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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_request,
   9     parse_duration,
  10     str_to_int,
  11 )
  12
  13
  14 class XTubeIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
  16     _TEST = {
  17         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  18         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  19         'info_dict': {
  20             'id': 'kVTUy_G222_',
  21             'ext': 'mp4',
  22             'title': 'strange erotica',
  23             'description': 'surreal gay themed erotica...almost an ET kind of thing',
  24             'uploader': 'greenshowers',
  25             'duration': 450,
  26             'age_limit': 18,
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('videoid')
  33         url = 'http://www.' + mobj.group('url')
  34
  35         req = compat_urllib_request.Request(url)
  36         req.add_header('Cookie', 'age_verified=1')
  37         webpage = self._download_webpage(req, video_id)
  38
  39         video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title')
  40         video_uploader = self._html_search_regex(
  41             r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False)
  42         video_description = self._html_search_regex(
  43             r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False)
  44         duration = parse_duration(self._html_search_regex(
  45             r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False))
  46         view_count = self._html_search_regex(
  47             r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False)
  48         if view_count:
  49             view_count = str_to_int(view_count)
  50         comment_count = self._html_search_regex(
  51             r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False)
  52         if comment_count:
  53             comment_count = str_to_int(comment_count)
  54
  55         player_quality_option = json.loads(self._html_search_regex(
  56             r'playerQualityOption = ({.+?});', webpage, 'player quality option'))
  57
  58         QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080']
  59         formats = [
  60             {
  61                 'url': url,
  62                 'format_id': format_id,
  63                 'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1,
  64             } for format_id, url in player_quality_option.items()
  65         ]
  66         self._sort_formats(formats)
  67
  68         return {
  69             'id': video_id,
  70             'title': video_title,
  71             'uploader': video_uploader,
  72             'description': video_description,
  73             'duration': duration,
  74             'view_count': view_count,
  75             'comment_count': comment_count,
  76             'formats': formats,
  77             'age_limit': 18,
  78         }