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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     clean_html,
   8     compat_parse_qs,
   9 )
  10
  11
  12 class Ro220IE(InfoExtractor):
  13     IE_NAME = '220.ro'
  14     _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)'
  15     _TEST = {
  16         "url": "http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
  17         'file': 'LYV6doKo7f.mp4',
  18         'md5': '03af18b73a07b4088753930db7a34add',
  19         'info_dict': {
  20             "title": "Luati-le Banii sez 4 ep 1",
  21             "description": "Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group('video_id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30         flashVars_str = self._search_regex(
  31             r'<param name="flashVars" value="([^"]+)"',
  32             webpage, 'flashVars')
  33         flashVars = compat_parse_qs(flashVars_str)
  34
  35         return {
  36             '_type': 'video',
  37             'id': video_id,
  38             'ext': 'mp4',
  39             'url': flashVars['videoURL'][0],
  40             'title': flashVars['title'][0],
  41             'description': clean_html(flashVars['desc'][0]),
  42             'thumbnail': flashVars['preview'][0],
  43         }