_ Git - youtube-dl/blob - youtube_dl/extractor/xtube.py

   1 from __future__ import unicode_literals
   2
   3 import os
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10     parse_duration,
  11     str_to_int,
  12 )
  13
  14
  15 class XTubeIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
  17     _TEST = {
  18         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  19         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  20         'info_dict': {
  21             'id': 'kVTUy_G222_',
  22             'ext': 'mp4',
  23             'title': 'strange erotica',
  24             'description': 'surreal gay themed erotica...almost an ET kind of thing',
  25             'uploader': 'greenshowers',
  26             'duration': 450,
  27             'age_limit': 18,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('videoid')
  34         url = 'http://www.' + mobj.group('url')
  35
  36         req = compat_urllib_request.Request(url)
  37         req.add_header('Cookie', 'age_verified=1')
  38         webpage = self._download_webpage(req, video_id)
  39
  40         video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title')
  41         video_uploader = self._html_search_regex(
  42             r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False)
  43         video_description = self._html_search_regex(
  44             r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False)
  45         video_url = self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, 'video_url').replace('\\/', '/')
  46         duration = parse_duration(self._html_search_regex(
  47             r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False))
  48         view_count = self._html_search_regex(
  49             r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False)
  50         if view_count:
  51             view_count = str_to_int(view_count)
  52         comment_count = self._html_search_regex(
  53             r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False)
  54         if comment_count:
  55             comment_count = str_to_int(comment_count)
  56
  57         path = compat_urllib_parse_urlparse(video_url).path
  58         extension = os.path.splitext(path)[1][1:]
  59         format = path.split('/')[5].split('_')[:2]
  60         format[0] += 'p'
  61         format[1] += 'k'
  62         format = "-".join(format)
  63
  64         return {
  65             'id': video_id,
  66             'title': video_title,
  67             'uploader': video_uploader,
  68             'description': video_description,
  69             'duration': duration,
  70             'view_count': view_count,
  71             'comment_count': comment_count,
  72             'url': video_url,
  73             'ext': extension,
  74             'format': format,
  75             'format_id': format,
  76             'age_limit': 18,
  77         }