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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     unified_strdate,
   8     parse_duration,
   9     qualities,
  10     strip_jsonp,
  11     url_basename,
  12 )
  13
  14
  15 class NPOIE(InfoExtractor):
  16     IE_NAME = 'npo.nl'
  17     _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
  22             'md5': '4b3f9c429157ec4775f2c9cb7b911016',
  23             'info_dict': {
  24                 'id': 'VPWON_1220719',
  25                 'ext': 'm4v',
  26                 'title': 'Nieuwsuur',
  27                 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
  28                 'upload_date': '20140622',
  29             },
  30         },
  31         {
  32             'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
  33             'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
  34             'info_dict': {
  35                 'id': 'VARA_101191800',
  36                 'ext': 'm4v',
  37                 'title': 'De Mega Mike & Mega Thomas show',
  38                 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
  39                 'upload_date': '20090227',
  40                 'duration': 2400,
  41             },
  42         },
  43         {
  44             'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
  45             'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
  46             'info_dict': {
  47                 'id': 'VPWON_1169289',
  48                 'ext': 'm4v',
  49                 'title': 'Tegenlicht',
  50                 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
  51                 'upload_date': '20130225',
  52                 'duration': 3000,
  53             },
  54         }
  55     ]
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         video_id = mobj.group('id')
  60         return self._get_info(video_id)
  61
  62     def _get_info(self, video_id):
  63         metadata = self._download_json(
  64             'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
  65             video_id,
  66             # We have to remove the javascript callback
  67             transform_source=strip_jsonp,
  68         )
  69         token_page = self._download_webpage(
  70             'http://ida.omroep.nl/npoplayer/i.js',
  71             video_id,
  72             note='Downloading token'
  73         )
  74         token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')
  75
  76         formats = []
  77         quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
  78         for format_id in metadata['pubopties']:
  79             format_info = self._download_json(
  80                 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token),
  81                 video_id, 'Downloading %s JSON' % format_id)
  82             if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
  83                 continue
  84             streams = format_info.get('streams')
  85             if streams:
  86                 video_info = self._download_json(
  87                     streams[0] + '&type=json',
  88                     video_id, 'Downloading %s stream JSON' % format_id)
  89             else:
  90                 video_info = format_info
  91             video_url = video_info.get('url')
  92             if not video_url:
  93                 continue
  94             if format_id == 'adaptive':
  95                 formats.extend(self._extract_m3u8_formats(video_url, video_id))
  96             else:
  97                 formats.append({
  98                     'url': video_url,
  99                     'format_id': format_id,
 100                     'quality': quality(format_id),
 101                 })
 102         self._sort_formats(formats)
 103
 104         return {
 105             'id': video_id,
 106             'title': metadata['titel'],
 107             'description': metadata['info'],
 108             'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
 109             'upload_date': unified_strdate(metadata.get('gidsdatum')),
 110             'duration': parse_duration(metadata.get('tijdsduur')),
 111             'formats': formats,
 112         }
 113
 114
 115 class TegenlichtVproIE(NPOIE):
 116     IE_NAME = 'tegenlicht.vpro.nl'
 117     _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
 118
 119     _TESTS = [
 120         {
 121             'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
 122             'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
 123             'info_dict': {
 124                 'id': 'VPWON_1169289',
 125                 'ext': 'm4v',
 126                 'title': 'Tegenlicht',
 127                 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
 128                 'upload_date': '20130225',
 129             },
 130         },
 131     ]
 132
 133     def _real_extract(self, url):
 134         name = url_basename(url)
 135         webpage = self._download_webpage(url, name)
 136         urn = self._html_search_meta('mediaurn', webpage)
 137         info_page = self._download_json(
 138             'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
 139         return self._get_info(info_page['mid'])