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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7
   8
   9 class TruTubeIE(InfoExtractor):
  10     _VALID_URL = r'(?:https?://)?(?:www\.)?(?P<url>trutube\.tv/video/(?P<videoid>.*/.*))'
  11     _TEST = {
  12         'url': ('http://www.trutube.tv/video/20814/Ernst-Zundel-met-les-Jui'
  13                 'fs-en-guarde-VOSTFR'),
  14         'md5': '9973aa3c2870626799d2ac4e36cfc3dc',
  15         'info_dict': {
  16             u"title": u"TruTube.TV - Spitting in the face of die-versity",
  17             u"ext": u"mp4"
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23
  24         video_id = mobj.group('videoid')
  25
  26         # Get webpage content
  27         webpage = self._download_webpage(url, video_id)
  28
  29         # Get the video title
  30         video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
  31                                               webpage, 'title').strip()
  32
  33         video_url = self._search_regex(r'(http://.*\.(?:mp4|flv))',
  34                                        webpage, u'video URL')
  35
  36         ext = video_url[-3:]
  37
  38         return {
  39             'id': video_id,
  40             'url': video_url,
  41             'title': video_title,
  42             'ext': ext
  43             }