youtube_dl/extractor/snotr.py

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