aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tvnet.py
blob: 2b2630b916dc94cea142986169cc615479d30d7e (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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    int_or_none,
    unescapeHTML,
)


class TVNetIE(InfoExtractor):
    _VALID_URL = r'https?://(?:[^/]+)\.tvnet\.gov\.vn/[^/]+/(?:\d+/)?(?P<id>\d+)(?:/|$)'
    _TESTS = [{
        # video
        'url': 'http://de.tvnet.gov.vn/video/109788/vtv1---bac-tuyet-tai-lao-cai-va-ha-giang/tin-nong-24h',
        'md5': 'b4d7abe0252c9b47774760b7519c7558',
        'info_dict': {
            'id': '109788',
            'ext': 'mp4',
            'title': 'VTV1 - Bắc tuyết tại Lào Cai và Hà Giang',
            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
            'is_live': False,
            'view_count': int,
        },
    }, {
        # audio
        'url': 'http://vn.tvnet.gov.vn/radio/27017/vov1---ban-tin-chieu-10062018/doi-song-va-xa-hoi',
        'md5': 'b5875ce9b0a2eecde029216d0e6db2ae',
        'info_dict': {
            'id': '27017',
            'ext': 'm4a',
            'title': 'VOV1 - Bản tin chiều (10/06/2018)',
            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
            'is_live': False,
        },
    }, {
        'url': 'http://us.tvnet.gov.vn/video/118023/129999/ngay-0705',
        'info_dict': {
            'id': '129999',
            'ext': 'mp4',
            'title': 'VTV1 - Quốc hội với cử tri (11/06/2018)',
            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
            'is_live': False,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # live stream
        'url': 'http://us.tvnet.gov.vn/kenh-truyen-hinh/1011/vtv1',
        'info_dict': {
            'id': '1011',
            'ext': 'mp4',
            'title': r're:^VTV1 \| LiveTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # radio live stream
        'url': 'http://vn.tvnet.gov.vn/kenh-truyen-hinh/1014',
        'info_dict': {
            'id': '1014',
            'ext': 'm4a',
            'title': r're:VOV1 \| LiveTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'http://us.tvnet.gov.vn/phim/6136/25510/vtv3---ca-mot-doi-an-oan-tap-1-50/phim-truyen-hinh',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(url, video_id)

        title = self._og_search_title(
            webpage, default=None) or self._html_search_meta(
            'title', webpage, default=None) or self._search_regex(
            r'<title>([^<]+)<', webpage, 'title')
        title = re.sub(r'\s*-\s*TV Net\s*$', '', title)

        if '/video/' in url or '/radio/' in url:
            is_live = False
        elif '/kenh-truyen-hinh/' in url:
            is_live = True
        else:
            is_live = None

        data_file = unescapeHTML(self._search_regex(
            r'data-file=(["\'])(?P<url>(?:https?:)?//.+?)\1', webpage,
            'data file', group='url'))

        stream_urls = set()
        formats = []
        for stream in self._download_json(data_file, video_id):
            if not isinstance(stream, dict):
                continue
            stream_url = stream.get('url')
            if (stream_url in stream_urls or not stream_url or
                    not isinstance(stream_url, compat_str)):
                continue
            stream_urls.add(stream_url)
            formats.extend(self._extract_m3u8_formats(
                stream_url, video_id, 'mp4',
                entry_protocol='m3u8' if is_live else 'm3u8_native',
                m3u8_id='hls', fatal=False))
        self._sort_formats(formats)

        # better support for radio streams
        if title.startswith('VOV'):
            for f in formats:
                f.update({
                    'ext': 'm4a',
                    'vcodec': 'none',
                })

        thumbnail = self._og_search_thumbnail(
            webpage, default=None) or unescapeHTML(
            self._search_regex(
                r'data-image=(["\'])(?P<url>(?:https?:)?//.+?)\1', webpage,
                'thumbnail', default=None, group='url'))

        if is_live:
            title = self._live_title(title)

        view_count = int_or_none(self._search_regex(
            r'(?s)<div[^>]+\bclass=["\'].*?view-count[^>]+>.*?(\d+).*?</div>',
            webpage, 'view count', default=None))

        return {
            'id': video_id,
            'title': title,
            'thumbnail': thumbnail,
            'is_live': is_live,
            'view_count': view_count,
            'formats': formats,
        }