Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/varzesh3.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class Varzesh3IE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?video\.varzesh3\.com/(?:[^/]+/)+(?P<id>[^/]+)/?'
   9     _TEST = {
  10         'url': 'http://video.varzesh3.com/germany/bundesliga/5-%D9%88%D8%A7%DA%A9%D9%86%D8%B4-%D8%A8%D8%B1%D8%AA%D8%B1-%D8%AF%D8%B1%D9%88%D8%A7%D8%B2%D9%87%E2%80%8C%D8%A8%D8%A7%D9%86%D8%A7%D9%86%D8%9B%D9%87%D9%81%D8%AA%D9%87-26-%D8%A8%D9%88%D9%86%D8%AF%D8%B3/',
  11         'md5': '2a933874cb7dce4366075281eb49e855',
  12         'info_dict': {
  13             'id': '76337',
  14             'ext': 'mp4',
  15             'title': '۵ واکنش برتر دروازه‌بانان؛هفته ۲۶ بوندسلیگا',
  16             'description': 'فصل ۲۰۱۵-۲۰۱۴',
  17             'thumbnail': 're:^https?://.*\.jpg$',
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         display_id = self._match_id(url)
  23
  24         webpage = self._download_webpage(url, display_id)
  25
  26         video_url = self._search_regex(
  27             r'<source[^>]+src="([^"]+)"', webpage, 'video url')
  28
  29         title = self._og_search_title(webpage)
  30         description = self._html_search_regex(
  31             r'(?s)<div class="matn">(.+?)</div>',
  32             webpage, 'description', fatal=False)
  33         thumbnail = self._og_search_thumbnail(webpage)
  34
  35         video_id = self._search_regex(
  36             r"<link[^>]+rel='(?:canonical|shortlink)'[^>]+href='/\?p=([^']+)'",
  37             webpage, display_id, default=display_id)
  38
  39         return {
  40             'url': video_url,
  41             'id': video_id,
  42             'title': title,
  43             'description': description,
  44             'thumbnail': thumbnail,
  45         }