1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5 import re
6
7 from .common import InfoExtractor
8 from ..utils import (
9 determine_ext,
10 extract_attributes,
11 js_to_json,
12 url_or_none,
13 )
14
15
16 class TV2DKIE(InfoExtractor):
17 _VALID_URL = r'''(?x)
18 https?://
19 (?:www\.)?
20 (?:
21 tvsyd|
22 tv2ostjylland|
23 tvmidtvest|
24 tv2fyn|
25 tv2east|
26 tv2lorry|
27 tv2nord
28 )\.dk/
29 (:[^/]+/)*
30 (?P<id>[^/?\#&]+)
31 '''
32 _TESTS = [{
33 'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player',
34 'info_dict': {
35 'id': '0_52jmwa0p',
36 'ext': 'mp4',
37 'title': '19:30 - 28. okt. 2019',
38 'timestamp': 1572290248,
39 'upload_date': '20191028',
40 'uploader_id': 'tvsyd',
41 'duration': 1347,
42 'view_count': int,
43 },
44 'add_ie': ['Kaltura'],
45 }, {
46 'url': 'https://www.tv2lorry.dk/gadekamp/gadekamp-6-hoejhuse-i-koebenhavn',
47 'info_dict': {
48 'id': '1_7iwll9n0',
49 'ext': 'mp4',
50 'upload_date': '20211027',
51 'title': 'Gadekamp #6 - Højhuse i København',
52 'uploader_id': 'tv2lorry',
53 'timestamp': 1635345229,
54 },
55 'add_ie': ['Kaltura'],
56 }, {
57 'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi',
58 'only_matching': True,
59 }, {
60 'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player',
61 'only_matching': True,
62 }, {
63 'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019',
64 'only_matching': True,
65 }, {
66 'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof',
67 'only_matching': True,
68 }, {
69 'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy',
70 'only_matching': True,
71 }, {
72 'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player',
73 'only_matching': True,
74 }, {
75 'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt',
76 'only_matching': True,
77 }]
78
79 def _real_extract(self, url):
80 video_id = self._match_id(url)
81
82 webpage = self._download_webpage(url, video_id)
83
84 entries = []
85
86 def add_entry(partner_id, kaltura_id):
87 entries.append(self.url_result(
88 'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
89 video_id=kaltura_id))
90
91 for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage):
92 video = extract_attributes(video_el)
93 kaltura_id = video.get('data-entryid')
94 if not kaltura_id:
95 continue
96 partner_id = video.get('data-partnerid')
97 if not partner_id:
98 continue
99 add_entry(partner_id, kaltura_id)
100 if not entries:
101 kaltura_id = self._search_regex(
102 (r'entry_id\s*:\s*["\']([0-9a-z_]+)',
103 r'\\u002FentryId\\u002F(\w+)\\u002F'), webpage, 'kaltura id')
104 partner_id = self._search_regex(
105 (r'\\u002Fp\\u002F(\d+)\\u002F', r'/p/(\d+)/'), webpage,
106 'partner id')
107 add_entry(partner_id, kaltura_id)
108 if len(entries) == 1:
109 return entries[0]
110 return self.playlist_result(entries)
111
112
113 class TV2DKBornholmPlayIE(InfoExtractor):
114 _VALID_URL = r'https?://play\.tv2bornholm\.dk/\?.*?\bid=(?P<id>\d+)'
115 _TEST = {
116 'url': 'http://play.tv2bornholm.dk/?area=specifikTV&id=781021',
117 'info_dict': {
118 'id': '781021',
119 'ext': 'mp4',
120 'title': '12Nyheder-27.11.19',
121 },
122 'params': {
123 'skip_download': True,
124 },
125 }
126
127 def _real_extract(self, url):
128 video_id = self._match_id(url)
129
130 video = self._download_json(
131 'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
132 data=json.dumps({
133 'playlist_id': video_id,
134 'serienavn': '',
135 }).encode(), headers={
136 'X-Requested-With': 'XMLHttpRequest',
137 'Content-Type': 'application/json; charset=UTF-8',
138 })['d']
139
140 # TODO: generalize flowplayer
141 title = self._search_regex(
142 r'title\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', video, 'title',
143 group='value')
144 sources = self._parse_json(self._search_regex(
145 r'(?s)sources:\s*(\[.+?\]),', video, 'sources'),
146 video_id, js_to_json)
147
148 formats = []
149 srcs = set()
150 for source in sources:
151 src = url_or_none(source.get('src'))
152 if not src:
153 continue
154 if src in srcs:
155 continue
156 srcs.add(src)
157 ext = determine_ext(src)
158 src_type = source.get('type')
159 if src_type == 'application/x-mpegurl' or ext == 'm3u8':
160 formats.extend(self._extract_m3u8_formats(
161 src, video_id, ext='mp4', entry_protocol='m3u8_native',
162 m3u8_id='hls', fatal=False))
163 elif src_type == 'application/dash+xml' or ext == 'mpd':
164 formats.extend(self._extract_mpd_formats(
165 src, video_id, mpd_id='dash', fatal=False))
166 else:
167 formats.append({
168 'url': src,
169 })
170 self._sort_formats(formats)
171
172 return {
173 'id': video_id,
174 'title': title,
175 'formats': formats,
176 }
|
