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