aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tv2dk.py
blob: ec5cbdf03537ee7d83ca6b3e94e34bc1aba138be (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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
# coding: utf-8
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    extract_attributes,
    js_to_json,
    url_or_none,
)


class TV2DKIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                    https?://
                        (?:www\.)?
                        (?:
                            tvsyd|
                            tv2ostjylland|
                            tvmidtvest|
                            tv2fyn|
                            tv2east|
                            tv2lorry|
                            tv2nord
                        )\.dk/
                        (:[^/]+/)*
                        (?P<id>[^/?\#&]+)
                    '''
    _TESTS = [{
        'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player',
        'info_dict': {
            'id': '0_52jmwa0p',
            'ext': 'mp4',
            'title': '19:30 - 28. okt. 2019',
            'timestamp': 1572290248,
            'upload_date': '20191028',
            'uploader_id': 'tvsyd',
            'duration': 1347,
            'view_count': int,
        },
        'add_ie': ['Kaltura'],
    }, {
        'url': 'https://www.tv2lorry.dk/gadekamp/gadekamp-6-hoejhuse-i-koebenhavn',
        'info_dict': {
            'id': '1_7iwll9n0',
            'ext': 'mp4',
            'upload_date': '20211027',
            'title': 'Gadekamp #6 - Højhuse i København',
            'uploader_id': 'tv2lorry',
            'timestamp': 1635345229,
        },
        'add_ie': ['Kaltura'],
    }, {
        'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi',
        'only_matching': True,
    }, {
        'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player',
        'only_matching': True,
    }, {
        'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019',
        'only_matching': True,
    }, {
        'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof',
        'only_matching': True,
    }, {
        'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy',
        'only_matching': True,
    }, {
        'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player',
        'only_matching': True,
    }, {
        'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(url, video_id)

        entries = []

        def add_entry(partner_id, kaltura_id):
            entries.append(self.url_result(
                'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
                video_id=kaltura_id))

        for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage):
            video = extract_attributes(video_el)
            kaltura_id = video.get('data-entryid')
            if not kaltura_id:
                continue
            partner_id = video.get('data-partnerid')
            if not partner_id:
                continue
            add_entry(partner_id, kaltura_id)
        if not entries:
            kaltura_id = self._search_regex(
                (r'entry_id\s*:\s*["\']([0-9a-z_]+)',
                 r'\\u002FentryId\\u002F(\w+)\\u002F'), webpage, 'kaltura id')
            partner_id = self._search_regex(
                (r'\\u002Fp\\u002F(\d+)\\u002F', r'/p/(\d+)/'), webpage,
                'partner id')
            add_entry(partner_id, kaltura_id)
        if len(entries) == 1:
            return entries[0]
        return self.playlist_result(entries)


class TV2DKBornholmPlayIE(InfoExtractor):
    _VALID_URL = r'https?://play\.tv2bornholm\.dk/\?.*?\bid=(?P<id>\d+)'
    _TEST = {
        'url': 'http://play.tv2bornholm.dk/?area=specifikTV&id=781021',
        'info_dict': {
            'id': '781021',
            'ext': 'mp4',
            'title': '12Nyheder-27.11.19',
        },
        'params': {
            'skip_download': True,
        },
    }

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

        video = self._download_json(
            'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
            data=json.dumps({
                'playlist_id': video_id,
                'serienavn': '',
            }).encode(), headers={
                'X-Requested-With': 'XMLHttpRequest',
                'Content-Type': 'application/json; charset=UTF-8',
            })['d']

        # TODO: generalize flowplayer
        title = self._search_regex(
            r'title\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', video, 'title',
            group='value')
        sources = self._parse_json(self._search_regex(
            r'(?s)sources:\s*(\[.+?\]),', video, 'sources'),
            video_id, js_to_json)

        formats = []
        srcs = set()
        for source in sources:
            src = url_or_none(source.get('src'))
            if not src:
                continue
            if src in srcs:
                continue
            srcs.add(src)
            ext = determine_ext(src)
            src_type = source.get('type')
            if src_type == 'application/x-mpegurl' or ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    src, video_id, ext='mp4', entry_protocol='m3u8_native',
                    m3u8_id='hls', fatal=False))
            elif src_type == 'application/dash+xml' or ext == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    src, video_id, mpd_id='dash', fatal=False))
            else:
                formats.append({
                    'url': src,
                })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
        }