yt_dlp/extractor/snotr.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     parse_duration,
   4     parse_filesize,
   5     str_to_int,
   6 )
   7
   8
   9 class SnotrIE(InfoExtractor):
  10     _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)'
  11     _TESTS = [{
  12         'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
  13         'info_dict': {
  14             'id': '13708',
  15             'ext': 'mp4',
  16             'title': 'Drone flying through fireworks!',
  17             'duration': 248,
  18             'filesize_approx': 40700000,
  19             'description': 'A drone flying through Fourth of July Fireworks',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21         },
  22         'expected_warnings': ['description'],
  23     }, {
  24         'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
  25         'info_dict': {
  26             'id': '530',
  27             'ext': 'mp4',
  28             'title': 'David Letteman - George W. Bush Top 10',
  29             'duration': 126,
  30             'filesize_approx': 8500000,
  31             'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
  32             'thumbnail': r're:^https?://.*\.jpg$',
  33         }
  34     }]
  35
  36     def _real_extract(self, url):
  37         mobj = self._match_valid_url(url)
  38         video_id = mobj.group('id')
  39
  40         webpage = self._download_webpage(url, video_id)
  41         title = self._og_search_title(webpage)
  42
  43         description = self._og_search_description(webpage)
  44         info_dict = self._parse_html5_media_entries(
  45             url, webpage, video_id, m3u8_entry_protocol='m3u8_native')[0]
  46
  47         view_count = str_to_int(self._html_search_regex(
  48             r'<p[^>]*>\s*<strong[^>]*>Views:</strong>\s*<span[^>]*>([\d,\.]+)',
  49             webpage, 'view count', fatal=False))
  50
  51         duration = parse_duration(self._html_search_regex(
  52             r'<p[^>]*>\s*<strong[^>]*>Length:</strong>\s*<span[^>]*>([\d:]+)',
  53             webpage, 'duration', fatal=False))
  54
  55         filesize_approx = parse_filesize(self._html_search_regex(
  56             r'<p[^>]*>\s*<strong[^>]*>Filesize:</strong>\s*<span[^>]*>([^<]+)',
  57             webpage, 'filesize', fatal=False))
  58
  59         info_dict.update({
  60             'id': video_id,
  61             'description': description,
  62             'title': title,
  63             'view_count': view_count,
  64             'duration': duration,
  65             'filesize_approx': filesize_approx,
  66         })
  67
  68         return info_dict