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     _TEST = {
  14         u'url': u'http://www.liveleak.com/view?i=757_1364311680',
  15         u'file': u'757_1364311680.mp4',
  16         u'md5': u'0813c2430bea7a46bf13acf3406992f4',
  17         u'info_dict': {
  18             u"description": u"extremely bad day for this guy..!",
  19             u"uploader": u"ljfriel2",
  20             u"title": u"Most unlucky car accident"
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         if mobj is None:
  27             raise ExtractorError(u'Invalid URL: %s' % url)
  28
  29         video_id = mobj.group('video_id')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         video_url = self._search_regex(r'file: "(.*?)",',
  34             webpage, u'video URL')
  35
  36         video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
  37             webpage, u'title').replace('LiveLeak.com -', '').strip()
  38
  39         video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
  40             webpage, u'description', fatal=False)
  41
  42         video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>',
  43             webpage, u'uploader', fatal=False)
  44
  45         info = {
  46             'id':  video_id,
  47             'url': video_url,
  48             'ext': 'mp4',
  49             'title': video_title,
  50             'description': video_description,
  51             'uploader': video_uploader
  52         }
  53
  54         return [info]