yt_dlp/extractor/snotr.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     parse_filesize,
   9     str_to_int,
  10 )
  11
  12
  13 class SnotrIE(InfoExtractor):
  14     _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)'
  15     _TESTS = [{
  16         'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
  17         'info_dict': {
  18             'id': '13708',
  19             'ext': 'mp4',
  20             'title': 'Drone flying through fireworks!',
  21             'duration': 248,
  22             'filesize_approx': 40700000,
  23             'description': 'A drone flying through Fourth of July Fireworks',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25         },
  26         'expected_warnings': ['description'],
  27     }, {
  28         'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
  29         'info_dict': {
  30             'id': '530',
  31             'ext': 'mp4',
  32             'title': 'David Letteman - George W. Bush Top 10',
  33             'duration': 126,
  34             'filesize_approx': 8500000,
  35             'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
  36             'thumbnail': r're:^https?://.*\.jpg$',
  37         }
  38     }]
  39
  40     def _real_extract(self, url):
  41         mobj = self._match_valid_url(url)
  42         video_id = mobj.group('id')
  43
  44         webpage = self._download_webpage(url, video_id)
  45         title = self._og_search_title(webpage)
  46
  47         description = self._og_search_description(webpage)
  48         info_dict = self._parse_html5_media_entries(
  49             url, webpage, video_id, m3u8_entry_protocol='m3u8_native')[0]
  50
  51         view_count = str_to_int(self._html_search_regex(
  52             r'<p[^>]*>\s*<strong[^>]*>Views:</strong>\s*<span[^>]*>([\d,\.]+)',
  53             webpage, 'view count', fatal=False))
  54
  55         duration = parse_duration(self._html_search_regex(
  56             r'<p[^>]*>\s*<strong[^>]*>Length:</strong>\s*<span[^>]*>([\d:]+)',
  57             webpage, 'duration', fatal=False))
  58
  59         filesize_approx = parse_filesize(self._html_search_regex(
  60             r'<p[^>]*>\s*<strong[^>]*>Filesize:</strong>\s*<span[^>]*>([^<]+)',
  61             webpage, 'filesize', fatal=False))
  62
  63         info_dict.update({
  64             'id': video_id,
  65             'description': description,
  66             'title': title,
  67             'view_count': view_count,
  68             'duration': duration,
  69             'filesize_approx': filesize_approx,
  70         })
  71
  72         return info_dict