]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/prosiebensat1.py
2 from __future__
import unicode_literals
6 from hashlib
import sha1
7 from .common
import InfoExtractor
8 from ..compat
import compat_str
18 class ProSiebenSat1BaseIE(InfoExtractor
):
19 _GEO_COUNTRIES
= ['DE']
21 _SUPPORTED_PROTOCOLS
= 'dash:clear,hls:clear,progressive:clear'
22 _V4_BASE_URL
= 'https://vas-v4.p7s1video.net/4.0/get'
24 def _extract_video_info(self
, url
, clip_id
):
27 video
= self
._download
_json
(
28 'http://vas.sim-technik.de/vas/live/v2/videos',
29 clip_id
, 'Downloading videos JSON', query
={
30 'access_token': self
._TOKEN
,
31 'client_location': client_location
,
32 'client_name': self
._CLIENT
_NAME
,
36 if video
.get('is_protected') is True:
37 raise ExtractorError('This video is DRM protected.', expected
=True)
41 raw_ct
= self
._ENCRYPTION
_KEY
+ clip_id
+ self
._IV
+ self
._ACCESS
_ID
42 server_token
= (self
._download
_json
(
43 self
._V
4_BASE
_URL
+ 'protocols', clip_id
,
44 'Downloading protocols JSON',
45 headers
=self
.geo_verification_headers(), query
={
46 'access_id': self
._ACCESS
_ID
,
47 'client_token': sha1((raw_ct
).encode()).hexdigest(),
49 }, fatal
=False) or {}).get('server_token')
51 urls
= (self
._download
_json
(
52 self
._V
4_BASE
_URL
+ 'urls', clip_id
, 'Downloading urls JSON', query
={
53 'access_id': self
._ACCESS
_ID
,
54 'client_token': sha1((raw_ct
+ server_token
+ self
._SUPPORTED
_PROTOCOLS
).encode()).hexdigest(),
55 'protocols': self
._SUPPORTED
_PROTOCOLS
,
56 'server_token': server_token
,
58 }, fatal
=False) or {}).get('urls') or {}
59 for protocol
, variant
in urls
.items():
60 source_url
= variant
.get('clear', {}).get('url')
63 if protocol
== 'dash':
64 formats
.extend(self
._extract
_mpd
_formats
(
65 source_url
, clip_id
, mpd_id
=protocol
, fatal
=False))
66 elif protocol
== 'hls':
67 formats
.extend(self
._extract
_m
3u8_formats
(
68 source_url
, clip_id
, 'mp4', 'm3u8_native',
69 m3u8_id
=protocol
, fatal
=False))
73 'format_id': protocol
,
76 source_ids
= [compat_str(source
['id']) for source
in video
['sources']]
78 client_id
= self
._SALT
[:2] + sha1(''.join([clip_id
, self
._SALT
, self
._TOKEN
, client_location
, self
._SALT
, self
._CLIENT
_NAME
]).encode('utf-8')).hexdigest()
80 sources
= self
._download
_json
(
81 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id
,
82 clip_id
, 'Downloading sources JSON', query
={
83 'access_token': self
._TOKEN
,
84 'client_id': client_id
,
85 'client_location': client_location
,
86 'client_name': self
._CLIENT
_NAME
,
88 server_id
= sources
['server_id']
90 def fix_bitrate(bitrate
):
91 bitrate
= int_or_none(bitrate
)
94 return (bitrate
// 1000) if bitrate
% 1000 == 0 else bitrate
96 for source_id
in source_ids
:
97 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()
98 urls
= self
._download
_json
(
99 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id
,
100 clip_id
, 'Downloading urls JSON', fatal
=False, query
={
101 'access_token': self
._TOKEN
,
102 'client_id': client_id
,
103 'client_location': client_location
,
104 'client_name': self
._CLIENT
_NAME
,
105 'server_id': server_id
,
106 'source_ids': source_id
,
110 if urls
.get('status_code') != 0:
111 raise ExtractorError('This video is unavailable', expected
=True)
112 urls_sources
= urls
['sources']
113 if isinstance(urls_sources
, dict):
114 urls_sources
= urls_sources
.values()
115 for source
in urls_sources
:
116 source_url
= source
.get('url')
119 protocol
= source
.get('protocol')
120 mimetype
= source
.get('mimetype')
121 if mimetype
== 'application/f4m+xml' or 'f4mgenerator' in source_url
or determine_ext(source_url
) == 'f4m':
122 formats
.extend(self
._extract
_f
4m
_formats
(
123 source_url
, clip_id
, f4m_id
='hds', fatal
=False))
124 elif mimetype
== 'application/x-mpegURL':
125 formats
.extend(self
._extract
_m
3u8_formats
(
126 source_url
, clip_id
, 'mp4', 'm3u8_native',
127 m3u8_id
='hls', fatal
=False))
128 elif mimetype
== 'application/dash+xml':
129 formats
.extend(self
._extract
_mpd
_formats
(
130 source_url
, clip_id
, mpd_id
='dash', fatal
=False))
132 tbr
= fix_bitrate(source
['bitrate'])
133 if protocol
in ('rtmp', 'rtmpe'):
134 mobj
= re
.search(r
'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url
)
137 path
= mobj
.group('path')
138 mp4colon_index
= path
.rfind('mp4:')
139 app
= path
[:mp4colon_index
]
140 play_path
= path
[mp4colon_index
:]
142 'url': '%s/%s' % (mobj
.group('url'), app
),
144 'play_path': play_path
,
145 'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
146 'page_url': 'http://www.prosieben.de',
149 'format_id': 'rtmp%s' % ('-%d' % tbr
if tbr
else ''),
155 'format_id': 'http%s' % ('-%d' % tbr
if tbr
else ''),
157 self
._sort
_formats
(formats
)
160 'duration': float_or_none(video
.get('duration')),
165 class ProSiebenSat1IE(ProSiebenSat1BaseIE
):
166 IE_NAME
= 'prosiebensat1'
167 IE_DESC
= 'ProSiebenSat.1 Digital'
168 _VALID_URL
= r
'''(?x)
174 prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|7tv|advopedia
176 ran\.de|fem\.com|advopedia\.de|galileo\.tv/video
183 # Tests changes introduced in https://github.com/ytdl-org/youtube-dl/pull/6242
184 # in response to fixing https://github.com/ytdl-org/youtube-dl/issues/6215:
185 # - malformed f4m manifest support
186 # - proper handling of URLs starting with `https?://` in 2.0 manifests
187 # - recursive child f4m manifests extraction
188 'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
192 'title': 'Episode 18 - Staffel 2',
193 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
194 'upload_date': '20131231',
199 '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',
203 'title': 'Lady-Umstyling für Audrina',
204 'description': 'md5:4c16d0c17a3461a0d43ea4084e96319d',
205 'upload_date': '20131014',
210 'skip_download': True,
212 'skip': 'Seems to be broken',
215 'url': 'http://www.prosiebenmaxx.de/tv/experience/video/144-countdown-fuer-die-autowerkstatt-ganze-folge',
219 'title': 'Countdown für die Autowerkstatt',
220 'description': 'md5:809fc051a457b5d8666013bc40698817',
221 'upload_date': '20140223',
226 'skip_download': True,
228 'skip': 'This video is unavailable',
231 'url': 'http://www.sixx.de/stars-style/video/sexy-laufen-in-ugg-boots-clip',
235 'title': 'Sexy laufen in Ugg Boots',
236 'description': 'md5:edf42b8bd5bc4e5da4db4222c5acb7d6',
237 'upload_date': '20140122',
242 'skip_download': True,
244 'skip': 'This video is unavailable',
247 'url': 'http://www.sat1.de/film/der-ruecktritt/video/im-interview-kai-wiesinger-clip',
251 'title': 'Im Interview: Kai Wiesinger',
252 'description': 'md5:e4e5370652ec63b95023e914190b4eb9',
253 'upload_date': '20140203',
258 'skip_download': True,
260 'skip': 'This video is unavailable',
263 'url': 'http://www.kabeleins.de/tv/rosins-restaurants/videos/jagd-auf-fertigkost-im-elsthal-teil-2-ganze-folge',
267 'title': 'Jagd auf Fertigkost im Elsthal - Teil 2',
268 'description': 'md5:2669cde3febe9bce13904f701e774eb6',
269 'upload_date': '20141014',
274 'skip_download': True,
276 'skip': 'This video is unavailable',
279 'url': 'http://www.ran.de/fussball/bundesliga/video/schalke-toennies-moechte-raul-zurueck-ganze-folge',
283 'title': 'Schalke: Tönnies möchte Raul zurück',
284 'description': 'md5:4b5b271d9bcde223b54390754c8ece3f',
285 'upload_date': '20140226',
290 'skip_download': True,
292 'skip': 'This video is unavailable',
295 'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
299 'title': 'Andreas Kümmert: Rocket Man',
300 'description': 'md5:6ddb02b0781c6adf778afea606652e38',
301 'upload_date': '20131017',
305 'skip_download': True,
309 'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html',
313 'title': 'Kurztrips zum Valentinstag',
314 'description': 'Romantischer Kurztrip zum Valentinstag? Nina Heinemann verrät, was sich hier wirklich lohnt.',
318 'skip_download': True,
322 'url': 'http://www.prosieben.de/tv/joko-gegen-klaas/videos/playlists/episode-8-ganze-folge-playlist',
325 'title': 'Episode 8 - Ganze Folge - Playlist',
326 'description': 'md5:63b8963e71f481782aeea877658dec84',
329 'skip': 'This video is unavailable',
332 'url': 'http://www.7tv.de/circus-halligalli/615-best-of-circus-halligalli-ganze-folge',
336 'title': 'Best of Circus HalliGalli',
337 'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9',
338 'upload_date': '20151229',
341 'skip_download': True,
345 # title in <h2 class="subtitle">
346 'url': 'http://www.prosieben.de/stars/oscar-award/videos/jetzt-erst-enthuellt-das-geheimnis-von-emma-stones-oscar-robe-clip',
350 'title': 'Jetzt erst enthüllt: Das Geheimnis von Emma Stones Oscar-Robe',
351 'description': 'md5:e5ace2bc43fadf7b63adc6187e9450b9',
352 'upload_date': '20170302',
355 'skip_download': True,
357 'skip': 'geo restricted to Germany',
360 # geo restricted to Germany
361 'url': 'http://www.kabeleinsdoku.de/tv/mayday-alarm-im-cockpit/video/102-notlandung-im-hudson-river-ganze-folge',
362 'only_matching': True,
365 # geo restricted to Germany
366 'url': 'http://www.sat1gold.de/tv/edel-starck/video/11-staffel-1-episode-1-partner-wider-willen-ganze-folge',
367 'only_matching': True,
370 # geo restricted to Germany
371 'url': 'https://www.galileo.tv/video/diese-emojis-werden-oft-missverstanden',
372 'only_matching': True,
375 'url': 'http://www.sat1gold.de/tv/edel-starck/playlist/die-gesamte-1-staffel',
376 'only_matching': True,
379 'url': 'http://www.advopedia.de/videos/lenssen-klaert-auf/lenssen-klaert-auf-folge-8-staffel-3-feiertage-und-freie-tage',
380 'only_matching': True,
385 _SALT
= '01!8d8F_)r9]4s[qeuXfP%'
386 _CLIENT_NAME
= 'kolibri-2.0.19-splec4'
388 _ACCESS_ID
= 'x_prosiebenmaxx-de'
389 _ENCRYPTION_KEY
= 'Eeyeey9oquahthainoofashoyoikosag'
390 _IV
= 'Aeluchoc6aevechuipiexeeboowedaok'
393 r
'"clip_id"\s*:\s+"(\d+)"',
396 r
'clip[iI][dD]\s*=\s*["\'](\d
+)',
397 r"'itemImageUrl
'\s*:\s*'/dynamic
/thumbnails
/full
/\d
+/(\d
+)",
398 r'proMamsId"\s*:\s*"(\d+)',
399 r'proMamsId"\s
*:\s
*"(\d+)',
402 r'<h2 class="subtitle
" itemprop="name
">\s*(.+?)</h2>',
403 r'<header class="clearfix
">\s*<h3>(.+?)</h3>',
404 r'<!-- start video -->\s*<h1>(.+?)</h1>',
405 r'<h1 class="att
-name
">\s*(.+?)</h1>',
406 r'<header class="module_header
">\s*<h2>([^<]+)</h2>\s*</header>',
407 r'<h2 class="video
-title
" itemprop="name
">\s*(.+?)</h2>',
408 r'<div[^>]+id="veeseoTitle
"[^>]*>(.+?)</div>',
409 r'<h2[^>]+class="subtitle
"[^>]*>([^<]+)</h2>',
411 _DESCRIPTION_REGEXES = [
412 r'<p itemprop="description
">\s*(.+?)</p>',
413 r'<div class="videoDecription
">\s*<p><strong>Beschreibung</strong>: (.+?)</p>',
414 r'<div class="g
-plusone
" data-size="medium
"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>',
415 r'<p class="att
-description
">\s*(.+?)\s*</p>',
416 r'<p class="video
-description
" itemprop="description
">\s*(.+?)</p>',
417 r'<div[^>]+id="veeseoDescription
"[^>]*>(.+?)</div>',
419 _UPLOAD_DATE_REGEXES = [
420 r'<meta property="og
:published_time
" content="(.+?
)">',
421 r'<span>\s*(\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}) \|\s*<span itemprop="duration
"',
422 r'<footer>\s*(\d{2}\.\d{2}\.\d{4}) \d{2}:\d{2} Uhr',
423 r'<span style="padding
-left
: 4px
;line
-height
:20px
; color
:#404040">(\d{2}\.\d{2}\.\d{4})</span>',
424 r
'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>',
426 _PAGE_TYPE_REGEXES
= [
427 r
'<meta name="page_type" content="([^"]+)">',
428 r
"'itemType'\s*:\s*'([^']*)'",
430 _PLAYLIST_ID_REGEXES
= [
431 r
'content[iI]d=(\d+)',
432 r
"'itemId'\s*:\s*'([^']*)'",
434 _PLAYLIST_CLIP_REGEXES
= [
435 r
'(?s)data-qvt=.+?<a href="([^"]+)"',
438 def _extract_clip(self
, url
, webpage
):
439 clip_id
= self
._html
_search
_regex
(
440 self
._CLIPID
_REGEXES
, webpage
, 'clip id')
441 title
= self
._html
_search
_regex
(
442 self
._TITLE
_REGEXES
, webpage
, 'title',
443 default
=None) or self
._og
_search
_title
(webpage
)
444 info
= self
._extract
_video
_info
(url
, clip_id
)
445 description
= self
._html
_search
_regex
(
446 self
._DESCRIPTION
_REGEXES
, webpage
, 'description', default
=None)
447 if description
is None:
448 description
= self
._og
_search
_description
(webpage
)
449 thumbnail
= self
._og
_search
_thumbnail
(webpage
)
450 upload_date
= unified_strdate(self
._html
_search
_regex
(
451 self
._UPLOAD
_DATE
_REGEXES
, webpage
, 'upload date', default
=None))
456 'description': description
,
457 'thumbnail': thumbnail
,
458 'upload_date': upload_date
,
462 def _extract_playlist(self
, url
, webpage
):
463 playlist_id
= self
._html
_search
_regex
(
464 self
._PLAYLIST
_ID
_REGEXES
, webpage
, 'playlist id')
465 playlist
= self
._parse
_json
(
467 r
'var\s+contentResources\s*=\s*(\[.+?\]);\s*</script',
468 webpage
, 'playlist'),
471 for item
in playlist
:
472 clip_id
= item
.get('id') or item
.get('upc')
475 info
= self
._extract
_video
_info
(url
, clip_id
)
478 'title': item
.get('title') or item
.get('teaser', {}).get('headline'),
479 'description': item
.get('teaser', {}).get('description'),
480 'thumbnail': item
.get('poster'),
481 'duration': float_or_none(item
.get('duration')),
482 'series': item
.get('tvShowTitle'),
483 'uploader': item
.get('broadcastPublisher'),
486 return self
.playlist_result(entries
, playlist_id
)
488 def _real_extract(self
, url
):
489 video_id
= self
._match
_id
(url
)
490 webpage
= self
._download
_webpage
(url
, video_id
)
491 page_type
= self
._search
_regex
(
492 self
._PAGE
_TYPE
_REGEXES
, webpage
,
493 'page type', default
='clip').lower()
494 if page_type
== 'clip':
495 return self
._extract
_clip
(url
, webpage
)
496 elif page_type
== 'playlist':
497 return self
._extract
_playlist
(url
, webpage
)
499 raise ExtractorError(
500 'Unsupported page type %s' % page_type
, expected
=True)