_VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
_TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
_MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
+ _TEST = {
+ u'url': u'http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640',
+ u'file': u'14077640.mp4',
+ u'md5': u'6ca8824255460c787376353f9e20bbd8',
+ u'info_dict': {
+ u"title": u"11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
+ },
+ u'skip': u'Requires rtmpdump'
+ }
def _real_extract(self, url):
# determine video id from url
# determine title and media streams from webpage
html = self._download_webpage(url, video_id)
title = re.search(self._TITLE, html).group('title')
- streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
+ streams = [mo.groupdict() for mo in re.finditer(self._MEDIA_STREAM, html)]
if not streams:
assert '"fsk"' in html
raise ExtractorError(u'This video is only available after 8:00 pm')