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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 class MojvideoIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-.*/(?P<id>[a-f0-9]+)'
   7     _TEST = {
   8         'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906',
   9         'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7',
  10         'info_dict': {
  11             'id': '3d1ed4497707730b2906',
  12             'ext': 'mp4',
  13             'title': 'V avtu pred mano rdečelaska - Alfi Nipič',
  14             'description':'Video: V avtu pred mano rdečelaska - Alfi Nipič',
  15             'height':378,
  16             'width':480
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         video_id = mobj.group('id')
  23
  24         webpage = self._download_webpage(url, video_id)
  25         title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
  26         description = self._search_regex(r'<meta name="description" content="(.*)" />', webpage, 'video description')
  27         final_url = self._html_search_regex(r'mp4: \'(.*)\'', webpage, 'video url')
  28         height=int(self._search_regex(r'<meta name="video_height" content="([0-9]*)" />',webpage,"video height"))
  29         width=int(self._search_regex(r'<meta name="video_width" content="([0-9]*)" />',webpage,"video width"))
  30
  31         return {
  32             'id': video_id,
  33             'title': title,
  34             'description': description,
  35             'ext': 'mp4',
  36             'url': final_url,
  37             'height':height,
  38             'width':width
  39         }