Raphaël G. Git Repositories - youtubedl/blob - 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     float_or_none,
   9     str_to_int,
  10     parse_duration,
  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': 'flv',
  21             'title': 'Drone flying through fireworks!',
  22             'duration': 247,
  23             'filesize_approx': 98566144,
  24             'description': 'A drone flying through Fourth of July Fireworks',
  25         }
  26     }, {
  27         'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
  28         'info_dict': {
  29             'id': '530',
  30             'ext': 'flv',
  31             'title': 'David Letteman - George W. Bush Top 10',
  32             'duration': 126,
  33             'filesize_approx': 8912896,
  34             'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
  35         }
  36     }]
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40         video_id = mobj.group('id')
  41
  42         webpage = self._download_webpage(url, video_id)
  43         title = self._og_search_title(webpage)
  44
  45         description = self._og_search_description(webpage)
  46         video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id
  47
  48         view_count = str_to_int(self._html_search_regex(
  49             r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',
  50             webpage, 'view count', fatal=False))
  51
  52         duration = parse_duration(self._html_search_regex(
  53             r'<p>\n<strong>Length:</strong>\n\s*([0-9:]+).*?</p>',
  54             webpage, 'duration', fatal=False))
  55
  56         filesize_approx = float_or_none(self._html_search_regex(
  57             r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>',
  58             webpage, 'filesize', fatal=False), invscale=1024 * 1024)
  59
  60         return {
  61             'id': video_id,
  62             'description': description,
  63             'title': title,
  64             'url': video_url,
  65             'view_count': view_count,
  66             'duration': duration,
  67             'filesize_approx': filesize_approx,
  68         }