_ Git - youtube-dl/blob - youtube_dl/extractor/karaoketv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6 import sys
   7
   8 from .common import InfoExtractor
   9 from ..utils import compat_urllib_parse, ExtractorError
  10
  11
  12 class KaraoketvIE(InfoExtractor):
  13     _VALID_URL = r'http://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
  14     _TEST = {
  15         'url': 'http://karaoketv.co.il/?container=songs&id=171568',
  16         'info_dict': {
  17             'id': '171568',
  18             'ext': 'mp4',
  19             'title': 'אל העולם שלך - רותם כהן - שרים קריוקי',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24
  25         # BUG: SSL23_GET_SERVER_HELLO:unknown protocol
  26         if sys.hexversion < 0x03000000:
  27             raise ExtractorError("Only python 3 supported.\n")
  28
  29         mobj = re.match(self._VALID_URL, url)
  30
  31         video_id = mobj.group('id')
  32
  33         webpage = self._download_webpage(url, video_id)
  34
  35         settings_json = compat_urllib_parse.unquote_plus(self._search_regex(r'config=(.*)', self._og_search_video_url(webpage ,video_id), ''))
  36
  37         urls_info_webpage = self._download_webpage(settings_json, 'Downloading settings json')
  38
  39         urls_info_json = json.loads(urls_info_webpage.replace('\'', '"'))
  40
  41         url = urls_info_json['playlist'][0]['url']
  42
  43         return {
  44             'id': video_id,
  45             'title': self._og_search_title(webpage),
  46             'url': url,
  47         }