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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urlparse
   6
   7
   8 class FczenitIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/(?P<id>[0-9]+)'
  10     _TEST = {
  11         'url': 'http://fc-zenit.ru/video/41044/',
  12         'md5': '0e3fab421b455e970fa1aa3891e57df0',
  13         'info_dict': {
  14             'id': '41044',
  15             'ext': 'mp4',
  16             'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»',
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23
  24         video_title = self._html_search_regex(
  25             r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title')
  26
  27         video_items = self._parse_json(self._search_regex(
  28             r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'),
  29             video_id)
  30
  31         def merge_dicts(*dicts):
  32             ret = {}
  33             for a_dict in dicts:
  34                 ret.update(a_dict)
  35             return ret
  36
  37         formats = [{
  38             'url': compat_urlparse.urljoin(url, video_url),
  39             'tbr': int(tbr),
  40         } for tbr, video_url in merge_dicts(*video_items).items()]
  41
  42         self._sort_formats(formats)
  43
  44         return {
  45             'id': video_id,
  46             'title': video_title,
  47             'formats': formats,
  48         }