_ 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 ..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         # FLV videos with duplicated formats
  43         'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
  44         'md5': 'a406963eb349dd43692ec54631efd88b',
  45         'info_dict': {
  46             'id': '9299752',
  47             'display_id': 'A-Super-Run-Part-1-YT',
  48             'ext': 'flv',
  49             'title': 'A Super Run - Part 1 (YT)',
  50             'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
  51             'uploader': 'tshirtguy59',
  52             'duration': 579,
  53             'view_count': int,
  54             'comment_count': int,
  55             'age_limit': 18,
  56         },
  57     }, {
  58         # new URL schema
  59         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
  60         'only_matching': True,
  61     }, {
  62         'url': 'xtube:625837',
  63         'only_matching': True,
  64     }, {
  65         'url': 'xtube:kVTUy_G222_',
  66         'only_matching': True,
  67     }, {
  68         'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
  69         'only_matching': True,
  70     }]
  71
  72     def _real_extract(self, url):
  73         mobj = re.match(self._VALID_URL, url)
  74         video_id = mobj.group('id')
  75         display_id = mobj.group('display_id')
  76
  77         if not display_id:
  78             display_id = video_id
  79
  80         if video_id.isdigit() and len(video_id) < 11:
  81             url_pattern = 'http://www.xtube.com/video-watch/-%s'
  82         else:
  83             url_pattern = 'http://www.xtube.com/watch.php?v=%s'
  84
  85         webpage = self._download_webpage(
  86             url_pattern % video_id, display_id, headers={
  87                 'Cookie': 'age_verified=1; cookiesAccepted=1',
  88             })
  89
  90         sources = self._parse_json(self._search_regex(
  91             r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
  92             webpage, 'sources', group='sources'), video_id,
  93             transform_source=js_to_json)
  94
  95         formats = []
  96         for format_id, format_url in sources.items():
  97             formats.append({
  98                 'url': format_url,
  99                 'format_id': format_id,
 100                 'height': int_or_none(format_id),
 101             })
 102         self._remove_duplicate_formats(formats)
 103         self._sort_formats(formats)
 104
 105         title = self._search_regex(
 106             (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
 107             webpage, 'title', group='title')
 108         description = self._search_regex(
 109             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
 110         uploader = self._search_regex(
 111             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
 112              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
 113             webpage, 'uploader', fatal=False)
 114         duration = parse_duration(self._search_regex(
 115             r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
 116             webpage, 'duration', fatal=False))
 117         view_count = str_to_int(self._search_regex(
 118             r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
 119             webpage, 'view count', fatal=False))
 120         comment_count = str_to_int(self._html_search_regex(
 121             r'>Comments? \(([\d,\.]+)\)<',
 122             webpage, 'comment count', fatal=False))
 123
 124         return {
 125             'id': video_id,
 126             'display_id': display_id,
 127             'title': title,
 128             'description': description,
 129             'uploader': uploader,
 130             'duration': duration,
 131             'view_count': view_count,
 132             'comment_count': comment_count,
 133             'age_limit': 18,
 134             'formats': formats,
 135         }
 136
 137
 138 class XTubeUserIE(InfoExtractor):
 139     IE_DESC = 'XTube user profile'
 140     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 141     _TEST = {
 142         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 143         'info_dict': {
 144             'id': 'greenshowers-4056496',
 145             'age_limit': 18,
 146         },
 147         'playlist_mincount': 155,
 148     }
 149
 150     def _real_extract(self, url):
 151         user_id = self._match_id(url)
 152
 153         entries = []
 154         for pagenum in itertools.count(1):
 155             request = sanitized_Request(
 156                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 157                 headers={
 158                     'Cookie': 'popunder=4',
 159                     'X-Requested-With': 'XMLHttpRequest',
 160                     'Referer': url,
 161                 })
 162
 163             page = self._download_json(
 164                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 165
 166             html = page.get('html')
 167             if not html:
 168                 break
 169
 170             for video_id in orderedSet([video_id for _, video_id in re.findall(
 171                     r'data-plid=(["\'])(.+?)\1', html)]):
 172                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 173
 174             page_count = int_or_none(page.get('pageCount'))
 175             if not page_count or pagenum == page_count:
 176                 break
 177
 178         playlist = self.playlist_result(entries, user_id)
 179         playlist['age_limit'] = 18
 180         return playlist