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 ..utils import (
   8     int_or_none,
   9     orderedSet,
  10     parse_duration,
  11     sanitized_Request,
  12     str_to_int,
  13 )
  14
  15
  16 class XTubeIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18                         (?:
  19                             xtube:|
  20                             https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P<display_id>[^/]+)-)
  21                         )
  22                         (?P<id>[^/?&#]+)
  23                     '''
  24
  25     _TESTS = [{
  26         # old URL schema
  27         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  28         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  29         'info_dict': {
  30             'id': 'kVTUy_G222_',
  31             'ext': 'mp4',
  32             'title': 'strange erotica',
  33             'description': 'contains:an ET kind of thing',
  34             'uploader': 'greenshowers',
  35             'duration': 450,
  36             'view_count': int,
  37             'comment_count': int,
  38             'age_limit': 18,
  39         }
  40     }, {
  41         # new URL schema
  42         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
  43         'only_matching': True,
  44     }, {
  45         'url': 'xtube:625837',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_extract(self, url):
  50         mobj = re.match(self._VALID_URL, url)
  51         video_id = mobj.group('id')
  52         display_id = mobj.group('display_id')
  53
  54         if not display_id:
  55             display_id = video_id
  56             url = 'http://www.xtube.com/video-watch/-%s' % video_id
  57
  58         req = sanitized_Request(url)
  59         req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
  60         webpage = self._download_webpage(req, display_id)
  61
  62         sources = self._parse_json(self._search_regex(
  63             r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),',
  64             webpage, 'sources', group='sources'), video_id)
  65
  66         formats = []
  67         for format_id, format_url in sources.items():
  68             formats.append({
  69                 'url': format_url,
  70                 'format_id': format_id,
  71                 'height': int_or_none(format_id),
  72             })
  73         self._sort_formats(formats)
  74
  75         title = self._search_regex(
  76             (r'<h1>(?P<title>[^<]+)</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
  77             webpage, 'title', group='title')
  78         description = self._search_regex(
  79             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
  80         uploader = self._search_regex(
  81             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
  82              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
  83             webpage, 'uploader', fatal=False)
  84         duration = parse_duration(self._search_regex(
  85             r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
  86             webpage, 'duration', fatal=False))
  87         view_count = str_to_int(self._search_regex(
  88             r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
  89             webpage, 'view count', fatal=False))
  90         comment_count = str_to_int(self._html_search_regex(
  91             r'>Comments? \(([\d,\.]+)\)<',
  92             webpage, 'comment count', fatal=False))
  93
  94         return {
  95             'id': video_id,
  96             'display_id': display_id,
  97             'title': title,
  98             'description': description,
  99             'uploader': uploader,
 100             'duration': duration,
 101             'view_count': view_count,
 102             'comment_count': comment_count,
 103             'age_limit': 18,
 104             'formats': formats,
 105         }
 106
 107
 108 class XTubeUserIE(InfoExtractor):
 109     IE_DESC = 'XTube user profile'
 110     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 111     _TEST = {
 112         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 113         'info_dict': {
 114             'id': 'greenshowers-4056496',
 115             'age_limit': 18,
 116         },
 117         'playlist_mincount': 155,
 118     }
 119
 120     def _real_extract(self, url):
 121         user_id = self._match_id(url)
 122
 123         entries = []
 124         for pagenum in itertools.count(1):
 125             request = sanitized_Request(
 126                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 127                 headers={
 128                     'Cookie': 'popunder=4',
 129                     'X-Requested-With': 'XMLHttpRequest',
 130                     'Referer': url,
 131                 })
 132
 133             page = self._download_json(
 134                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 135
 136             html = page.get('html')
 137             if not html:
 138                 break
 139
 140             for video_id in orderedSet([video_id for _, video_id in re.findall(
 141                     r'data-plid=(["\'])(.+?)\1', html)]):
 142                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 143
 144             page_count = int_or_none(page.get('pageCount'))
 145             if not page_count or pagenum == page_count:
 146                 break
 147
 148         playlist = self.playlist_result(entries, user_id)
 149         playlist['age_limit'] = 18
 150         return playlist