Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtlnl.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_duration,
   8 )
   9
  10
  11 class RtlNlIE(InfoExtractor):
  12     IE_NAME = 'rtl.nl'
  13     IE_DESC = 'rtl.nl and rtlxl.nl'
  14     _VALID_URL = r'''(?x)
  15         https?://(?:(?:www|static)\.)?
  16         (?:
  17             rtlxl\.nl/(?:[^\#]*\#!|programma)/[^/]+/|
  18             rtl\.nl/(?:(?:system/videoplayer/(?:[^/]+/)+(?:video_)?embed\.html|embed)\b.+?\buuid=|video/)|
  19             embed\.rtl\.nl/\#uuid=
  20         )
  21         (?P<id>[0-9a-f-]+)'''
  22
  23     _TESTS = [{
  24         # new URL schema
  25         'url': 'https://www.rtlxl.nl/programma/rtl-nieuws/0bd1384d-d970-3086-98bb-5c104e10c26f',
  26         'md5': '490428f1187b60d714f34e1f2e3af0b6',
  27         'info_dict': {
  28             'id': '0bd1384d-d970-3086-98bb-5c104e10c26f',
  29             'ext': 'mp4',
  30             'title': 'RTL Nieuws',
  31             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  32             'timestamp': 1593293400,
  33             'upload_date': '20200627',
  34             'duration': 661.08,
  35         },
  36     }, {
  37         # old URL schema
  38         'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
  39         'md5': '473d1946c1fdd050b2c0161a4b13c373',
  40         'info_dict': {
  41             'id': '82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
  42             'ext': 'mp4',
  43             'title': 'RTL Nieuws',
  44             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  45             'timestamp': 1461951000,
  46             'upload_date': '20160429',
  47             'duration': 1167.96,
  48         },
  49         'skip': '404',
  50     }, {
  51         # best format available a3t
  52         'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
  53         'md5': 'dea7474214af1271d91ef332fb8be7ea',
  54         'info_dict': {
  55             'id': '84ae5571-ac25-4225-ae0c-ef8d9efb2aed',
  56             'ext': 'mp4',
  57             'timestamp': 1424039400,
  58             'title': 'RTL Nieuws - Nieuwe beelden Kopenhagen: chaos direct na aanslag',
  59             'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed$',
  60             'upload_date': '20150215',
  61             'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
  62         }
  63     }, {
  64         # empty synopsis and missing episodes (see https://github.com/ytdl-org/youtube-dl/issues/6275)
  65         # best format available nettv
  66         'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a/autoplay=false',
  67         'info_dict': {
  68             'id': 'f536aac0-1dc3-4314-920e-3bd1c5b3811a',
  69             'ext': 'mp4',
  70             'title': 'RTL Nieuws - Meer beelden van overval juwelier',
  71             'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a$',
  72             'timestamp': 1437233400,
  73             'upload_date': '20150718',
  74             'duration': 30.474,
  75         },
  76         'params': {
  77             'skip_download': True,
  78         },
  79     }, {
  80         # encrypted m3u8 streams, georestricted
  81         'url': 'http://www.rtlxl.nl/#!/afl-2-257632/52a74543-c504-4cde-8aa8-ec66fe8d68a7',
  82         'only_matching': True,
  83     }, {
  84         'url': 'http://www.rtl.nl/system/videoplayer/derden/embed.html#!/uuid=bb0353b0-d6a4-1dad-90e9-18fe75b8d1f0',
  85         'only_matching': True,
  86     }, {
  87         'url': 'http://rtlxl.nl/?_ga=1.204735956.572365465.1466978370#!/rtl-nieuws-132237/3c487912-023b-49ac-903e-2c5d79f8410f',
  88         'only_matching': True,
  89     }, {
  90         'url': 'https://www.rtl.nl/video/c603c9c2-601d-4b5e-8175-64f1e942dc7d/',
  91         'only_matching': True,
  92     }, {
  93         'url': 'https://static.rtl.nl/embed/?uuid=1a2970fc-5c0b-43ff-9fdc-927e39e6d1bc&autoplay=false&publicatiepunt=rtlnieuwsnl',
  94         'only_matching': True,
  95     }, {
  96         # new embed URL schema
  97         'url': 'https://embed.rtl.nl/#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
  98         'only_matching': True,
  99     }]
 100
 101     def _real_extract(self, url):
 102         uuid = self._match_id(url)
 103         info = self._download_json(
 104             'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=adaptive/' % uuid,
 105             uuid)
 106
 107         material = info['material'][0]
 108         title = info['abstracts'][0]['name']
 109         subtitle = material.get('title')
 110         if subtitle:
 111             title += ' - %s' % subtitle
 112         description = material.get('synopsis')
 113
 114         meta = info.get('meta', {})
 115
 116         videopath = material['videopath']
 117         m3u8_url = meta.get('videohost', 'http://manifest.us.rtl.nl') + videopath
 118
 119         formats = self._extract_m3u8_formats(
 120             m3u8_url, uuid, 'mp4', m3u8_id='hls', fatal=False)
 121         self._sort_formats(formats)
 122
 123         thumbnails = []
 124
 125         for p in ('poster_base_url', '"thumb_base_url"'):
 126             if not meta.get(p):
 127                 continue
 128
 129             thumbnails.append({
 130                 'url': self._proto_relative_url(meta[p] + uuid),
 131                 'width': int_or_none(self._search_regex(
 132                     r'/sz=([0-9]+)', meta[p], 'thumbnail width', fatal=False)),
 133                 'height': int_or_none(self._search_regex(
 134                     r'/sz=[0-9]+x([0-9]+)',
 135                     meta[p], 'thumbnail height', fatal=False))
 136             })
 137
 138         return {
 139             'id': uuid,
 140             'title': title,
 141             'formats': formats,
 142             'timestamp': material['original_date'],
 143             'description': description,
 144             'duration': parse_duration(material.get('duration')),
 145             'thumbnails': thumbnails,
 146         }