youtube_dl/extractor/wrzuta.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     qualities,
  10 )
  11
  12
  13 class WrzutaIE(InfoExtractor):
  14     IE_NAME = 'wrzuta.pl'
  15
  16     _VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/(?P<typ>film|audio)/(?P<id>[0-9a-zA-Z]+)'
  17
  18     _TESTS = [{
  19         'url': 'http://laboratoriumdextera.wrzuta.pl/film/aq4hIZWrkBu/nike_football_the_last_game',
  20         'md5': '9e67e05bed7c03b82488d87233a9efe7',
  21         'info_dict': {
  22             'id': 'aq4hIZWrkBu',
  23             'ext': 'mp4',
  24             'title': 'Nike Football: The Last Game',
  25             'duration': 307,
  26             'uploader_id': 'laboratoriumdextera',
  27             'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd',
  28         },
  29     }, {
  30         'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad',
  31         'md5': '1e546a18e1c22ac6e9adce17b8961ff5',
  32         'info_dict': {
  33             'id': '9oXJqdcndqv',
  34             'ext': 'ogg',
  35             'title': 'David Guetta & Showtek ft. Vassy - Bad',
  36             'duration': 270,
  37             'uploader_id': 'w729',
  38             'description': 'md5:4628f01c666bbaaecefa83476cfa794a',
  39         },
  40     }]
  41
  42     def _real_extract(self, url):
  43         mobj = re.match(self._VALID_URL, url)
  44         video_id = mobj.group('id')
  45         typ = mobj.group('typ')
  46         uploader = mobj.group('uploader')
  47
  48         webpage = self._download_webpage(url, video_id)
  49
  50         quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
  51
  52         audio_table = {'flv': 'mp3', 'webm': 'ogg'}
  53
  54         embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id)
  55
  56         formats = []
  57         for media in embedpage['url']:
  58             if typ == 'audio':
  59                 ext = audio_table[media['type'].split('@')[0]]
  60             else:
  61                 ext = media['type'].split('@')[0]
  62
  63             formats.append({
  64                 'format_id': '%s_%s' % (ext, media['quality'].lower()),
  65                 'url': media['url'],
  66                 'ext': ext,
  67                 'quality': quality(media['quality']),
  68             })
  69
  70         self._sort_formats(formats)
  71
  72         return {
  73             'id': video_id,
  74             'title': self._og_search_title(webpage),
  75             'thumbnail': self._og_search_thumbnail(webpage),
  76             'formats': formats,
  77             'duration': int_or_none(embedpage['duration']),
  78             'uploader_id': uploader,
  79             'description': self._og_search_description(webpage),
  80             'age_limit': embedpage.get('minimalAge', 0),
  81         }