2 from __future__ import unicode_literals
6 from hashlib import sha1
7 from .common import InfoExtractor
16 class ProSiebenSat1IE(InfoExtractor):
17 IE_NAME = 'prosiebensat1'
18 IE_DESC = 'ProSiebenSat.1 Digital'
19 _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)'
23 'url': 'http://www.prosieben.de/tv/circus-halligalli/videos/218-staffel-2-episode-18-jahresrueckblick-ganze-folge',
27 'title': 'Staffel 2, Episode 18 - Jahresrückblick',
28 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
29 'upload_date': '20131231',
34 'skip_download': True,
38 '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',
42 'title': 'Lady-Umstyling für Audrina',
43 'description': 'md5:4c16d0c17a3461a0d43ea4084e96319d',
44 'upload_date': '20131014',
49 'skip_download': True,
51 'skip': 'Seems to be broken',
54 'url': 'http://www.prosiebenmaxx.de/yep/one-piece/video/148-folge-48-gold-rogers-heimat-ganze-folge',
58 'title': 'Folge 48: Gold Rogers Heimat',
59 'description': 'Ruffy erreicht die Insel, auf der der berühmte Gold Roger lebte und hingerichtet wurde.',
60 'upload_date': '20140226',
65 'skip_download': True,
69 'url': 'http://www.sixx.de/stars-style/video/sexy-laufen-in-ugg-boots-clip',
73 'title': 'Sexy laufen in Ugg Boots',
74 'description': 'md5:edf42b8bd5bc4e5da4db4222c5acb7d6',
75 'upload_date': '20140122',
80 'skip_download': True,
84 'url': 'http://www.sat1.de/film/der-ruecktritt/video/im-interview-kai-wiesinger-clip',
88 'title': 'Im Interview: Kai Wiesinger',
89 'description': 'md5:e4e5370652ec63b95023e914190b4eb9',
90 'upload_date': '20140225',
95 'skip_download': True,
99 'url': 'http://www.kabeleins.de/tv/rosins-restaurants/videos/jagd-auf-fertigkost-im-elsthal-teil-2-ganze-folge',
103 'title': 'Jagd auf Fertigkost im Elsthal - Teil 2',
104 'description': 'md5:2669cde3febe9bce13904f701e774eb6',
105 'upload_date': '20140225',
110 'skip_download': True,
114 'url': 'http://www.ran.de/fussball/bundesliga/video/schalke-toennies-moechte-raul-zurueck-ganze-folge',
118 'title': 'Schalke: Tönnies möchte Raul zurück',
119 'description': 'md5:4b5b271d9bcde223b54390754c8ece3f',
120 'upload_date': '20140226',
125 'skip_download': True,
129 'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
133 'title': 'Andreas Kümmert: Rocket Man',
134 'description': 'md5:6ddb02b0781c6adf778afea606652e38',
135 'upload_date': '20131017',
140 'skip_download': True,
144 'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html',
148 'title': 'Kurztrips zum Valentinstag',
149 'description': 'md5:8ba6301e70351ae0bedf8da00f7ba528',
150 'upload_date': '20130206',
155 'skip_download': True,
161 r'"clip_id"\s*:\s+"(\d+)"',
165 r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',
166 r'<header class="clearfix">\s*<h3>(.+?)</h3>',
167 r'<!-- start video -->\s*<h1>(.+?)</h1>',
168 r'<div class="ep-femvideos-pi4-video-txt">\s*<h2>(.+?)</h2>',
170 _DESCRIPTION_REGEXES = [
171 r'<p itemprop="description">\s*(.+?)</p>',
172 r'<div class="videoDecription">\s*<p><strong>Beschreibung</strong>: (.+?)</p>',
173 r'<div class="g-plusone" data-size="medium"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>',
174 r'<p>(.+?)</p>\s*<div class="ep-femvideos-pi4-video-footer">',
176 _UPLOAD_DATE_REGEXES = [
177 r'<meta property="og:published_time" content="(.+?)">',
178 r'<span>\s*(\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}) \|\s*<span itemprop="duration"',
179 r'<footer>\s*(\d{2}\.\d{2}\.\d{4}) \d{2}:\d{2} Uhr',
180 r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>',
181 r'(\d{2}\.\d{2}\.\d{4}) \| \d{2}:\d{2} Min<br/>',
184 def _real_extract(self, url):
185 mobj = re.match(self._VALID_URL, url)
186 video_id = mobj.group('id')
188 page = self._download_webpage(url, video_id, 'Downloading page')
190 def extract(patterns, name, page, fatal=False):
191 for pattern in patterns:
192 mobj = re.search(pattern, page)
194 return clean_html(mobj.group(1))
196 raise RegexNotFoundError(u'Unable to extract %s' % name)
199 clip_id = extract(self._CLIPID_REGEXES, 'clip id', page, fatal=True)
201 access_token = 'testclient'
202 client_name = 'kolibri-1.2.5'
203 client_location = url
205 videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse.urlencode({
206 'access_token': access_token,
207 'client_location': client_location,
208 'client_name': client_name,
212 videos = self._download_json(videos_api_url, clip_id, 'Downloading videos JSON')
214 duration = float(videos[0]['duration'])
215 source_ids = [source['id'] for source in videos[0]['sources']]
216 source_ids_str = ','.join(map(str, source_ids))
218 g = '01!8d8F_)r9]4s[qeuXfP%'
220 client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name])
221 .encode('utf-8')).hexdigest()
223 sources_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources?%s' % (clip_id, compat_urllib_parse.urlencode({
224 'access_token': access_token,
225 'client_id': client_id,
226 'client_location': client_location,
227 'client_name': client_name,
230 sources = self._download_json(sources_api_url, clip_id, 'Downloading sources JSON')
231 server_id = sources['server_id']
233 client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id,
234 client_location, source_ids_str, g, client_name])
235 .encode('utf-8')).hexdigest()
237 url_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url?%s' % (clip_id, compat_urllib_parse.urlencode({
238 'access_token': access_token,
239 'client_id': client_id,
240 'client_location': client_location,
241 'client_name': client_name,
242 'server_id': server_id,
243 'source_ids': source_ids_str,
246 urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON')
248 title = extract(self._TITLE_REGEXES, 'title', page, fatal=True)
249 description = extract(self._DESCRIPTION_REGEXES, 'description', page)
250 thumbnail = self._og_search_thumbnail(page)
252 upload_date = extract(self._UPLOAD_DATE_REGEXES, 'upload date', page)
254 upload_date = unified_strdate(upload_date)
258 urls_sources = urls['sources']
259 if isinstance(urls_sources, dict):
260 urls_sources = urls_sources.values()
262 def fix_bitrate(bitrate):
263 return bitrate / 1000 if bitrate % 1000 == 0 else bitrate
265 for source in urls_sources:
266 protocol = source['protocol']
267 if protocol == 'rtmp' or protocol == 'rtmpe':
268 mobj = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', source['url'])
272 'url': mobj.group('url'),
273 'app': mobj.group('app'),
274 'play_path': mobj.group('playpath'),
275 'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
276 'page_url': 'http://www.prosieben.de',
277 'vbr': fix_bitrate(source['bitrate']),
279 'format_id': '%s_%s' % (source['cdn'], source['bitrate']),
283 'url': source['url'],
284 'vbr': fix_bitrate(source['bitrate']),
287 self._sort_formats(formats)
292 'description': description,
293 'thumbnail': thumbnail,
294 'upload_date': upload_date,
295 'duration': duration,