youtube_dl/extractor/varzesh3.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7 import re
   8
   9
  10 class Varzesh3IE(InfoExtractor):
  11     _VALID_URL = r'(?P<url>(https?://(?:www\.)?video\.varzesh3\.com)/(?P<id>.+))'
  12     _TEST ={
  13         '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/',
  14         'md5': '2a933874cb7dce4366075281eb49e855',
  15         'info_dict': {
  16             'url': 'http://dl1.video.varzesh3.com/video/clip94/1/video/namayeshi/saves_week26.mp4',
  17             'id': '76337',
  18             'ext': 'mp4',
  19             'title': '۵ واکنش برتر دروازه‌بانان؛هفته ۲۶ بوندسلیگا',
  20             'thumbnail': 'http://video.varzesh3.com/wp-content/uploads/230315_saves_week26.jpg',
  21             'description': 'فصل ۲۰۱۵-۲۰۱۴',
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27         webpage = self._download_webpage(url, video_id)
  28
  29         if not 'shortlink' in webpage:
  30             raise ExtractorError('URL has no videos or there is a problem.')
  31
  32         title = self._html_search_regex(r'meta[^>]+property="og:title"[^>]+content="([^"]+)"', webpage, 'title')
  33         video_link = self._html_search_regex(r'source[^>]+src="([^"]+)"', webpage, 'video_link')
  34         vid_id = self._html_search_regex(r"link[^>]+rel='canonical'[^>]+href='\/\?p=([^']+)'\/>", webpage, 'vid_id')
  35         try:
  36             description = self._html_search_regex(r'<div class="matn">(.*?)</div>', webpage, 'description', flags=re.DOTALL)
  37         except:
  38             description = title
  39         thumbnail = self._html_search_regex(r'link[^>]+rel="image_src"[^>]+href="([^"]+)"', webpage, 'thumbnail')
  40
  41         return {
  42             'url': video_link,
  43             'id': vid_id,
  44             'title': title,
  45             'ext': video_link.split(".")[-1],
  46             'description': description,
  47             'thumbnail': thumbnail,
  48         }