_ Git - youtube-dl/blob - youtube_dl/extractor/clipfish.py

   1 import re
   2 import time
   3
   4 from .common import InfoExtractor
   5
   6
   7 class ClipfishIE(InfoExtractor):
   8     IE_NAME = u'clipfish'
   9
  10     _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
  11     _TEST = {
  12         u'url': u'http://www.clipfish.de/special/supertalent/video/4028320/supertalent-2013-ivana-opacak-singt-nobodys-perfect/',
  13         u'file': u'4028320.f4v',
  14         u'md5': u'5e38bda8c329fbfb42be0386a3f5a382',
  15         u'info_dict': {
  16             u'title': u'Supertalent 2013: Ivana Opacak singt Nobody\'s Perfect',
  17             u'duration': 399,
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group(1)
  24
  25         info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
  26                     (video_id, int(time.time())))
  27         doc = self._download_xml(
  28             info_url, video_id, note=u'Downloading info page')
  29         title = doc.find('title').text
  30         video_url = doc.find('filename').text
  31         thumbnail = doc.find('imageurl').text
  32         duration_str = doc.find('duration').text
  33         m = re.match(
  34             r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
  35             duration_str)
  36         if m:
  37             duration = (
  38                 (int(m.group('hours')) * 60 * 60) +
  39                 (int(m.group('minutes')) * 60) +
  40                 (int(m.group('seconds')))
  41             )
  42         else:
  43             duration = None
  44
  45         return {
  46             'id': video_id,
  47             'title': title,
  48             'url': video_url,
  49             'thumbnail': thumbnail,
  50             'duration': duration,
  51         }