_ Git - youtube-dl/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
   8 from ..utils import (
   9
  10     str_to_int,
  11     parse_iso8601,
  12
  13
  14
  15 )
  16
  17 class SnotrIE(InfoExtractor):
  18     _VALID_URL = r'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)'
  19     _TESTS =[ {
  20         'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
  21         'info_dict': {
  22             'id': '13708',
  23             'ext': 'flv',
  24             'title': 'Drone flying through fireworks!',
  25             'duration': 247,
  26             'filesize':12320768
  27           }
  28     },
  29
  30
  31
  32         {
  33
  34         'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
  35         'info_dict': {
  36             'id': '530',
  37             'ext': 'flv',
  38             'title': 'David Letteman - George W. Bush Top 10',
  39             'duration': 126,
  40             'filesize': 1048576
  41            }
  42      }]
  43
  44
  45     def _real_extract(self, url):
  46         mobj = re.match(self._VALID_URL, url)
  47         video_id = mobj.group('id')
  48
  49         # TODO more code goes here, for example ...
  50         webpage = self._download_webpage(url, video_id)
  51         title = self._og_search_title(webpage)
  52
  53         description = self._og_search_description(webpage)
  54
  55         video_url = "http://cdn.videos.snotr.com/%s.flv" % video_id
  56
  57         view_count = str_to_int(self._html_search_regex(r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',webpage,'view count'))
  58
  59         duration = self._html_search_regex(r'<p>\n<strong>Length:</strong>\n(.*?)</p>',webpage,'duration')
  60         duration = str_to_int(duration[:1])*60 + str_to_int(duration[2:4])
  61
  62         file_size = self._html_search_regex(r'<p>\n<strong>Filesize:</strong>\n(.*?)</p>',webpage,'filesize')
  63         file_size = str_to_int(re.match(r'\d+',file_size).group())*131072
  64
  65         return {
  66             'id': video_id,
  67             'title': title,
  68             'url':video_url,
  69             'view_count':view_count,
  70             'duration':duration,
  71             'filesize':file_size
  72
  73         }