youtube_dl/extractor/ynet.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_urllib_parse_unquote_plus
   9
  10
  11 class YnetIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
  13     _TESTS = [
  14         {
  15             'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
  16             'info_dict': {
  17                 'id': 'L-11659-99244',
  18                 'ext': 'flv',
  19                 'title': 'איש לא יודע מאיפה באנו',
  20                 'thumbnail': r're:^https?://.*\.jpg',
  21             }
  22         }, {
  23             'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
  24             'info_dict': {
  25                 'id': 'L-8859-84418',
  26                 'ext': 'flv',
  27                 'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
  28                 'thumbnail': r're:^https?://.*\.jpg',
  29             }
  30         }
  31     ]
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35         webpage = self._download_webpage(url, video_id)
  36
  37         content = compat_urllib_parse_unquote_plus(self._og_search_video_url(webpage))
  38         config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
  39         f4m_url = config['clip']['url']
  40         title = self._og_search_title(webpage)
  41         m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
  42         if m:
  43             title = m.group('title')
  44         formats = self._extract_f4m_formats(f4m_url, video_id)
  45         self._sort_formats(formats)
  46
  47         return {
  48             'id': video_id,
  49             'title': title,
  50             'formats': formats,
  51             'thumbnail': self._og_search_thumbnail(webpage),
  52         }