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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class FczenitIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P<id>[0-9]+)'
  11     _TEST = {
  12         'url': 'http://fc-zenit.ru/video/gl6785/',
  13         'md5': '458bacc24549173fe5a5aa29174a5606',
  14         'info_dict': {
  15             'id': '6785',
  16             'ext': 'mp4',
  17             'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         video_title = self._html_search_regex(r'<div class=\"photoalbum__title\">([^<]+)', webpage, 'title')
  26
  27         bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL')
  28         bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw)
  29
  30         formats = [{
  31             'url': furl,
  32             'tbr': tbr,
  33         } for furl, tbr in bitrates]
  34
  35         self._sort_formats(formats)
  36
  37         return {
  38             'id': video_id,
  39             'title': video_title,
  40             'formats': formats,
  41         }