youtube_dl/extractor/ir90tv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import remove_start
   6
   7
   8 class Ir90TvIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?90tv\.ir/video/(?P<id>[0-9]+)/.*'
  10     _TESTS = [{
  11         'url': 'http://90tv.ir/video/95719/%D8%B4%D8%A7%DB%8C%D8%B9%D8%A7%D8%AA-%D9%86%D9%82%D9%84-%D9%88-%D8%A7%D9%86%D8%AA%D9%82%D8%A7%D9%84%D8%A7%D8%AA-%D9%85%D9%87%D9%85-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7-940218',
  12         'md5': '411dbd94891381960cb9e13daa47a869',
  13         'info_dict': {
  14             'id': '95719',
  15             'ext': 'mp4',
  16             'title': 'شایعات نقل و انتقالات مهم فوتبال اروپا 94/02/18',
  17             'thumbnail': r're:^https?://.*\.jpg$',
  18         }
  19     }, {
  20         'url': 'http://www.90tv.ir/video/95719/%D8%B4%D8%A7%DB%8C%D8%B9%D8%A7%D8%AA-%D9%86%D9%82%D9%84-%D9%88-%D8%A7%D9%86%D8%AA%D9%82%D8%A7%D9%84%D8%A7%D8%AA-%D9%85%D9%87%D9%85-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7-940218',
  21         'only_matching': True,
  22     }]
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         title = remove_start(self._html_search_regex(
  29             r'<title>([^<]+)</title>', webpage, 'title'), '90tv.ir :: ')
  30
  31         video_url = self._search_regex(
  32             r'<source[^>]+src="([^"]+)"', webpage, 'video url')
  33
  34         thumbnail = self._search_regex(r'poster="([^"]+)"', webpage, 'thumbnail url', fatal=False)
  35
  36         return {
  37             'url': video_url,
  38             'id': video_id,
  39             'title': title,
  40             'video_url': video_url,
  41             'thumbnail': thumbnail,
  42         }