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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     parse_iso8601,
   9     int_or_none,
  10     xpath_attr,
  11     xpath_element,
  12 )
  13
  14
  15 class TwentyFourVideoIE(InfoExtractor):
  16     IE_NAME = '24video'
  17     _VALID_URL = r'https?://(?P<host>(?:www\.)?24video\.(?:net|me|xxx|sex|tube))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
  18
  19     _TESTS = [{
  20         'url': 'http://www.24video.net/video/view/1044982',
  21         'md5': 'e09fc0901d9eaeedac872f154931deeb',
  22         'info_dict': {
  23             'id': '1044982',
  24             'ext': 'mp4',
  25             'title': 'Эротика каменного века',
  26             'description': 'Как смотрели порно в каменном веке.',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'uploader': 'SUPERTELO',
  29             'duration': 31,
  30             'timestamp': 1275937857,
  31             'upload_date': '20100607',
  32             'age_limit': 18,
  33             'like_count': int,
  34             'dislike_count': int,
  35         },
  36     }, {
  37         'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://www.24video.me/video/view/1044982',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://www.24video.tube/video/view/2363750',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         video_id = mobj.group('id')
  50         host = mobj.group('host')
  51
  52         webpage = self._download_webpage(
  53             'http://%s/video/view/%s' % (host, video_id), video_id)
  54
  55         title = self._og_search_title(webpage)
  56         description = self._html_search_regex(
  57             r'<(p|span)[^>]+itemprop="description"[^>]*>(?P<description>[^<]+)</\1>',
  58             webpage, 'description', fatal=False, group='description')
  59         thumbnail = self._og_search_thumbnail(webpage)
  60         duration = int_or_none(self._og_search_property(
  61             'duration', webpage, 'duration', fatal=False))
  62         timestamp = parse_iso8601(self._search_regex(
  63             r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">',
  64             webpage, 'upload date'))
  65
  66         uploader = self._html_search_regex(
  67             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
  68             webpage, 'uploader', fatal=False)
  69
  70         view_count = int_or_none(self._html_search_regex(
  71             r'<span class="video-views">(\d+) просмотр',
  72             webpage, 'view count', fatal=False))
  73         comment_count = int_or_none(self._html_search_regex(
  74             r'<a[^>]+href="#tab-comments"[^>]*>(\d+) комментари',
  75             webpage, 'comment count', fatal=False))
  76
  77         # Sets some cookies
  78         self._download_xml(
  79             r'http://%s/video/xml/%s?mode=init' % (host, video_id),
  80             video_id, 'Downloading init XML')
  81
  82         video_xml = self._download_xml(
  83             'http://%s/video/xml/%s?mode=play' % (host, video_id),
  84             video_id, 'Downloading video XML')
  85
  86         video = xpath_element(video_xml, './/video', 'video', fatal=True)
  87
  88         formats = [{
  89             'url': xpath_attr(video, '', 'url', 'video URL', fatal=True),
  90         }]
  91
  92         like_count = int_or_none(video.get('ratingPlus'))
  93         dislike_count = int_or_none(video.get('ratingMinus'))
  94         age_limit = 18 if video.get('adult') == 'true' else 0
  95
  96         return {
  97             'id': video_id,
  98             'title': title,
  99             'description': description,
 100             'thumbnail': thumbnail,
 101             'uploader': uploader,
 102             'duration': duration,
 103             'timestamp': timestamp,
 104             'view_count': view_count,
 105             'comment_count': comment_count,
 106             'like_count': like_count,
 107             'dislike_count': dislike_count,
 108             'age_limit': age_limit,
 109             'formats': formats,
 110         }