Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ro220.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_html,
   6     compat_parse_qs,
   7 )
   8
   9
  10 class Ro220IE(InfoExtractor):
  11     IE_NAME = '220.ro'
  12     _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)'
  13     _TEST = {
  14         u"url": u"http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
  15         u'file': u'LYV6doKo7f.mp4',
  16         u'md5': u'03af18b73a07b4088753930db7a34add',
  17         u'info_dict': {
  18             u"title": u"Luati-le Banii sez 4 ep 1",
  19             u"description": u"Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('video_id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28         flashVars_str = self._search_regex(
  29             r'<param name="flashVars" value="([^"]+)"',
  30             webpage, u'flashVars')
  31         flashVars = compat_parse_qs(flashVars_str)
  32
  33         info = {
  34             '_type': 'video',
  35             'id': video_id,
  36             'ext': 'mp4',
  37             'url': flashVars['videoURL'][0],
  38             'title': flashVars['title'][0],
  39             'description': clean_html(flashVars['desc'][0]),
  40             'thumbnail': flashVars['preview'][0],
  41         }
  42         return info