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