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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_iso8601,
   7     int_or_none,
   8     xpath_attr,
   9     xpath_element,
  10 )
  11
  12
  13 class TwentyFourVideoIE(InfoExtractor):
  14     IE_NAME = '24video'
  15     _VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
  16
  17     _TESTS = [{
  18         'url': 'http://www.24video.net/video/view/1044982',
  19         'md5': 'e09fc0901d9eaeedac872f154931deeb',
  20         'info_dict': {
  21             'id': '1044982',
  22             'ext': 'mp4',
  23             'title': 'Эротика каменного века',
  24             'description': 'Как смотрели порно в каменном веке.',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26             'uploader': 'SUPERTELO',
  27             'duration': 31,
  28             'timestamp': 1275937857,
  29             'upload_date': '20100607',
  30             'age_limit': 18,
  31             'like_count': int,
  32             'dislike_count': int,
  33         },
  34     }, {
  35         'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
  36         'only_matching': True,
  37     }, {
  38         'url': 'http://www.24video.me/video/view/1044982',
  39         'only_matching': True,
  40     }]
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44
  45         webpage = self._download_webpage(
  46             'http://www.24video.net/video/view/%s' % video_id, video_id)
  47
  48         title = self._og_search_title(webpage)
  49         description = self._html_search_regex(
  50             r'<(p|span)[^>]+itemprop="description"[^>]*>(?P<description>[^<]+)</\1>',
  51             webpage, 'description', fatal=False, group='description')
  52         thumbnail = self._og_search_thumbnail(webpage)
  53         duration = int_or_none(self._og_search_property(
  54             'duration', webpage, 'duration', fatal=False))
  55         timestamp = parse_iso8601(self._search_regex(
  56             r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">',
  57             webpage, 'upload date'))
  58
  59         uploader = self._html_search_regex(
  60             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
  61             webpage, 'uploader', fatal=False)
  62
  63         view_count = int_or_none(self._html_search_regex(
  64             r'<span class="video-views">(\d+) просмотр',
  65             webpage, 'view count', fatal=False))
  66         comment_count = int_or_none(self._html_search_regex(
  67             r'<a[^>]+href="#tab-comments"[^>]*>(\d+) комментари',
  68             webpage, 'comment count', fatal=False))
  69
  70         # Sets some cookies
  71         self._download_xml(
  72             r'http://www.24video.net/video/xml/%s?mode=init' % video_id,
  73             video_id, 'Downloading init XML')
  74
  75         video_xml = self._download_xml(
  76             'http://www.24video.net/video/xml/%s?mode=play' % video_id,
  77             video_id, 'Downloading video XML')
  78
  79         video = xpath_element(video_xml, './/video', 'video', fatal=True)
  80
  81         formats = [{
  82             'url': xpath_attr(video, '', 'url', 'video URL', fatal=True),
  83         }]
  84
  85         like_count = int_or_none(video.get('ratingPlus'))
  86         dislike_count = int_or_none(video.get('ratingMinus'))
  87         age_limit = 18 if video.get('adult') == 'true' else 0
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'description': description,
  93             'thumbnail': thumbnail,
  94             'uploader': uploader,
  95             'duration': duration,
  96             'timestamp': timestamp,
  97             'view_count': view_count,
  98             'comment_count': comment_count,
  99             'like_count': like_count,
 100             'dislike_count': dislike_count,
 101             'age_limit': age_limit,
 102             'formats': formats,
 103         }