_ Git - youtube-dl/blob - youtube_dl/extractor/ir90tv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class Ir90TvIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?90tv\.ir/video/(?P<id>[0-9]+)/.*'
   9     _TEST = {
  10         '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',
  11         'md5': '411dbd94891381960cb9e13daa47a869',
  12         'info_dict': {
  13             'id': '95719',
  14             'ext': 'mp4',
  15             'title': 'شایعات نقل و انتقالات مهم فوتبال اروپا 94/02/18',
  16             'thumbnail': 're:^https?://.*\.jpg$',
  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         # TODO more code goes here, for example ...
  25         title = self._html_search_regex(
  26             r'<title>\n90tv.ir :: (.*?)</title>', webpage, 'title')
  27
  28         video_url = self._search_regex(
  29             r'<source[^>]+src="([^"]+)"', webpage, 'video url')
  30
  31         thumbnail = self._search_regex(r'poster="([^"]+)"', webpage, 'thumbnail url')
  32         print thumbnail
  33
  34
  35         return {
  36             'url': video_url,
  37             'id': video_id,
  38             'title': title,
  39             'video_url' : video_url,
  40             'thumbnail' : thumbnail,
  41         }