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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import ExtractorError
   8 from ..compat import compat_urlparse
   9
  10
  11 class TuneInBaseIE(InfoExtractor):
  12     _API_BASE_URL = 'http://tunein.com/tuner/tune/'
  13
  14     def _real_extract(self, url):
  15         content_id = self._match_id(url)
  16
  17         content_info = self._download_json(
  18             self._API_BASE_URL + self._API_URL_QUERY % content_id,
  19             content_id, note='Downloading JSON metadata')
  20
  21         title = content_info['Title']
  22         thumbnail = content_info.get('Logo')
  23         location = content_info.get('Location')
  24         streams_url = content_info.get('StreamUrl')
  25         if not streams_url:
  26             raise ExtractorError('No downloadable streams found', expected=True)
  27         if not streams_url.startswith('http://'):
  28             streams_url = compat_urlparse.urljoin(url, streams_url)
  29
  30         stream_data = self._download_webpage(
  31             streams_url, content_id, note='Downloading stream data')
  32         streams = json.loads(self._search_regex(
  33             r'\((.*)\);', stream_data, 'stream info'))['Streams']
  34
  35         is_live = None
  36         formats = []
  37         for stream in streams:
  38             if stream.get('Type') == 'Live':
  39                 is_live = True
  40             reliability = stream.get('Reliability')
  41             format_note = (
  42                 'Reliability: %d%%' % reliability
  43                 if reliability is not None else None)
  44             formats.append({
  45                 'preference': (
  46                     0 if reliability is None or reliability > 90
  47                     else 1),
  48                 'abr': stream.get('Bandwidth'),
  49                 'ext': stream.get('MediaType').lower(),
  50                 'acodec': stream.get('MediaType'),
  51                 'vcodec': 'none',
  52                 'url': stream.get('Url'),
  53                 'source_preference': reliability,
  54                 'format_note': format_note,
  55             })
  56         self._sort_formats(formats)
  57
  58         return {
  59             'id': content_id,
  60             'title': title,
  61             'formats': formats,
  62             'thumbnail': thumbnail,
  63             'location': location,
  64             'is_live': is_live,
  65         }
  66
  67
  68 class TuneInClipIE(TuneInBaseIE):
  69     IE_NAME = 'tunein:clip'
  70     _VALID_URL = r'https?://(?:www\.)?tunein\.com/station/.*?audioClipId\=(?P<id>\d+)'
  71     _API_URL_QUERY = '?tuneType=AudioClip&audioclipId=%s'
  72
  73     _TESTS = [
  74         {
  75             'url': 'http://tunein.com/station/?stationId=246119&audioClipId=816',
  76             'md5': '99f00d772db70efc804385c6b47f4e77',
  77             'info_dict': {
  78                 'id': '816',
  79                 'title': '32m',
  80                 'ext': 'mp3',
  81             },
  82         },
  83     ]
  84
  85
  86 class TuneInStationIE(TuneInBaseIE):
  87     IE_NAME = 'tunein:station'
  88     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-s|station/.*?StationId\=)(?P<id>\d+)'
  89     _API_URL_QUERY = '?tuneType=Station&stationId=%s'
  90
  91     @classmethod
  92     def suitable(cls, url):
  93         return False if TuneInClipIE.suitable(url) else super(TuneInStationIE, cls).suitable(url)
  94
  95     _TESTS = [
  96         {
  97             'url': 'http://tunein.com/radio/Jazz24-885-s34682/',
  98             'info_dict': {
  99                 'id': '34682',
 100                 'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
 101                 'ext': 'mp3',
 102                 'location': 'Tacoma, WA',
 103             },
 104             'params': {
 105                 'skip_download': True,  # live stream
 106             },
 107         },
 108     ]
 109
 110
 111 class TuneInProgramIE(TuneInBaseIE):
 112     IE_NAME = 'tunein:program'
 113     _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-p|program/.*?ProgramId\=)(?P<id>\d+)'
 114     _API_URL_QUERY = '?tuneType=Program&programId=%s'
 115
 116     _TESTS = [
 117         {
 118             'url': 'http://tunein.com/radio/Jazz-24-p2506/',
 119             'info_dict': {
 120                 'id': '2506',
 121                 'title': 'Jazz 24 on 91.3 WUKY-HD3',
 122                 'ext': 'mp3',
 123                 'location': 'Lexington, KY',
 124             },
 125             'params': {
 126                 'skip_download': True,  # live stream
 127             },
 128         },
 129     ]
 130
 131
 132 class TuneInTopicIE(TuneInBaseIE):
 133     IE_NAME = 'tunein:topic'
 134     _VALID_URL = r'https?://(?:www\.)?tunein\.com/topic/.*?TopicId\=(?P<id>\d+)'
 135     _API_URL_QUERY = '?tuneType=Topic&topicId=%s'
 136
 137     _TESTS = [
 138         {
 139             'url': 'http://tunein.com/topic/?TopicId=101830576',
 140             'md5': 'c31a39e6f988d188252eae7af0ef09c9',
 141             'info_dict': {
 142                 'id': '101830576',
 143                 'title': 'Votez pour moi du 29 octobre 2015 (29/10/15)',
 144                 'ext': 'mp3',
 145                 'location': 'Belgium',
 146             },
 147         },
 148     ]
 149
 150
 151 class TuneInShortenerIE(InfoExtractor):
 152     IE_NAME = 'tunein:shortener'
 153     IE_DESC = False  # Do not list
 154     _VALID_URL = r'https?://tun\.in/(?P<id>[A-Za-z0-9]+)'
 155
 156     _TEST = {
 157         # test redirection
 158         'url': 'http://tun.in/ser7s',
 159         'info_dict': {
 160             'id': '34682',
 161             'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
 162             'ext': 'mp3',
 163             'location': 'Tacoma, WA',
 164         },
 165         'params': {
 166             'skip_download': True,  # live stream
 167         },
 168     }
 169
 170     def _real_extract(self, url):
 171         redirect_id = self._match_id(url)
 172         # The server doesn't support HEAD requests
 173         urlh = self._request_webpage(
 174             url, redirect_id, note='Downloading redirect page')
 175         url = urlh.geturl()
 176         self.to_screen('Following redirect: %s' % url)
 177         return self.url_result(url)