yt_dlp/extractor/tv2dk.py

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