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