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     int_or_none,
   9     js_to_json,
  10     orderedSet,
  11     parse_duration,
  12     sanitized_Request,
  13     str_to_int,
  14 )
  15
  16
  17 class XTubeIE(InfoExtractor):
  18     _VALID_URL = r'''(?x)
  19                         (?:
  20                             xtube:|
  21                             https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-)
  22                         )
  23                         (?P<id>[^/?&#]+)
  24                     '''
  25
  26     _TESTS = [{
  27         # old URL schema
  28         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  29         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  30         'info_dict': {
  31             'id': 'kVTUy_G222_',
  32             'ext': 'mp4',
  33             'title': 'strange erotica',
  34             'description': 'contains:an ET kind of thing',
  35             'uploader': 'greenshowers',
  36             'duration': 450,
  37             'view_count': int,
  38             'comment_count': int,
  39             'age_limit': 18,
  40         }
  41     }, {
  42         # new URL schema
  43         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
  44         'only_matching': True,
  45     }, {
  46         'url': 'xtube:625837',
  47         'only_matching': True,
  48     }, {
  49         'url': 'xtube:kVTUy_G222_',
  50         'only_matching': True,
  51     }, {
  52         'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
  53         'only_matching': True,
  54     }]
  55
  56     def _real_extract(self, url):
  57         mobj = re.match(self._VALID_URL, url)
  58         video_id = mobj.group('id')
  59         display_id = mobj.group('display_id')
  60
  61         if not display_id:
  62             display_id = video_id
  63
  64         if video_id.isdigit() and len(video_id) < 11:
  65             url_pattern = 'http://www.xtube.com/video-watch/-%s'
  66         else:
  67             url_pattern = 'http://www.xtube.com/watch.php?v=%s'
  68
  69         webpage = self._download_webpage(
  70             url_pattern % video_id, display_id, headers={
  71                 'Cookie': 'age_verified=1; cookiesAccepted=1',
  72             })
  73
  74         title, thumbnail, duration = [None] * 3
  75
  76         config = self._parse_json(self._search_regex(
  77             r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf)', webpage, 'config',
  78             default='{}'), video_id, transform_source=js_to_json, fatal=False)
  79         if config:
  80             config = config.get('mainRoll')
  81             if isinstance(config, dict):
  82                 title = config.get('title')
  83                 thumbnail = config.get('poster')
  84                 duration = int_or_none(config.get('duration'))
  85                 sources = config.get('sources') or config.get('format')
  86
  87         if not isinstance(sources, dict):
  88             sources = self._parse_json(self._search_regex(
  89                 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
  90                 webpage, 'sources', group='sources'), video_id,
  91                 transform_source=js_to_json)
  92
  93         formats = []
  94         for format_id, format_url in sources.items():
  95             formats.append({
  96                 'url': format_url,
  97                 'format_id': format_id,
  98                 'height': int_or_none(format_id),
  99             })
 100         self._remove_duplicate_formats(formats)
 101         self._sort_formats(formats)
 102
 103         if not title:
 104             title = self._search_regex(
 105                 (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
 106                 webpage, 'title', group='title')
 107         description = self._og_search_description(
 108             webpage, default=None) or self._html_search_meta(
 109             'twitter:description', webpage, default=None) or self._search_regex(
 110             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
 111         uploader = self._search_regex(
 112             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
 113              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
 114             webpage, 'uploader', fatal=False)
 115         if not duration:
 116             duration = parse_duration(self._search_regex(
 117                 r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
 118                 webpage, 'duration', fatal=False))
 119         view_count = str_to_int(self._search_regex(
 120             (r'["\']viewsCount["\'][^>]*>(\d+)\s+views',
 121              r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'),
 122             webpage, 'view count', fatal=False))
 123         comment_count = str_to_int(self._html_search_regex(
 124             r'>Comments? \(([\d,\.]+)\)<',
 125             webpage, 'comment count', fatal=False))
 126
 127         return {
 128             'id': video_id,
 129             'display_id': display_id,
 130             'title': title,
 131             'description': description,
 132             'thumbnail': thumbnail,
 133             'uploader': uploader,
 134             'duration': duration,
 135             'view_count': view_count,
 136             'comment_count': comment_count,
 137             'age_limit': 18,
 138             'formats': formats,
 139         }
 140
 141
 142 class XTubeUserIE(InfoExtractor):
 143     IE_DESC = 'XTube user profile'
 144     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 145     _TEST = {
 146         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 147         'info_dict': {
 148             'id': 'greenshowers-4056496',
 149             'age_limit': 18,
 150         },
 151         'playlist_mincount': 154,
 152     }
 153
 154     def _real_extract(self, url):
 155         user_id = self._match_id(url)
 156
 157         entries = []
 158         for pagenum in itertools.count(1):
 159             request = sanitized_Request(
 160                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 161                 headers={
 162                     'Cookie': 'popunder=4',
 163                     'X-Requested-With': 'XMLHttpRequest',
 164                     'Referer': url,
 165                 })
 166
 167             page = self._download_json(
 168                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 169
 170             html = page.get('html')
 171             if not html:
 172                 break
 173
 174             for video_id in orderedSet([video_id for _, video_id in re.findall(
 175                     r'data-plid=(["\'])(.+?)\1', html)]):
 176                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 177
 178             page_count = int_or_none(page.get('pageCount'))
 179             if not page_count or pagenum == page_count:
 180                 break
 181
 182         playlist = self.playlist_result(entries, user_id)
 183         playlist['age_limit'] = 18
 184         return playlist