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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class LiveLeakIE(InfoExtractor):
  10     _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
  11     _TESTS = [{
  12         'url': 'http://www.liveleak.com/view?i=757_1364311680',
  13         'file': '757_1364311680.mp4',
  14         'md5': '0813c2430bea7a46bf13acf3406992f4',
  15         'info_dict': {
  16             'description': 'extremely bad day for this guy..!',
  17             'uploader': 'ljfriel2',
  18             'title': 'Most unlucky car accident'
  19         }
  20     },
  21     {
  22         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
  23         'file': 'f93_1390833151.mp4',
  24         'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
  25         'info_dict': {
  26             'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
  27             'uploader': 'ARD_Stinkt',
  28             'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
  29         }
  30     }]
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34
  35         video_id = mobj.group('video_id')
  36         webpage = self._download_webpage(url, video_id)
  37         sources_raw = self._search_regex(
  38             r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
  39         if sources_raw is None:
  40             sources_raw = '[{ %s}]' % (
  41                 self._search_regex(r'(file: ".*?"),', webpage, 'video URL'))
  42
  43         sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
  44         sources = json.loads(sources_json)
  45
  46         formats = [{
  47             'format_note': s.get('label'),
  48             'url': s['file'],
  49         } for s in sources]
  50         self._sort_formats(formats)
  51
  52         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
  53         video_description = self._og_search_description(webpage)
  54         video_uploader = self._html_search_regex(
  55             r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
  56
  57         return {
  58             'id': video_id,
  59             'title': video_title,
  60             'description': video_description,
  61             'uploader': video_uploader,
  62             'formats': formats,
  63         }