youtube_dlc/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     ExtractorError,
   9     int_or_none,
  10     js_to_json,
  11     orderedSet,
  12     parse_duration,
  13     sanitized_Request,
  14     str_to_int,
  15 )
  16
  17
  18 class XTubeIE(InfoExtractor):
  19     _VALID_URL = r'''(?x)
  20                         (?:
  21                             xtube:|
  22                             https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-)
  23                         )
  24                         (?P<id>[^/?&#]+)
  25                     '''
  26
  27     _TESTS = [{
  28         # old URL schema
  29         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  30         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  31         'info_dict': {
  32             'id': 'kVTUy_G222_',
  33             'ext': 'mp4',
  34             'title': 'strange erotica',
  35             'description': 'contains:an ET kind of thing',
  36             'uploader': 'greenshowers',
  37             'duration': 449,
  38             'view_count': int,
  39             'comment_count': int,
  40             'age_limit': 18,
  41         }
  42     }, {
  43         # new URL schema
  44         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
  45         'only_matching': True,
  46     }, {
  47         'url': 'xtube:625837',
  48         'only_matching': True,
  49     }, {
  50         'url': 'xtube:kVTUy_G222_',
  51         'only_matching': True,
  52     }, {
  53         'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
  54         'only_matching': True,
  55     }]
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         video_id = mobj.group('id')
  60         display_id = mobj.group('display_id')
  61
  62         if not display_id:
  63             display_id = video_id
  64
  65         if video_id.isdigit() and len(video_id) < 11:
  66             url_pattern = 'http://www.xtube.com/video-watch/-%s'
  67         else:
  68             url_pattern = 'http://www.xtube.com/watch.php?v=%s'
  69
  70         webpage = self._download_webpage(
  71             url_pattern % video_id, display_id, headers={
  72                 'Cookie': 'age_verified=1; cookiesAccepted=1',
  73             })
  74
  75         title, thumbnail, duration = [None] * 3
  76
  77         json_config_string = self._search_regex(
  78             r'playerConf=({.+?}),loaderConf',
  79             webpage, 'config', default=None)
  80         if not json_config_string:
  81             raise ExtractorError("Could not extract video player data")
  82
  83         json_config_string = json_config_string.replace("!0", "true").replace("!1", "false")
  84
  85         config = self._parse_json(json_config_string, video_id, transform_source=js_to_json, fatal=False)
  86         if not config:
  87             raise ExtractorError("Could not extract video player data")
  88
  89         config = config.get('mainRoll')
  90         if isinstance(config, dict):
  91             title = config.get('title')
  92             thumbnail = config.get('poster')
  93             duration = int_or_none(config.get('duration'))
  94             sources = config.get('sources') or config.get('format')
  95
  96         if not isinstance(sources, dict):
  97             sources = self._parse_json(self._search_regex(
  98                 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
  99                 webpage, 'sources', group='sources'), video_id,
 100                 transform_source=js_to_json)
 101
 102         formats = []
 103         for format_id, format_url in sources.items():
 104             formats.append({
 105                 'url': format_url,
 106                 'format_id': format_id,
 107                 'height': int_or_none(format_id),
 108             })
 109         self._remove_duplicate_formats(formats)
 110         self._sort_formats(formats)
 111
 112         if not title:
 113             title = self._search_regex(
 114                 (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
 115                 webpage, 'title', group='title')
 116         description = self._og_search_description(
 117             webpage, default=None) or self._html_search_meta(
 118             'twitter:description', webpage, default=None) or self._search_regex(
 119             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
 120         uploader = self._search_regex(
 121             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
 122              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
 123             webpage, 'uploader', fatal=False)
 124         if not duration:
 125             duration = parse_duration(self._search_regex(
 126                 r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
 127                 webpage, 'duration', fatal=False))
 128         view_count = str_to_int(self._search_regex(
 129             (r'["\']viewsCount["\'][^>]*>(\d+)\s+views',
 130              r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'),
 131             webpage, 'view count', fatal=False))
 132         comment_count = str_to_int(self._html_search_regex(
 133             r'>Comments? \(([\d,\.]+)\)<',
 134             webpage, 'comment count', fatal=False))
 135
 136         return {
 137             'id': video_id,
 138             'display_id': display_id,
 139             'title': title,
 140             'description': description,
 141             'thumbnail': thumbnail,
 142             'uploader': uploader,
 143             'duration': duration,
 144             'view_count': view_count,
 145             'comment_count': comment_count,
 146             'age_limit': 18,
 147             'formats': formats,
 148         }
 149
 150
 151 class XTubeUserIE(InfoExtractor):
 152     IE_DESC = 'XTube user profile'
 153     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 154     _TEST = {
 155         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 156         'info_dict': {
 157             'id': 'greenshowers-4056496',
 158             'age_limit': 18,
 159         },
 160         'playlist_mincount': 154,
 161     }
 162
 163     def _real_extract(self, url):
 164         user_id = self._match_id(url)
 165
 166         entries = []
 167         for pagenum in itertools.count(1):
 168             request = sanitized_Request(
 169                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 170                 headers={
 171                     'Cookie': 'popunder=4',
 172                     'X-Requested-With': 'XMLHttpRequest',
 173                     'Referer': url,
 174                 })
 175
 176             page = self._download_json(
 177                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 178
 179             html = page.get('html')
 180             if not html:
 181                 break
 182
 183             for video_id in orderedSet([video_id for _, video_id in re.findall(
 184                     r'data-plid=(["\'])(.+?)\1', html)]):
 185                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 186
 187             page_count = int_or_none(page.get('pageCount'))
 188             if not page_count or pagenum == page_count:
 189                 break
 190
 191         playlist = self.playlist_result(entries, user_id)
 192         playlist['age_limit'] = 18
 193         return playlist