[NPORadio] Added extractor for live radio

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 095feabf90198a63494fc6b8382f53cef342c6c6..b118c3d1def33fbb95945fd07bdba609075bd902 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -320,6 +320,7 @@ from .npo import (
     NPOLiveIE,
     TegenlichtVproIE,
 )
+from .nporadio import NPORadioIE
 from .nrk import (
     NRKIE,
     NRKTVIE,

diff --git a/youtube_dl/extractor/nporadio.py b/youtube_dl/extractor/nporadio.py
new file mode 100644 (file)
index 0000000..dd8d97c
--- /dev/null
+++ b/youtube_dl/extractor/nporadio.py
@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+
+
+class NPORadioIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>.*)'
+    _TEST = {
+        'url': 'http://www.npo.nl/radio/radio-1',
+        'info_dict': {
+            'id': 'radio-1',
+            'ext': 'mp3',
+            'title': 'NPO Radio 1',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+                self._html_get_attribute_regex('data-channel'), webpage, 'title')
+       
+        json_data = json.loads(
+                     self._html_search_regex(
+                     self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'))
+        
+        return {
+            'id': video_id,
+            'title': title,
+            'ext': json_data['codec'],
+            'url': json_data['url']
+        }
+
+    def _html_get_attribute_regex(self, attribute):
+        return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
+