youtube_dl/extractor/liveleak.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8 )
   9
  10
  11 class LiveLeakIE(InfoExtractor):
  12     _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
  13     _TEST = {
  14         'url': 'http://www.liveleak.com/view?i=757_1364311680',
  15         'file': '757_1364311680.mp4',
  16         'md5': '0813c2430bea7a46bf13acf3406992f4',
  17         'info_dict': {
  18             'description': 'extremely bad day for this guy..!',
  19             'uploader': 'ljfriel2',
  20             'title': 'Most unlucky car accident'
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26
  27         video_id = mobj.group('video_id')
  28         webpage = self._download_webpage(url, video_id)
  29         video_url = self._search_regex(
  30             r'file: "(.*?)",', webpage, 'video URL')
  31
  32         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
  33         video_description = self._og_search_description(webpage)
  34         video_uploader = self._html_search_regex(
  35             r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
  36
  37         return {
  38             'id': video_id,
  39             'url': video_url,
  40             'ext': 'mp4',
  41             'title': video_title,
  42             'description': video_description,
  43             'uploader': video_uploader
  44         }