youtube_dl/extractor/clipfish.py

   1 import re
   2 import time
   3 import xml.etree.ElementTree
   4
   5 from .common import InfoExtractor
   6
   7
   8 class ClipfishIE(InfoExtractor):
   9     IE_NAME = u'clipfish'
  10
  11     _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
  12     _TEST = {
  13         u'url': u'http://www.clipfish.de/special/supertalent/video/4028320/supertalent-2013-ivana-opacak-singt-nobodys-perfect/',
  14         u'file': u'4028320.f4v',
  15         u'md5': u'5e38bda8c329fbfb42be0386a3f5a382',
  16         u'info_dict': {
  17             u'title': u'Supertalent 2013: Ivana Opacak singt Nobody\'s Perfect',
  18             u'duration': 399,
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group(1)
  25
  26         info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
  27                     (video_id, int(time.time())))
  28         info_xml = self._download_webpage(
  29             info_url, video_id, note=u'Downloading info page')
  30         doc = xml.etree.ElementTree.fromstring(info_xml)
  31         title = doc.find('title').text
  32         video_url = doc.find('filename').text
  33         thumbnail = doc.find('imageurl').text
  34         duration_str = doc.find('duration').text
  35         m = re.match(
  36             r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
  37             duration_str)
  38         if m:
  39             duration = (
  40                 (int(m.group('hours')) * 60 * 60) +
  41                 (int(m.group('minutes')) * 60) +
  42                 (int(m.group('seconds')))
  43             )
  44         else:
  45             duration = None
  46
  47         return {
  48             'id': video_id,
  49             'title': title,
  50             'url': video_url,
  51             'thumbnail': thumbnail,
  52             'duration': duration,
  53         }