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         'url': 'xtube:kVTUy_G222_',
  49         'only_matching': True,
  50     }]
  51
  52     def _real_extract(self, url):
  53         mobj = re.match(self._VALID_URL, url)
  54         video_id = mobj.group('id')
  55         display_id = mobj.group('display_id')
  56
  57         if not display_id:
  58             display_id = video_id
  59
  60         if video_id.isdigit() and len(video_id) < 11:
  61             url_pattern = 'http://www.xtube.com/video-watch/-%s'
  62         else:
  63             url_pattern = 'http://www.xtube.com/watch.php?v=%s'
  64
  65         webpage = self._download_webpage(
  66             url_pattern % video_id, display_id, headers={
  67                 'Cookie': 'age_verified=1; cookiesAccepted=1',
  68             })
  69
  70         sources = self._parse_json(self._search_regex(
  71             r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),',
  72             webpage, 'sources', group='sources'), video_id)
  73
  74         formats = []
  75         for format_id, format_url in sources.items():
  76             formats.append({
  77                 'url': format_url,
  78                 'format_id': format_id,
  79                 'height': int_or_none(format_id),
  80             })
  81         self._sort_formats(formats)
  82
  83         title = self._search_regex(
  84             (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
  85             webpage, 'title', group='title')
  86         description = self._search_regex(
  87             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
  88         uploader = self._search_regex(
  89             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
  90              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
  91             webpage, 'uploader', fatal=False)
  92         duration = parse_duration(self._search_regex(
  93             r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
  94             webpage, 'duration', fatal=False))
  95         view_count = str_to_int(self._search_regex(
  96             r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
  97             webpage, 'view count', fatal=False))
  98         comment_count = str_to_int(self._html_search_regex(
  99             r'>Comments? \(([\d,\.]+)\)<',
 100             webpage, 'comment count', fatal=False))
 101
 102         return {
 103             'id': video_id,
 104             'display_id': display_id,
 105             'title': title,
 106             'description': description,
 107             'uploader': uploader,
 108             'duration': duration,
 109             'view_count': view_count,
 110             'comment_count': comment_count,
 111             'age_limit': 18,
 112             'formats': formats,
 113         }
 114
 115
 116 class XTubeUserIE(InfoExtractor):
 117     IE_DESC = 'XTube user profile'
 118     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 119     _TEST = {
 120         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 121         'info_dict': {
 122             'id': 'greenshowers-4056496',
 123             'age_limit': 18,
 124         },
 125         'playlist_mincount': 155,
 126     }
 127
 128     def _real_extract(self, url):
 129         user_id = self._match_id(url)
 130
 131         entries = []
 132         for pagenum in itertools.count(1):
 133             request = sanitized_Request(
 134                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 135                 headers={
 136                     'Cookie': 'popunder=4',
 137                     'X-Requested-With': 'XMLHttpRequest',
 138                     'Referer': url,
 139                 })
 140
 141             page = self._download_json(
 142                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 143
 144             html = page.get('html')
 145             if not html:
 146                 break
 147
 148             for video_id in orderedSet([video_id for _, video_id in re.findall(
 149                     r'data-plid=(["\'])(.+?)\1', html)]):
 150                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 151
 152             page_count = int_or_none(page.get('pageCount'))
 153             if not page_count or pagenum == page_count:
 154                 break
 155
 156         playlist = self.playlist_result(entries, user_id)
 157         playlist['age_limit'] = 18
 158         return playlist