2 from __future__ import unicode_literals
6 from .common import InfoExtractor
23 class WDRIE(InfoExtractor):
24 _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js'
25 _GEO_COUNTRIES = ['DE']
27 'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js',
30 'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100',
32 'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen',
33 'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.',
34 'upload_date': '20160615',
36 'skip': 'Geo-restricted to Germany',
39 def _real_extract(self, url):
40 video_id = self._match_id(url)
42 metadata = self._download_json(
43 url, video_id, transform_source=strip_jsonp)
45 is_live = metadata.get('mediaType') == 'live'
47 tracker_data = metadata['trackerData']
48 media_resource = metadata['mediaResource']
52 # check if the metadata contains a direct URL to a file
53 for kind, media_resource in media_resource.items():
54 if kind not in ('dflt', 'alt'):
57 for tag_name, medium_url in media_resource.items():
58 if tag_name not in ('videoURL', 'audioURL'):
61 ext = determine_ext(medium_url)
63 formats.extend(self._extract_m3u8_formats(
64 medium_url, video_id, 'mp4', 'm3u8_native',
67 manifest_url = update_url_query(
68 medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
69 formats.extend(self._extract_f4m_formats(
70 manifest_url, video_id, f4m_id='hds', fatal=False))
72 formats.extend(self._extract_smil_formats(
73 medium_url, 'stream', fatal=False))
78 if ext == 'unknown_video':
79 urlh = self._request_webpage(
80 medium_url, video_id, note='Determining extension')
81 ext = urlhandle_detect_ext(urlh)
83 formats.append(a_format)
85 self._sort_formats(formats)
88 caption_url = media_resource.get('captionURL')
95 title = tracker_data['trackerClipTitle']
98 'id': tracker_data.get('trackerClipId', video_id),
99 'title': self._live_title(title) if is_live else title,
100 'alt_title': tracker_data.get('trackerClipSubcategory'),
102 'subtitles': subtitles,
103 'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')),
108 class WDRPageIE(InfoExtractor):
109 _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
110 _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
111 _VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
115 'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
116 # HDS download, MD5 is unstable
120 'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100',
121 'title': 'Geheimnis Aachener Dom',
122 'alt_title': 'Doku am Freitag',
123 'upload_date': '20160304',
124 'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
126 'subtitles': {'de': [{
127 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
131 'skip': 'HTTP Error 404: Not Found',
134 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
135 'md5': 'f4c1f96d01cf285240f53ea4309663d8',
139 'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100',
140 'title': 'Schriftstellerin Juli Zeh',
141 'alt_title': 'WDR 3 Gespräch am Samstag',
142 'upload_date': '20160312',
143 'description': 'md5:e127d320bc2b1f149be697ce044a3dd7',
147 'skip': 'HTTP Error 404: Not Found',
150 'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
154 'title': r're:^WDR Fernsehen im Livestream \(nur in Deutschland erreichbar\) [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
155 'alt_title': 'WDR Fernsehen Live',
156 'upload_date': '20150101',
160 'skip_download': True, # m3u8 download
164 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
165 'playlist_mincount': 7,
167 'id': 'aktuelle-stunde-120',
171 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
175 'upload_date': 're:^[0-9]{8}$',
176 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
178 'skip': 'The id changes from week to week because of the new episode'
181 'url': 'http://www.wdrmaus.de/filme/sachgeschichten/achterbahn.php5',
182 'md5': '803138901f6368ee497b4d195bb164f2',
186 'upload_date': '20130919',
187 'title': 'Sachgeschichte - Achterbahn ',
191 'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
192 # Live stream, MD5 unstable
196 'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
197 'upload_date': '20160101',
200 'skip_download': True, # m3u8 download
204 'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html',
208 'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"',
209 'upload_date': '20180111',
212 'skip_download': True,
216 'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
217 'only_matching': True,
221 def _real_extract(self, url):
222 mobj = re.match(self._VALID_URL, url)
223 display_id = mobj.group('display_id')
224 webpage = self._download_webpage(url, display_id)
228 # Article with several videos
230 # for wdr.de the data-extension is in a tag with the class "mediaLink"
231 # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
232 # for wdrmaus, in a tag with the class "videoButton" (previously a link
233 # to the page in a multiline "videoLink"-tag)
234 for mobj in re.finditer(
237 (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+|
238 (["\'])videoLink\b.*?\2[\s]*>\n[^\n]*
239 )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3
241 media_link_obj = self._parse_json(
242 mobj.group('data'), display_id, transform_source=js_to_json,
244 if not media_link_obj:
247 media_link_obj, lambda x: x['mediaObj']['url'], compat_str)
249 entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key()))
251 # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html)
255 compat_urlparse.urljoin(url, mobj.group('href')),
256 ie=WDRPageIE.ie_key())
257 for mobj in re.finditer(
258 r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=',
259 webpage) if re.match(self._PAGE_REGEX, mobj.group('href'))
262 return self.playlist_result(entries, playlist_id=display_id)
265 class WDRElefantIE(InfoExtractor):
266 _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)'
268 'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015',
270 'title': 'Folge Oster-Spezial 2015',
274 'upload_date': '20150406'
277 'skip_download': True,
281 def _real_extract(self, url):
282 display_id = self._match_id(url)
284 # Table of Contents seems to always be at this address, so fetch it directly.
285 # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5.
286 table_of_contents = self._download_json(
287 'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5',
289 if display_id not in table_of_contents:
290 raise ExtractorError(
291 'No entry in site\'s table of contents for this URL. '
292 'Is the fragment part of the URL (after the #) correct?',
294 xml_metadata_path = table_of_contents[display_id]['xmlPath']
295 xml_metadata = self._download_xml(
296 'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path,
298 zmdb_url_element = xml_metadata.find('./movie/zmdb_url')
299 if zmdb_url_element is None:
300 raise ExtractorError(
301 '%s is not a video' % display_id, expected=True)
302 return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key())
305 class WDRMobileIE(InfoExtractor):
306 _VALID_URL = r'''(?x)
307 https?://mobile-ondemand\.wdr\.de/
308 .*?/fsk(?P<age_limit>[0-9]+)
310 (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
311 IE_NAME = 'wdr:mobile'
313 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
320 'skip': 'Problems with loading data.'
323 def _real_extract(self, url):
324 mobj = re.match(self._VALID_URL, url)
326 'id': mobj.group('id'),
327 'title': mobj.group('title'),
328 'age_limit': int(mobj.group('age_limit')),
331 'User-Agent': 'mobile',