yt_dlp/extractor/tv2dk.py

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