)
from ..utils import (
determine_ext,
+ dict_get,
ExtractorError,
js_to_json,
strip_jsonp,
class WDRIE(InfoExtractor):
- _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js'
+ __API_URL_TPL = '//deviceids-medp.wdr.de/ondemand/%s/%s'
+ _VALID_URL = r'''(?x)https?://
+ (?:deviceids-medp\.wdr\.de/ondemand/\d+/|
+ kinder\.wdr\.de/(?!mediathek/)[^#?]+-)
+ (?P<id>\d+)\.(?:js|assetjsonp)
+ '''
_GEO_COUNTRIES = ['DE']
- _TEST = {
+ _TESTS = [{
'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js',
'info_dict': {
'id': 'mdb-1557833',
'title': 'Biathlon-Staffel verpasst Podest bei Olympia-Generalprobe',
'upload_date': '20180112',
},
- }
+ }]
+
+ def _asset_url(self, wdr_id):
+ id_len = max(len(wdr_id), 5)
+ return ''.join(('https:', self.__API_URL_TPL % (wdr_id[:id_len - 4], wdr_id, ), '.js'))
def _real_extract(self, url):
video_id = self._match_id(url)
+ if url.startswith('wdr:'):
+ video_id = url[4:]
+ url = self._asset_url(video_id)
+
metadata = self._download_json(
url, video_id, transform_source=strip_jsonp)
return {
'id': tracker_data.get('trackerClipId', video_id),
- 'title': self._live_title(title) if is_live else title,
+ 'title': title,
'alt_title': tracker_data.get('trackerClipSubcategory'),
'formats': formats,
'subtitles': subtitles,
}
-class WDRPageIE(InfoExtractor):
- _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
+class WDRPageIE(WDRIE):
+ _MAUS_REGEX = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/)*?(?P<maus_id>[^/?#.]+)(?:/?|/index\.php5|\.php5)$'
_PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
- _VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
+ _VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _MAUS_REGEX
_TESTS = [
{
{
'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
'info_dict': {
- 'id': 'mdb-1406149',
+ 'id': 'mdb-2296252',
'ext': 'mp4',
- '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}$',
+ '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}$',
'alt_title': 'WDR Fernsehen Live',
- 'upload_date': '20150101',
+ 'upload_date': '20201112',
'is_live': True,
},
'params': {
},
{
'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html',
- 'playlist_mincount': 7,
+ 'playlist_mincount': 6,
'info_dict': {
'id': 'aktuelle-stunde-120',
},
{
'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
'info_dict': {
- 'id': 'mdb-1552552',
+ 'id': 'mdb-2627637',
'ext': 'mp4',
'upload_date': 're:^[0-9]{8}$',
- 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
+ 'title': 're:^Die Sendung (?:mit der Maus )?vom [0-9.]{10}$',
},
'skip': 'The id changes from week to week because of the new episode'
},
'upload_date': '20130919',
'title': 'Sachgeschichte - Achterbahn ',
},
+ 'skip': 'HTTP Error 404: Not Found',
},
{
'url': 'http://www1.wdr.de/radio/player/radioplayer116~_layout-popupVersion.html',
'params': {
'skip_download': True,
},
+ 'skip': 'HTTP Error 404: Not Found',
},
{
'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('display_id')
+ mobj = self._match_valid_url(url)
+ display_id = dict_get(mobj.groupdict(), ('display_id', 'maus_id'), 'wdrmaus')
webpage = self._download_webpage(url, display_id)
entries = []
jsonp_url = try_get(
media_link_obj, lambda x: x['mediaObj']['url'], compat_str)
if jsonp_url:
+ # metadata, or player JS with ['ref'] giving WDR id, or just media, perhaps
+ clip_id = media_link_obj['mediaObj'].get('ref')
+ if jsonp_url.endswith('.assetjsonp'):
+ asset = self._download_json(
+ jsonp_url, display_id, fatal=False, transform_source=strip_jsonp)
+ clip_id = try_get(asset, lambda x: x['trackerData']['trackerClipId'], compat_str)
+ if clip_id:
+ jsonp_url = self._asset_url(clip_id[4:])
entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key()))
# Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html)
class WDRElefantIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)'
_TEST = {
- 'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015',
+ 'url': 'http://www.wdrmaus.de/elefantenseite/#elefantenkino_wippe',
+ # adaptive stream: unstable file MD5
'info_dict': {
- 'title': 'Folge Oster-Spezial 2015',
- 'id': 'mdb-1088195',
+ 'title': 'Wippe',
+ 'id': 'mdb-1198320',
'ext': 'mp4',
'age_limit': None,
- 'upload_date': '20150406'
- },
- 'params': {
- 'skip_download': True,
+ 'upload_date': '20071003'
},
}
/[0-9]+/[0-9]+/
(?P<id>[0-9]+)_(?P<title>[0-9]+)'''
IE_NAME = 'wdr:mobile'
+ _WORKING = False # no such domain
_TEST = {
'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
'info_dict': {
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
+ mobj = self._match_valid_url(url)
return {
'id': mobj.group('id'),
'title': mobj.group('title'),