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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     int_or_none,
   7     str_to_int,
   8     unified_strdate,
   9 )
  10
  11
  12 class RedTubeIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
  14     _TEST = {
  15         'url': 'http://www.redtube.com/66418',
  16         'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
  17         'info_dict': {
  18             'id': '66418',
  19             'ext': 'mp4',
  20             'title': 'Sucked on a toilet',
  21             'upload_date': '20120831',
  22             'duration': 596,
  23             'view_count': int,
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31
  32         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
  33             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
  34
  35         title = self._html_search_regex(
  36             (r'<h1 class="videoTitle[^"]*">(?P<title>.+?)</h1>',
  37              r'videoTitle\s*:\s*(["\'])(?P<title>)\1'),
  38             webpage, 'title', group='title')
  39
  40         formats = []
  41         sources = self._parse_json(
  42             self._search_regex(
  43                 r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
  44             video_id, fatal=False)
  45         if sources and isinstance(sources, dict):
  46             for format_id, format_url in sources.items():
  47                 if format_url:
  48                     formats.append({
  49                         'url': format_url,
  50                         'format_id': format_id,
  51                         'height': int_or_none(format_id),
  52                     })
  53         else:
  54             video_url = self._html_search_regex(
  55                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
  56             formats.append({'url': video_url})
  57         self._sort_formats(formats)
  58
  59         thumbnail = self._og_search_thumbnail(webpage)
  60         upload_date = unified_strdate(self._search_regex(
  61             r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
  62             webpage, 'upload date', fatal=False))
  63         duration = int_or_none(self._search_regex(
  64             r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
  65         view_count = str_to_int(self._search_regex(
  66             r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
  67             webpage, 'view count', fatal=False))
  68
  69         # No self-labeling, but they describe themselves as
  70         # "Home of Videos Porno"
  71         age_limit = 18
  72
  73         return {
  74             'id': video_id,
  75             'ext': 'mp4',
  76             'title': title,
  77             'thumbnail': thumbnail,
  78             'upload_date': upload_date,
  79             'duration': duration,
  80             'view_count': view_count,
  81             'age_limit': age_limit,
  82             'formats': formats,
  83         }