summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/radiojavan.py
blob: b3befaef9098e5750696151db95275209a4cb951 (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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
import re

from .common import InfoExtractor
from ..utils import (
    parse_resolution,
    str_to_int,
    unified_strdate,
    urlencode_postdata,
    urljoin,
)


class RadioJavanIE(InfoExtractor):
    _WORKING = False
    _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
    _TEST = {
        'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
        'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
        'info_dict': {
            'id': 'chaartaar-ashoobam',
            'ext': 'mp4',
            'title': 'Chaartaar - Ashoobam',
            'thumbnail': r're:^https?://.*\.jpe?g$',
            'upload_date': '20150215',
            'view_count': int,
            'like_count': int,
            'dislike_count': int,
        }
    }

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

        download_host = self._download_json(
            'https://www.radiojavan.com/videos/video_host', video_id,
            data=urlencode_postdata({'id': video_id}),
            headers={
                'Content-Type': 'application/x-www-form-urlencoded',
                'Referer': url,
            }).get('host', 'https://host1.rjmusicmedia.com')

        webpage = self._download_webpage(url, video_id)

        formats = []
        for format_id, _, video_path in re.findall(
                r'RJ\.video(?P<format_id>\d+[pPkK])\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
                webpage):
            f = parse_resolution(format_id)
            f.update({
                'url': urljoin(download_host, video_path),
                'format_id': format_id,
            })
            formats.append(f)

        title = self._og_search_title(webpage)
        thumbnail = self._og_search_thumbnail(webpage)

        upload_date = unified_strdate(self._search_regex(
            r'class="date_added">Date added: ([^<]+)<',
            webpage, 'upload date', fatal=False))

        view_count = str_to_int(self._search_regex(
            r'class="views">Plays: ([\d,]+)',
            webpage, 'view count', fatal=False))
        like_count = str_to_int(self._search_regex(
            r'class="rating">([\d,]+) likes',
            webpage, 'like count', fatal=False))
        dislike_count = str_to_int(self._search_regex(
            r'class="rating">([\d,]+) dislikes',
            webpage, 'dislike count', fatal=False))

        return {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'upload_date': upload_date,
            'view_count': view_count,
            'like_count': like_count,
            'dislike_count': dislike_count,
            'formats': formats,
        }