aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ynet.py
blob: 66d53962a58c9d78cede366ecc684dd5fe3a3472 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
# coding: utf-8
from __future__ import unicode_literals

import re
import json

from .common import InfoExtractor
from ..utils import compat_urllib_parse


class YnetIE(InfoExtractor):
    _VALID_URL = r'http://.*ynet\.co\.il/.*/0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
    _TESTS = [
        {
            'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
            'md5': '002b44ee2f33d50363a1c153bed524cf',
            'info_dict': {
                'id': 'L-11659-99244',
                'ext': 'flv',
                'title': 'איש לא יודע מאיפה באנו',
                'thumbnail': 're:^https?://.*\.jpg',
            }
        }, {
            'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
            'md5': '6455046ae1b48cf7e2b7cae285e53a16',
            'info_dict': {
                'id': 'L-8859-84418',
                'ext': 'flv',
                'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
                'thumbnail': 're:^https?://.*\.jpg',
            }
        }
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        
        webpage = self._download_webpage(url, video_id)

        content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage))
        config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
        f4m_url = config['clip']['url']
        title = self._og_search_title(webpage)
        m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
        if m:
            title = m.group('title')

        return {
            'id': video_id,
            'title': title,
            'formats': self._extract_f4m_formats(f4m_url, video_id),
            'thumbnail': self._og_search_thumbnail(webpage),
        }