Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/localnews8.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class LocalNews8IE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?localnews8\.com/(?:[^/]+/)*(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
  11     _TEST = {
  12         'url': 'http://www.localnews8.com/news/rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings/35183304',
  13         'md5': 'be4d48aea61aa2bde7be2ee47691ad20',
  14         'info_dict': {
  15             'id': '35183304',
  16             'display_id': 'rexburg-business-turns-carbon-fiber-scraps-into-wedding-rings',
  17             'ext': 'mp4',
  18             'title': 'Rexburg business turns carbon fiber scraps into wedding ring',
  19             'description': 'The process was first invented by Lamborghini and less than a dozen companies around the world use it.',
  20             'duration': 153,
  21             'timestamp': 1441844822,
  22             'upload_date': '20150910',
  23             'uploader_id': 'api',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30         display_id = mobj.group('display_id')
  31
  32         webpage = self._download_webpage(url, display_id)
  33
  34         partner_id = self._search_regex(
  35             r'partnerId\s*[:=]\s*(["\'])(?P<id>\d+)\1',
  36             webpage, 'partner id', group='id')
  37         kaltura_id = self._search_regex(
  38             r'videoIdString\s*[:=]\s*(["\'])kaltura:(?P<id>[0-9a-z_]+)\1',
  39             webpage, 'videl id', group='id')
  40
  41         return {
  42             '_type': 'url_transparent',
  43             'url': 'kaltura:%s:%s' % (partner_id, kaltura_id),
  44             'ie_key': 'Kaltura',
  45             'id': video_id,
  46             'display_id': display_id,
  47         }