-# coding: utf-8
-from __future__ import unicode_literals
-
import re
from .common import InfoExtractor
compat_urlparse,
)
from ..utils import (
+ ExtractorError,
determine_ext,
dict_get,
- ExtractorError,
js_to_json,
strip_jsonp,
try_get,
unified_strdate,
update_url_query,
- urlhandle_detect_ext,
url_or_none,
+ urlhandle_detect_ext,
)
a_format['ext'] = ext
formats.append(a_format)
- self._sort_formats(formats)
-
caption_url = media_resource.get('captionURL')
if caption_url:
subtitles['de'] = [{
}
-class WDRPageIE(WDRIE):
+class WDRPageIE(WDRIE): # XXX: Do not subclass from concrete IE
_MAUS_REGEX = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/)*?(?P<maus_id>[^/?#.]+)(?:/?|/index\.php5|\.php5)$'
_PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
_VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _MAUS_REGEX
'skip': 'HTTP Error 404: Not Found',
},
{
+ # FIXME: Asset JSON is directly embedded in webpage
'url': 'http://www1.wdr.de/mediathek/video/live/index.html',
'info_dict': {
'id': 'mdb-2296252',
'id': 'mdb-869971',
'ext': 'mp4',
'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'alt_title': 'COSMO Livestream',
+ 'live_status': 'is_live',
'upload_date': '20160101',
},
'params': {
'url': 'https://kinder.wdr.de/tv/die-sendung-mit-dem-elefanten/av/video-folge---astronaut-100.html',
'only_matching': True,
},
+ {
+ 'url': 'https://www1.wdr.de/mediathek/video/sendungen/rockpalast/video-baroness---freak-valley-festival--100.html',
+ 'info_dict': {
+ 'id': 'mdb-2741028',
+ 'ext': 'mp4',
+ 'title': 'Baroness - Freak Valley Festival 2022',
+ 'alt_title': 'Rockpalast',
+ 'upload_date': '20220725',
+ },
+ }
]
def _real_extract(self, url):
# Article with several videos
- # for wdr.de the data-extension is in a tag with the class "mediaLink"
+ # for wdr.de the data-extension-ard is in a tag with the class "mediaLink"
# for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
# for wdrmaus, in a tag with the class "videoButton" (previously a link
# to the page in a multiline "videoLink"-tag)
(?:
(["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+|
(["\'])videoLink\b.*?\2[\s]*>\n[^\n]*
- )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3
+ )data-extension(?:-ard)?=(["\'])(?P<data>(?:(?!\3).)+)\3
''', webpage):
media_link_obj = self._parse_json(
mobj.group('data'), display_id, transform_source=js_to_json,
compat_urlparse.urljoin(url, mobj.group('href')),
ie=WDRPageIE.ie_key())
for mobj in re.finditer(
- r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=',
+ r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension(?:-ard)?=',
webpage) if re.match(self._PAGE_REGEX, mobj.group('href'))
]
'title': 'Wippe',
'id': 'mdb-1198320',
'ext': 'mp4',
- 'age_limit': None,
'upload_date': '20071003'
},
}