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

   1 from __future__ import unicode_literals
   2
   3 import itertools
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urllib_parse_unquote
   8 from ..utils import (
   9     int_or_none,
  10     sanitized_Request,
  11     str_to_int,
  12 )
  13
  14
  15 class XTubeIE(InfoExtractor):
  16     _VALID_URL = r'(?:xtube:|https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P<display_id>[^/]+)-))(?P<id>[^/?&#]+)'
  17
  18     _TESTS = [{
  19         # old URL schema
  20         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  21         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  22         'info_dict': {
  23             'id': 'kVTUy_G222_',
  24             'ext': 'mp4',
  25             'title': 'strange erotica',
  26             'description': 'contains:an ET kind of thing',
  27             'uploader': 'greenshowers',
  28             'duration': 450,
  29             'age_limit': 18,
  30         }
  31     }, {
  32         # new URL schema
  33         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
  34         'only_matching': True,
  35     }, {
  36         'url': 'xtube:625837',
  37         'only_matching': True,
  38     }]
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('id')
  43         display_id = mobj.group('display_id')
  44
  45         if not display_id:
  46             display_id = video_id
  47             url = 'http://www.xtube.com/watch.php?v=%s' % video_id
  48
  49         req = sanitized_Request(url)
  50         req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
  51         webpage = self._download_webpage(req, display_id)
  52
  53         flashvars = self._parse_json(
  54             self._search_regex(
  55                 r'xt\.playerOps\s*=\s*({.+?});', webpage, 'player ops'),
  56             video_id)['flashvars']
  57
  58         title = flashvars.get('title') or self._search_regex(
  59             r'<h1>([^<]+)</h1>', webpage, 'title')
  60         video_url = compat_urllib_parse_unquote(flashvars['video_url'])
  61         duration = int_or_none(flashvars.get('video_duration'))
  62
  63         uploader = self._search_regex(
  64             r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
  65             webpage, 'uploader', fatal=False)
  66         description = self._search_regex(
  67             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
  68         view_count = str_to_int(self._search_regex(
  69             r'<dt>Views:</dt>\s*<dd>([\d,\.]+)</dd>',
  70             webpage, 'view count', fatal=False))
  71         comment_count = str_to_int(self._html_search_regex(
  72             r'>Comments? \(([\d,\.]+)\)<',
  73             webpage, 'comment count', fatal=False))
  74
  75         return {
  76             'id': video_id,
  77             'display_id': display_id,
  78             'url': video_url,
  79             'title': title,
  80             'description': description,
  81             'uploader': uploader,
  82             'duration': duration,
  83             'view_count': view_count,
  84             'comment_count': comment_count,
  85             'age_limit': 18,
  86         }
  87
  88
  89 class XTubeUserIE(InfoExtractor):
  90     IE_DESC = 'XTube user profile'
  91     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
  92     _TEST = {
  93         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
  94         'info_dict': {
  95             'id': 'greenshowers-4056496',
  96             'age_limit': 18,
  97         },
  98         'playlist_mincount': 155,
  99     }
 100
 101     def _real_extract(self, url):
 102         user_id = self._match_id(url)
 103
 104         entries = []
 105         for pagenum in itertools.count(1):
 106             request = sanitized_Request(
 107                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 108                 headers={
 109                     'Cookie': 'popunder=4',
 110                     'X-Requested-With': 'XMLHttpRequest',
 111                     'Referer': url,
 112                 })
 113
 114             page = self._download_json(
 115                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 116
 117             html = page.get('html')
 118             if not html:
 119                 break
 120
 121             for _, video_id in re.findall(r'data-plid=(["\'])(.+?)\1', html):
 122                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 123
 124             page_count = int_or_none(page.get('pageCount'))
 125             if not page_count or pagenum == page_count:
 126                 break
 127
 128         playlist = self.playlist_result(entries, user_id)
 129         playlist['age_limit'] = 18
 130         return playlist