aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vidzi.py
blob: d671e27decf973bb315bc306f94d89d4774e7ff2 (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
55
# coding: utf-8
from __future__ import unicode_literals

import re

from .jwplatform import JWPlatformBaseIE
from ..utils import (
    base_n,
    js_to_json,
)


class VidziIE(JWPlatformBaseIE):
    _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)'
    _TEST = {
        'url': 'http://vidzi.tv/cghql9yq6emu.html',
        'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
        'info_dict': {
            'id': 'cghql9yq6emu',
            'ext': 'mp4',
            'title': 'youtube-dl test video  1\\\\2\'3/4<5\\\\6ä7↭',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }

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

        webpage = self._download_webpage(url, video_id)
        title = self._html_search_regex(
            r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')

        mobj = re.search(r"}\('(.+)',36,(\d+),'([^']+)'\.split\('\|'\)", webpage)
        code, count, symbols = mobj.groups()

        count = int(count)
        symbols = symbols.split('|')

        while count:
            count -= 1
            if symbols[count]:
                code = re.sub(r'\b%s\b' % base_n(count, 36), symbols[count], code)

        code = code.replace('\\\'', '\'')
        jwplayer_data = self._parse_json(
            self._search_regex(r'setup\(([^)]+)\)', code, 'jwplayer data'),
            video_id, transform_source=js_to_json)

        info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
        info_dict['title'] = title

        return info_dict