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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9     str_to_int,
  10     unified_strdate,
  11 )
  12
  13
  14 class RedTubeIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
  16     _TESTS = [{
  17         'url': 'http://www.redtube.com/66418',
  18         'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
  19         'info_dict': {
  20             'id': '66418',
  21             'ext': 'mp4',
  22             'title': 'Sucked on a toilet',
  23             'upload_date': '20120831',
  24             'duration': 596,
  25             'view_count': int,
  26             'age_limit': 18,
  27         }
  28     }, {
  29         'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
  30         'only_matching': True,
  31     }]
  32
  33     @staticmethod
  34     def _extract_urls(webpage):
  35         return re.findall(
  36             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
  37             webpage)
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41         webpage = self._download_webpage(
  42             'http://www.redtube.com/%s' % video_id, video_id)
  43
  44         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
  45             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
  46
  47         title = self._html_search_regex(
  48             (r'<h1 class="videoTitle[^"]*">(?P<title>.+?)</h1>',
  49              r'videoTitle\s*:\s*(["\'])(?P<title>)\1'),
  50             webpage, 'title', group='title')
  51
  52         formats = []
  53         sources = self._parse_json(
  54             self._search_regex(
  55                 r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
  56             video_id, fatal=False)
  57         if sources and isinstance(sources, dict):
  58             for format_id, format_url in sources.items():
  59                 if format_url:
  60                     formats.append({
  61                         'url': format_url,
  62                         'format_id': format_id,
  63                         'height': int_or_none(format_id),
  64                     })
  65         else:
  66             video_url = self._html_search_regex(
  67                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
  68             formats.append({'url': video_url})
  69         self._sort_formats(formats)
  70
  71         thumbnail = self._og_search_thumbnail(webpage)
  72         upload_date = unified_strdate(self._search_regex(
  73             r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<',
  74             webpage, 'upload date', fatal=False))
  75         duration = int_or_none(self._search_regex(
  76             r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
  77         view_count = str_to_int(self._search_regex(
  78             r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)',
  79             webpage, 'view count', fatal=False))
  80
  81         # No self-labeling, but they describe themselves as
  82         # "Home of Videos Porno"
  83         age_limit = 18
  84
  85         return {
  86             'id': video_id,
  87             'ext': 'mp4',
  88             'title': title,
  89             'thumbnail': thumbnail,
  90             'upload_date': upload_date,
  91             'duration': duration,
  92             'view_count': view_count,
  93             'age_limit': age_limit,
  94             'formats': formats,
  95         }