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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7
   8
   9 class LiveLeakIE(InfoExtractor):
  10
  11     _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
  12     IE_NAME = u'liveleak'
  13
  14     def _real_extract(self, url):
  15         mobj = re.match(self._VALID_URL, url)
  16         if mobj is None:
  17             raise ExtractorError(u'Invalid URL: %s' % url)
  18
  19         video_id = mobj.group('video_id')
  20
  21         webpage = self._download_webpage(url, video_id)
  22
  23         video_url = self._search_regex(r'file: "(.*?)",',
  24             webpage, u'video URL')
  25
  26         video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
  27             webpage, u'title').replace('LiveLeak.com -', '').strip()
  28
  29         video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
  30             webpage, u'description', fatal=False)
  31
  32         video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
  33             webpage, u'uploader', fatal=False)
  34
  35         info = {
  36             'id':  video_id,
  37             'url': video_url,
  38             'ext': 'mp4',
  39             'title': video_title,
  40             'description': video_description,
  41             'uploader': video_uploader
  42         }
  43
  44         return [info]