2 from __future__ import unicode_literals
6 from .common import InfoExtractor
24 class WDRIE(InfoExtractor):
25 _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js'
26 _GEO_COUNTRIES = ['DE']
28 'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js',
32 'title': 'Biathlon-Staffel verpasst Podest bei Olympia-Generalprobe',
33 'upload_date': '20180112',
37 def _real_extract(self, url):
38 video_id = self._match_id(url)
40 metadata = self._download_json(
41 url, video_id, transform_source=strip_jsonp)
43 is_live = metadata.get('mediaType') == 'live'
45 tracker_data = metadata['trackerData']
46 title = tracker_data['trackerClipTitle']
48 media_resource = metadata['mediaResource']
52 # check if the metadata contains a direct URL to a file
53 for kind, media in media_resource.items():
54 if not isinstance(media, dict):
56 if kind not in ('dflt', 'alt'):
59 for tag_name, medium_url in media.items():
60 if tag_name not in ('videoURL', 'audioURL'):
63 ext = determine_ext(medium_url)
65 formats.extend(self._extract_m3u8_formats(
66 medium_url, video_id, 'mp4', 'm3u8_native',
69 manifest_url = update_url_query(
70 medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'})
71 formats.extend(self._extract_f4m_formats(
72 manifest_url, video_id, f4m_id='hds', fatal=False))
74 formats.extend(self._extract_smil_formats(
75 medium_url, 'stream', fatal=False))
80 if ext == 'unknown_video':
81 urlh = self._request_webpage(
82 medium_url, video_id, note='Determining extension')
83 ext = urlhandle_detect_ext(urlh)
85 formats.append(a_format)
87 self._sort_formats(formats)
90 caption_url = media_resource.get('captionURL')
96 captions_hash = media_resource.get('captionsHash')
97 if isinstance(captions_hash, dict):
98 for ext, format_url in captions_hash.items():
99 format_url = url_or_none(format_url)
102 subtitles.setdefault('de', []).append({
104 'ext': determine_ext(format_url, None) or ext,
108 'id': tracker_data.get('trackerClipId', video_id),
109 'title': self._live_title(title) if is_live else title,
110 'alt_title': tracker_data.get('trackerClipSubcategory'),
112 'subtitles': subtitles,
113 'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')),
118 class WDRPageIE(InfoExtractor):
119 _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
120 _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
121 _VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
125 'url': 'http://www1.wdr.de/mediathek/video/sendungen/doku-am-freitag/video-geheimnis-aachener-dom-100.html',
126 # HDS download, MD5 is unstable
130 'display_id': 'doku-am-freitag/video-geheimnis-aachener-dom-100',
131 'title': 'Geheimnis Aachener Dom',
132 'alt_title': 'Doku am Freitag',
133 'upload_date': '20160304',
134 'description': 'md5:87be8ff14d8dfd7a7ee46f0299b52318',
136 'subtitles': {'de': [{
137 'url': 'http://ondemand-ww.wdr.de/medp/fsk0/105/1058683/1058683_12220974.xml',
141 'skip': 'HTTP Error 404: Not Found',
144 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html',
145 'md5': 'f4c1f96d01cf285240f53ea4309663d8',
149 'display_id': 'wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100',
150 'title': 'Schriftstellerin Juli Zeh',
151 'alt_title': 'WDR 3 Gespräch am Samstag',
152 'upload_date': '20160312',
153 'description': 'md5:e127d320bc2b1f149be697ce044a3dd7',
157 'skip': 'HTTP Error 404: Not Found',
160 'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
164 '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}$',
165 'alt_title': 'WDR Fernsehen Live',
166 'upload_date': '20150101',
170 'skip_download': True, # m3u8 download
174 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
175 'playlist_mincount': 7,
177 'id': 'aktuelle-stunde-120',
181 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
185 'upload_date': 're:^[0-9]{8}$',
186 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
188 'skip': 'The id changes from week to week because of the new episode'
191 'url': 'http://www.wdrmaus.de/filme/sachgeschichten/achterbahn.php5',
192 'md5': '803138901f6368ee497b4d195bb164f2',
196 'upload_date': '20130919',
197 'title': 'Sachgeschichte - Achterbahn ',
201 'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
202 # Live stream, MD5 unstable
206 'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
207 'upload_date': '20160101',
210 'skip_download': True, # m3u8 download
214 'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html',
218 'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"',
219 'upload_date': '20180111',
222 'skip_download': True,
226 'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
227 'only_matching': True,
230 'url': 'https://kinder.wdr.de/tv/die-sendung-mit-dem-elefanten/av/video-folge---astronaut-100.html',
231 'only_matching': True,
235 def _real_extract(self, url):
236 mobj = re.match(self._VALID_URL, url)
237 display_id = mobj.group('display_id')
238 webpage = self._download_webpage(url, display_id)
242 # Article with several videos
244 # for wdr.de the data-extension is in a tag with the class "mediaLink"
245 # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
246 # for wdrmaus, in a tag with the class "videoButton" (previously a link
247 # to the page in a multiline "videoLink"-tag)
248 for mobj in re.finditer(
251 (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+|
252 (["\'])videoLink\b.*?\2[\s]*>\n[^\n]*
253 )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3
255 media_link_obj = self._parse_json(
256 mobj.group('data'), display_id, transform_source=js_to_json,
258 if not media_link_obj:
261 media_link_obj, lambda x: x['mediaObj']['url'], compat_str)
263 entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key()))
265 # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html)
269 compat_urlparse.urljoin(url, mobj.group('href')),
270 ie=WDRPageIE.ie_key())
271 for mobj in re.finditer(
272 r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=',
273 webpage) if re.match(self._PAGE_REGEX, mobj.group('href'))
276 return self.playlist_result(entries, playlist_id=display_id)
279 class WDRElefantIE(InfoExtractor):
280 _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)'
282 'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015',
284 'title': 'Folge Oster-Spezial 2015',
288 'upload_date': '20150406'
291 'skip_download': True,
295 def _real_extract(self, url):
296 display_id = self._match_id(url)
298 # Table of Contents seems to always be at this address, so fetch it directly.
299 # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5.
300 table_of_contents = self._download_json(
301 'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5',
303 if display_id not in table_of_contents:
304 raise ExtractorError(
305 'No entry in site\'s table of contents for this URL. '
306 'Is the fragment part of the URL (after the #) correct?',
308 xml_metadata_path = table_of_contents[display_id]['xmlPath']
309 xml_metadata = self._download_xml(
310 'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path,
312 zmdb_url_element = xml_metadata.find('./movie/zmdb_url')
313 if zmdb_url_element is None:
314 raise ExtractorError(
315 '%s is not a video' % display_id, expected=True)
316 return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key())
319 class WDRMobileIE(InfoExtractor):
320 _VALID_URL = r'''(?x)
321 https?://mobile-ondemand\.wdr\.de/
322 .*?/fsk(?P<age_limit>[0-9]+)
324 (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
325 IE_NAME = 'wdr:mobile'
327 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
334 'skip': 'Problems with loading data.'
337 def _real_extract(self, url):
338 mobj = re.match(self._VALID_URL, url)
340 'id': mobj.group('id'),
341 'title': mobj.group('title'),
342 'age_limit': int(mobj.group('age_limit')),
345 'User-Agent': 'mobile',