aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tvnoe.py
blob: 6d5c748264197ba99a2be8fefccf375761818610 (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
# coding: utf-8
from __future__ import unicode_literals

from .jwplatform import JWPlatformBaseIE
from ..utils import (
    clean_html,
    get_element_by_class,
    js_to_json,
)


class TVNoeIE(JWPlatformBaseIE):
    _VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
    _TEST = {
        'url': 'http://www.tvnoe.cz/video/10362',
        'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
        'info_dict': {
            'id': '10362',
            'ext': 'mp4',
            'series': 'Noční univerzita',
            'title': 'prof. Tomáš Halík, Th.D. - Návrat náboženství a střet civilizací',
            'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
        }
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        iframe_url = self._search_regex(
            r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')

        ifs_page = self._download_webpage(iframe_url, video_id)
        jwplayer_data = self._parse_json(
            self._find_jwplayer_data(ifs_page),
            video_id, transform_source=js_to_json)
        info_dict = self._parse_jwplayer_data(
            jwplayer_data, video_id, require_title=False, base_url=iframe_url)

        info_dict.update({
            'id': video_id,
            'title': clean_html(get_element_by_class(
                'field-name-field-podnazev', webpage)),
            'description': clean_html(get_element_by_class(
                'field-name-body', webpage)),
            'series': clean_html(get_element_by_class('title', webpage))
        })

        return info_dict