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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import url_basename
   8 from ..compat import compat_urlparse
   9
  10
  11 class VidbitIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?vidbit\.co/watch\?v=(?P<id>[\w-]+)'
  13     _TEST = {
  14         'url': 'http://www.vidbit.co/watch?v=MrM7LeaMJq',
  15         'md5': 'f1a579a93282a78de7e1c53220ef0f12',
  16         'info_dict': {
  17             'id': 'MrM7LeaMJq',
  18             'ext': 'mp4',
  19             'title': 'RoboCop (1987) - Dick You\'re Fired',
  20             'thumbnail': 'http://www.vidbit.co/thumbnails/MrM7LeaMJq.jpg',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         return {
  29             'id': video_id,
  30             'title': self._html_search_regex(r'<h1>(.+)</h1>', webpage, 'title'),
  31             'url': compat_urlparse.urljoin(url, self._html_search_regex(r'file:\s*(["\'])((?:(?!\1).)+)\1',
  32                 webpage, 'video URL', group=2)),
  33             'thumbnail': self._og_search_thumbnail(webpage),
  34             'description': self._html_search_regex(r'description:(["\'])((?:(?!\1).)+)\1',
  35                 webpage, 'description', None, group=2),
  36         }