2 from __future__ import unicode_literals
7 from .common import InfoExtractor
8 from ..utils import compat_urllib_parse
11 class YnetIE(InfoExtractor):
12 _VALID_URL = r'http://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
15 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
16 'md5': '002b44ee2f33d50363a1c153bed524cf',
18 'id': 'L-11659-99244',
20 'title': 'איש לא יודע מאיפה באנו',
21 'thumbnail': 're:^https?://.*\.jpg',
24 'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
25 'md5': '6455046ae1b48cf7e2b7cae285e53a16',
29 'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
30 'thumbnail': 're:^https?://.*\.jpg',
35 def _real_extract(self, url):
36 mobj = re.match(self._VALID_URL, url)
37 video_id = mobj.group('id')
39 webpage = self._download_webpage(url, video_id)
41 content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage))
42 config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
43 f4m_url = config['clip']['url']
44 title = self._og_search_title(webpage)
45 m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
47 title = m.group('title')
52 'formats': self._extract_f4m_formats(f4m_url, video_id),
53 'thumbnail': self._og_search_thumbnail(webpage),