[tunein] Add new extractor (Closes #4097)

2 files changed, 102 insertions, 0 deletions

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index fb5e6ac77..cdcda1fa9 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -405,6 +405,7 @@ from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
+from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
diff --git a/youtube_dl/extractor/tunein.py b/youtube_dl/extractor/tunein.py
new file mode 100644
index 000000000..8c29f1634
--- /dev/null
+++ b/youtube_dl/extractor/tunein.py
@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class TuneInIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?
+    (?:
+        tunein\.com/
+        (?:
+            radio/.*?-s|
+            station/.*?StationId\=
+        )(?P<id>[0-9]+)
+        |tun\.in/(?P<redirect_id>[A-Za-z0-9]+)
+    )
+    '''
+
+    _INFO_DICT = {
+        'id': '34682',
+        'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
+        'ext': 'AAC',
+        'thumbnail': 're:^https?://.*\.png$',
+        'location': 'Tacoma, WA',
+    }
+    _TESTS = [
+        {
+            'url': 'http://tunein.com/radio/Jazz24-885-s34682/',
+            'info_dict': _INFO_DICT,
+            'params': {
+                'skip_download': True,  # live stream
+            },
+        },
+        {  # test redirection
+            'url': 'http://tun.in/ser7s',
+            'info_dict': _INFO_DICT,
+            'params': {
+                'skip_download': True,  # live stream
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        redirect_id = mobj.group('redirect_id')
+        if redirect_id:
+            # The server doesn't support HEAD requests
+            urlh = self._request_webpage(
+                url, redirect_id, note='Downloading redirect page')
+            url = urlh.geturl()
+            self.to_screen('Following redirect: %s' % url)
+            mobj = re.match(self._VALID_URL, url)
+        station_id = mobj.group('id')
+
+        webpage = self._download_webpage(
+            url, station_id, note='Downloading station webpage')
+
+        payload = self._html_search_regex(
+            r'(?m)TuneIn\.payload\s*=\s*(\{[^$]+?)$', webpage, 'JSON data')
+        json_data = json.loads(payload)
+        station_info = json_data['Station']['broadcast']
+        title = station_info['Title']
+        thumbnail = station_info.get('Logo')
+        location = station_info.get('Location')
+        streams_url = station_info.get('StreamUrl')
+        if not streams_url:
+            raise ExtractorError('No downloadable streams found',
+                                 expected=True)
+        stream_data = self._download_webpage(
+            streams_url, station_id, note='Downloading stream data')
+        streams = json.loads(self._search_regex(
+            r'\((.*)\);', stream_data, 'stream info'))['Streams']
+
+        is_live = None
+        formats = []
+        for stream in streams:
+            if stream.get('Type') == 'Live':
+                is_live = True
+            formats.append({
+                'abr': stream.get('Bandwidth'),
+                'ext': stream.get('MediaType'),
+                'acodec': stream.get('MediaType'),
+                'vcodec': 'none',
+                'url': stream.get('Url'),
+                # Sometimes streams with the highest quality do not exist
+                'preference': stream.get('Reliability'),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': station_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'location': location,
+            'is_live': is_live,
+        }