2 from __future__ import unicode_literals
6 from .common import InfoExtractor
18 class WDRBaseIE(InfoExtractor):
19 def _extract_wdr_video(self, webpage, display_id):
20 # for wdr.de the data-extension is in a tag with the class "mediaLink"
21 # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
22 # for wdrmaus, in a tag with the class "videoButton" (previously a link
23 # to the page in a multiline "videoLink"-tag)
24 json_metadata = self._html_search_regex(
25 r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
26 webpage, 'media link', default=None, flags=re.MULTILINE)
31 media_link_obj = self._parse_json(json_metadata, display_id,
32 transform_source=js_to_json)
33 jsonp_url = media_link_obj['mediaObj']['url']
35 metadata = self._download_json(
36 jsonp_url, display_id, transform_source=strip_jsonp)
38 metadata_tracker_data = metadata['trackerData']
39 metadata_media_resource = metadata['mediaResource']
43 # check if the metadata contains a direct URL to a file
44 for kind, media_resource in metadata_media_resource.items():
45 if kind not in ('dflt', 'alt'):
48 for tag_name, medium_url in media_resource.items():
49 if tag_name not in ('videoURL', 'audioURL'):
52 ext = determine_ext(medium_url)
54 formats.extend(self._extract_m3u8_formats(
55 medium_url, display_id, 'mp4', 'm3u8_native',
58 manifest_url = update_url_query(
59 medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
60 formats.extend(self._extract_f4m_formats(
61 manifest_url, display_id, f4m_id='hds', fatal=False))
63 formats.extend(self._extract_smil_formats(
64 medium_url, 'stream', fatal=False))
69 if ext == 'unknown_video':
70 urlh = self._request_webpage(
71 medium_url, display_id, note='Determining extension')
72 ext = urlhandle_detect_ext(urlh)
74 formats.append(a_format)
76 self._sort_formats(formats)
79 caption_url = metadata_media_resource.get('captionURL')
86 title = metadata_tracker_data['trackerClipTitle']
89 'id': metadata_tracker_data.get('trackerClipId', display_id),
90 'display_id': display_id,
92 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'),
94 'subtitles': subtitles,
95 'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')),
99 class WDRIE(WDRBaseIE):
100 _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
101 _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html'
102 _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
106 'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
107 # HDS download, MD5 is unstable
111 'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100',
112 'title': 'Geheimnis Aachener Dom',
113 'alt_title': 'Doku am Freitag',
114 'upload_date': '20160304',
115 'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
117 'subtitles': {'de': [{
118 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
124 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
125 'md5': 'f4c1f96d01cf285240f53ea4309663d8',
129 'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100',
130 'title': 'Schriftstellerin Juli Zeh',
131 'alt_title': 'WDR 3 Gespräch am Samstag',
132 'upload_date': '20160312',
133 'description': 'md5:e127d320bc2b1f149be697ce044a3dd7',
139 'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
143 'display_id': 'index',
144 'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
145 'alt_title': 'WDR Fernsehen Live',
147 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
152 'skip_download': True, # m3u8 download
156 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
157 'playlist_mincount': 8,
159 'id': 'aktuelle-stunde/aktuelle-stunde-120',
163 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
167 'upload_date': 're:^[0-9]{8}$',
168 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
169 'description': 'Die Seite mit der Maus -',
171 'skip': 'The id changes from week to week because of the new episode'
174 'url': 'http://www.wdrmaus.de/filme/sachgeschichten/achterbahn.php5',
175 'md5': '803138901f6368ee497b4d195bb164f2',
179 'upload_date': '20130919',
180 'title': 'Sachgeschichte - Achterbahn ',
181 'description': 'Die Seite mit der Maus -',
185 'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
186 # Live stream, MD5 unstable
190 'title': 'COSMO Livestream',
191 'description': 'md5:2309992a6716c347891c045be50992e4',
192 'upload_date': '20160101',
197 def _real_extract(self, url):
198 mobj = re.match(self._VALID_URL, url)
199 url_type = mobj.group('type')
200 page_url = mobj.group('page_url')
201 display_id = mobj.group('display_id')
202 webpage = self._download_webpage(url, display_id)
204 info_dict = self._extract_wdr_video(webpage, display_id)
208 self.url_result(page_url + href[0], 'WDR')
209 for href in re.findall(
210 r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX,
214 if entries: # Playlist page
215 return self.playlist_result(entries, playlist_id=display_id)
217 raise ExtractorError('No downloadable streams found', expected=True)
219 is_live = url_type == 'live'
223 'title': self._live_title(info_dict['title']),
226 elif 'upload_date' not in info_dict:
227 info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date'))
230 'description': self._html_search_meta('Description', webpage),
237 class WDRMobileIE(InfoExtractor):
238 _VALID_URL = r'''(?x)
239 https?://mobile-ondemand\.wdr\.de/
240 .*?/fsk(?P<age_limit>[0-9]+)
242 (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
243 IE_NAME = 'wdr:mobile'
245 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
252 'skip': 'Problems with loading data.'
255 def _real_extract(self, url):
256 mobj = re.match(self._VALID_URL, url)
258 'id': mobj.group('id'),
259 'title': mobj.group('title'),
260 'age_limit': int(mobj.group('age_limit')),
263 'User-Agent': 'mobile',