_ Git - youtube-dl/blob - youtube_dl/extractor/beeg.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class BeegIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
  10     _TEST = {
  11         'url': 'http://beeg.com/5416503',
  12         'md5': '634526ae978711f6b748fe0dd6c11f57',
  13         'info_dict': {
  14             'id': '5416503',
  15             'ext': 'mp4',
  16             'title': 'Sultry Striptease',
  17             'description': 'md5:6db3c6177972822aaba18652ff59c773',
  18             'categories': list,  # NSFW
  19             'thumbnail': 're:https?://.*\.jpg$',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         video_url = self._html_search_regex(
  30             r"'480p'\s*:\s*'([^']+)'", webpage, 'video URL')
  31
  32         title = self._html_search_regex(
  33             r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
  34
  35         description = self._html_search_regex(
  36             r'<meta name="description" content="([^"]*)"',
  37             webpage, 'description', fatal=False)
  38         thumbnail = self._html_search_regex(
  39             r'\'previewer.url\'\s*:\s*"([^"]*)"',
  40             webpage, 'thumbnail', fatal=False)
  41
  42         categories_str = self._html_search_regex(
  43             r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
  44         categories = categories_str.split(',')
  45
  46         return {
  47             'id': video_id,
  48             'url': video_url,
  49             'title': title,
  50             'description': description,
  51             'thumbnail': thumbnail,
  52             'categories': categories,
  53         }