yt_dlp/extractor/sunporno.py

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