,
256 urls
= self
._download
_json
(url_api_url
, clip_id
, 'Downloading urls JSON')
258 title
= self
._html
_search
_regex
(self
._TITLE
_REGEXES
, webpage
, 'title')
259 description
= self
._html
_search
_regex
(self
._DESCRIPTION
_REGEXES
, webpage
, 'description', fatal
=False)
260 thumbnail
= self
._og
_search
_thumbnail
(webpage
)
262 upload_date
= unified_strdate(self
._html
_search
_regex
(
263 self
._UPLOAD
_DATE
_REGEXES
, webpage
, 'upload date', default
=None))
267 urls_sources
= urls
['sources']
268 if isinstance(urls_sources
, dict):
269 urls_sources
= urls_sources
.values()
271 def fix_bitrate(bitrate
):
272 bitrate
= int_or_none(bitrate
)
275 return (bitrate
// 1000) if bitrate
% 1000 == 0 else bitrate
277 for source
in urls_sources
:
278 protocol
= source
['protocol']
279 source_url
= source
['url']
280 if protocol
== 'rtmp' or protocol
== 'rtmpe':
281 mobj
= re
.search(r
'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url
)
284 path
= mobj
.group('path')
285 mp4colon_index
= path
.rfind('mp4:')
286 app
= path
[:mp4colon_index
]
287 play_path
= path
[mp4colon_index
:]
289 'url': '%s/%s' % (mobj
.group('url'), app
),
291 'play_path': play_path
,
292 'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
293 'page_url': 'http://www.prosieben.de',
294 'vbr': fix_bitrate(source
['bitrate']),
296 'format_id': '%s_%s' % (source
['cdn'], source
['bitrate']),
298 elif 'f4mgenerator' in source_url
:
299 manifest
= self
._download
_xml
(
300 source_url
, clip_id
, 'Downloading generated f4m manifest',
301 transform_source
=lambda s
: fix_xml_ampersands(s
).strip())
302 for media
in manifest
.findall('./{http://ns.adobe.com/f4m/2.0}media'):
303 manifest_url
= media
.get('href')
305 formats
.extend(self
._extract
_f
4m
_formats
(
306 manifest_url
, clip_id
, f4m_id
='hds'))
310 'vbr': fix_bitrate(source
['bitrate']),
313 self
._sort
_formats
(formats
)
318 'description': description
,
319 'thumbnail': thumbnail
,
320 'upload_date': upload_date
,
321 'duration': duration
,
325 def _extract_playlist(self
, url
, webpage
):
326 playlist_id
= self
._html
_search
_regex
(
327 self
._PLAYLIST
_ID
_REGEXES
, webpage
, 'playlist id')
328 for regex
in self
._PLAYLIST
_CLIP
_REGEXES
:
329 playlist_clips
= re
.findall(regex
, webpage
)
331 title
= self
._html
_search
_regex
(
332 self
._TITLE
_REGEXES
, webpage
, 'title')
333 description
= self
._html
_search
_regex
(
334 self
._DESCRIPTION
_REGEXES
, webpage
, 'description', fatal
=False)
337 re
.match('(.+?//.+?)/', url
).group(1) + clip_path
,
339 for clip_path
in playlist_clips
]
340 return self
.playlist_result(entries
, playlist_id
, title
, description
)
342 def _real_extract(self
, url
):
343 video_id
= self
._match
_id
(url
)
344 webpage
= self
._download
_webpage
(url
, video_id
)
345 page_type
= self
._search
_regex
(
346 self
._PAGE
_TYPE
_REGEXES
, webpage
,
347 'page type', default
='clip').lower()
348 if page_type
== 'clip':
349 return self
._extract
_clip
(url
, webpage
)
350 elif page_type
== 'playlist':
351 return self
._extract
_playlist
(url
, webpage
)