yt_dlp/extractor/rtlnl.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_duration,
   5 )
   6
   7
   8 class RtlNlIE(InfoExtractor):
   9     IE_NAME = 'rtl.nl'
  10     IE_DESC = 'rtl.nl and rtlxl.nl'
  11     _VALID_URL = r'''(?x)
  12         https?://(?:(?:www|static)\.)?
  13         (?:
  14             rtlxl\.nl/(?:[^\#]*\#!|programma)/[^/]+/|
  15             rtl\.nl/(?:(?:system/videoplayer/(?:[^/]+/)+(?:video_)?embed\.html|embed)\b.+?\buuid=|video/)|
  16             embed\.rtl\.nl/\#uuid=
  17         )
  18         (?P<id>[0-9a-f-]+)'''
  19
  20     _TESTS = [{
  21         # new URL schema
  22         'url': 'https://www.rtlxl.nl/programma/rtl-nieuws/0bd1384d-d970-3086-98bb-5c104e10c26f',
  23         'md5': '490428f1187b60d714f34e1f2e3af0b6',
  24         'info_dict': {
  25             'id': '0bd1384d-d970-3086-98bb-5c104e10c26f',
  26             'ext': 'mp4',
  27             'title': 'RTL Nieuws',
  28             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  29             'timestamp': 1593293400,
  30             'upload_date': '20200627',
  31             'duration': 661.08,
  32         },
  33     }, {
  34         # old URL schema
  35         'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
  36         'md5': '473d1946c1fdd050b2c0161a4b13c373',
  37         'info_dict': {
  38             'id': '82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
  39             'ext': 'mp4',
  40             'title': 'RTL Nieuws',
  41             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  42             'timestamp': 1461951000,
  43             'upload_date': '20160429',
  44             'duration': 1167.96,
  45         },
  46         'skip': '404',
  47     }, {
  48         # best format available a3t
  49         'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
  50         'md5': 'dea7474214af1271d91ef332fb8be7ea',
  51         'info_dict': {
  52             'id': '84ae5571-ac25-4225-ae0c-ef8d9efb2aed',
  53             'ext': 'mp4',
  54             'timestamp': 1424039400,
  55             'title': 'RTL Nieuws - Nieuwe beelden Kopenhagen: chaos direct na aanslag',
  56             'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed$',
  57             'upload_date': '20150215',
  58             'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
  59         }
  60     }, {
  61         # empty synopsis and missing episodes (see https://github.com/ytdl-org/youtube-dl/issues/6275)
  62         # best format available nettv
  63         'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a/autoplay=false',
  64         'info_dict': {
  65             'id': 'f536aac0-1dc3-4314-920e-3bd1c5b3811a',
  66             'ext': 'mp4',
  67             'title': 'RTL Nieuws - Meer beelden van overval juwelier',
  68             'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a$',
  69             'timestamp': 1437233400,
  70             'upload_date': '20150718',
  71             'duration': 30.474,
  72         },
  73         'params': {
  74             'skip_download': True,
  75         },
  76     }, {
  77         # encrypted m3u8 streams, georestricted
  78         'url': 'http://www.rtlxl.nl/#!/afl-2-257632/52a74543-c504-4cde-8aa8-ec66fe8d68a7',
  79         'only_matching': True,
  80     }, {
  81         'url': 'http://www.rtl.nl/system/videoplayer/derden/embed.html#!/uuid=bb0353b0-d6a4-1dad-90e9-18fe75b8d1f0',
  82         'only_matching': True,
  83     }, {
  84         'url': 'http://rtlxl.nl/?_ga=1.204735956.572365465.1466978370#!/rtl-nieuws-132237/3c487912-023b-49ac-903e-2c5d79f8410f',
  85         'only_matching': True,
  86     }, {
  87         'url': 'https://www.rtl.nl/video/c603c9c2-601d-4b5e-8175-64f1e942dc7d/',
  88         'only_matching': True,
  89     }, {
  90         'url': 'https://static.rtl.nl/embed/?uuid=1a2970fc-5c0b-43ff-9fdc-927e39e6d1bc&autoplay=false&publicatiepunt=rtlnieuwsnl',
  91         'only_matching': True,
  92     }, {
  93         # new embed URL schema
  94         'url': 'https://embed.rtl.nl/#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
  95         'only_matching': True,
  96     }]
  97
  98     def _real_extract(self, url):
  99         uuid = self._match_id(url)
 100         info = self._download_json(
 101             'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=adaptive/' % uuid,
 102             uuid)
 103
 104         material = info['material'][0]
 105         title = info['abstracts'][0]['name']
 106         subtitle = material.get('title')
 107         if subtitle:
 108             title += ' - %s' % subtitle
 109         description = material.get('synopsis')
 110
 111         meta = info.get('meta', {})
 112
 113         videopath = material['videopath']
 114         m3u8_url = meta.get('videohost', 'http://manifest.us.rtl.nl') + videopath
 115
 116         formats = self._extract_m3u8_formats(
 117             m3u8_url, uuid, 'mp4', m3u8_id='hls', fatal=False)
 118         self._sort_formats(formats)
 119
 120         thumbnails = []
 121
 122         for p in ('poster_base_url', '"thumb_base_url"'):
 123             if not meta.get(p):
 124                 continue
 125
 126             thumbnails.append({
 127                 'url': self._proto_relative_url(meta[p] + uuid),
 128                 'width': int_or_none(self._search_regex(
 129                     r'/sz=([0-9]+)', meta[p], 'thumbnail width', fatal=False)),
 130                 'height': int_or_none(self._search_regex(
 131                     r'/sz=[0-9]+x([0-9]+)',
 132                     meta[p], 'thumbnail height', fatal=False))
 133             })
 134
 135         return {
 136             'id': uuid,
 137             'title': title,
 138             'formats': formats,
 139             'timestamp': material['original_date'],
 140             'description': description,
 141             'duration': parse_duration(material.get('duration')),
 142             'thumbnails': thumbnails,
 143         }