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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     int_or_none,
   9     qualities,
  10     determine_ext,
  11 )
  12
  13
  14 class SunPornoIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:(?:www\.)?sunporno\.com/videos|embeds\.sunporno\.com/embed)/(?P<id>\d+)'
  16     _TESTS = [{
  17         'url': 'http://www.sunporno.com/videos/807778/',
  18         'md5': '507887e29033502f29dba69affeebfc9',
  19         'info_dict': {
  20             'id': '807778',
  21             'ext': 'mp4',
  22             'title': 'md5:0a400058e8105d39e35c35e7c5184164',
  23             'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'duration': 302,
  26             'age_limit': 18,
  27         }
  28     }, {
  29         'url': 'http://embeds.sunporno.com/embed/807778',
  30         'only_matching': True,
  31     }]
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         webpage = self._download_webpage(
  37             'http://www.sunporno.com/videos/%s' % video_id, video_id)
  38
  39         title = self._html_search_regex(
  40             r'<title>([^<]+)</title>', webpage, 'title')
  41         description = self._html_search_meta(
  42             'description', webpage, 'description')
  43         thumbnail = self._html_search_regex(
  44             r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
  45
  46         duration = parse_duration(self._search_regex(
  47             (r'itemprop="duration"[^>]*>\s*(\d+:\d+)\s*<',
  48              r'>Duration:\s*<span[^>]+>\s*(\d+:\d+)\s*<'),
  49             webpage, 'duration', fatal=False))
  50
  51         view_count = int_or_none(self._html_search_regex(
  52             r'class="views">(?:<noscript>)?\s*(\d+)\s*<',
  53             webpage, 'view count', fatal=False))
  54         comment_count = int_or_none(self._html_search_regex(
  55             r'(\d+)</b> Comments?',
  56             webpage, 'comment count', fatal=False, default=None))
  57
  58         formats = []
  59         quality = qualities(['mp4', 'flv'])
  60         for video_url in re.findall(r'<(?:source|video) src="([^"]+)"', webpage):
  61             video_ext = determine_ext(video_url)
  62             formats.append({
  63                 'url': video_url,
  64                 'format_id': video_ext,
  65                 'quality': quality(video_ext),
  66             })
  67         self._sort_formats(formats)
  68
  69         return {
  70             'id': video_id,
  71             'title': title,
  72             'description': description,
  73             'thumbnail': thumbnail,
  74             'duration': duration,
  75             'view_count': view_count,
  76             'comment_count': comment_count,
  77             'formats': formats,
  78             'age_limit': 18,
  79         }