moved from xml data to json

youtube_dl/extractor/npr.py

@@ -27,45 +27,45 @@ class NprIE(InfoExtractor):
         webpage = self._download_webpage(webpage_url, video_id)
         key = 'MDAzMzQ2MjAyMDEyMzk4MTU1MDg3ZmM3MQ010'
         xml_url = 'http://api.npr.org/query?id=%s&apiKey=%s' % (video_id, key)
+        json_url = 'http://api.npr.org/query?id=%s&apiKey=%s&format=json' % (video_id, key)
 
-        config = self._download_xml(xml_url,video_id, note='Downloading XML')
+        formats = []
-
-        audio = config.findall('./list/story/audio[@type="standard"]')
-        if not audio:
-            # audio type is primary
-            audio = config.findall('./list/story/audio[@type="primary"]')
-
-        regex = ('.//*[@type="mp3"]','.//*[@type="m3u"]','.//format/wm','.//format/threegp','.//format/mp4','.//format/hls','.//format/mediastream')
-        album_title = config.find('.//albumTitle')
-
-        if not album_title:
-            album_title = config.find('./list/story/title').text
-        else:
-            album_title = album_title.text
-
-        print(album_title)
-        format = []
         entries = []
-        for song in audio:
-            song_title = song.find('title').text
-            song_id = song.get('id')
-            song_duration = song.find('duration').text
 
-            for r in regex:
+        config = self._download_json(json_url, video_id)
-                t = song.find(r)
-                if t is not None:
-                    format.append({'format': t.get('type', t.tag),
-                               'url' : t.text})
 
-            entries.append({ "title":song_title,
+        content = config["list"]["story"]
-                             "id":song_id,
-                             "duration": str(int(song_duration) / 60) +":"+ str(int(song_duration) % 60) ,
-                             "formats":format})
-            format = []
 
-        return {
+        album_title = config["list"]["story"][0]['song'][0]['album']['albumTitle']
-            '_type': 'playlist',
+        print album_title['$text']
-            'id' : video_id,
+
-            'title' : album_title,
+        for key in content:
-            'entries': entries
+            if "audio" in key:
-        }
+                for x in key['audio']:
+                    if x['type'] == 'standard':
+                        playlist = True
+                        song_duration = x["duration"]['$text']
+                        song_title = x["title"]["$text"]
+                        song_id = x["id"]
+
+                        for k in x["format"]:
+                            if type(x["format"][k]) is list:
+                                for z in x["format"][k]:
+                                    formats.append({ 'format': z['type'], 
+                                                     'url'   : z['$text']
+                                              })
+                            else:
+                                formats.append({ 'format': k, 
+                                                 'url'   : x["format"][k]['$text']
+                                      })
+
+                        entries.append({ "title":song_title,
+                                         "id":song_id,
+                                         "duration": song_duration ,
+                                         "formats":formats})
+                        formats = []
+
+        return {    '_type': 'playlist',
+                    'id' : video_id,
+                    'title' : album_title,
+                    'entries': entries  }