]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/podomatic.py
debian/control: Mark compliance with policy 4.1.1. No further changes needed.
[youtubedl] / youtube_dl / extractor / podomatic.py
index 58200971bece7664e18b94eccb52b368ef5a999b..25fcebf9fa6a06a6bf955468ddf0740b648593a5 100644 (file)
@@ -1,42 +1,69 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
 from .common import InfoExtractor
 import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class PodomaticIE(InfoExtractor):
     IE_NAME = 'podomatic'
 
 
 class PodomaticIE(InfoExtractor):
     IE_NAME = 'podomatic'
-    _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
-
-    _TEST = {
-        u"url": u"http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
-        u"file": u"2009-01-02T16_03_35-08_00.mp3",
-        u"md5": u"84bb855fcf3429e6bf72460e1eed782d",
-        u"info_dict": {
-            u"uploader": u"Science Teaching Tips",
-            u"uploader_id": u"scienceteachingtips",
-            u"title": u"64.  When the Moon Hits Your Eye",
-            u"duration": 446,
+    _VALID_URL = r'''(?x)
+                    (?P<proto>https?)://
+                        (?:
+                            (?P<channel>[^.]+)\.podomatic\.com/entry|
+                            (?:www\.)?podomatic\.com/podcasts/(?P<channel_2>[^/]+)/episodes
+                        )/
+                        (?P<id>[^/?#&]+)
+                '''
+
+    _TESTS = [{
+        'url': 'http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00',
+        'md5': '84bb855fcf3429e6bf72460e1eed782d',
+        'info_dict': {
+            'id': '2009-01-02T16_03_35-08_00',
+            'ext': 'mp3',
+            'uploader': 'Science Teaching Tips',
+            'uploader_id': 'scienceteachingtips',
+            'title': '64.  When the Moon Hits Your Eye',
+            'duration': 446,
+        }
+    }, {
+        'url': 'http://ostbahnhof.podomatic.com/entry/2013-11-15T16_31_21-08_00',
+        'md5': 'd2cf443931b6148e27638650e2638297',
+        'info_dict': {
+            'id': '2013-11-15T16_31_21-08_00',
+            'ext': 'mp3',
+            'uploader': 'Ostbahnhof / Techno Mix',
+            'uploader_id': 'ostbahnhof',
+            'title': 'Einunddreizig',
+            'duration': 3799,
         }
         }
-    }
+    }, {
+        'url': 'https://www.podomatic.com/podcasts/scienceteachingtips/episodes/2009-01-02T16_03_35-08_00',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        channel = mobj.group('channel')
+        channel = mobj.group('channel') or mobj.group('channel_2')
 
         json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
                      '?permalink=true&rtmp=0') %
                     (mobj.group('proto'), channel, video_id))
         data_json = self._download_webpage(
 
         json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
                      '?permalink=true&rtmp=0') %
                     (mobj.group('proto'), channel, video_id))
         data_json = self._download_webpage(
-            json_url, video_id, note=u'Downloading video info')
+            json_url, video_id, 'Downloading video info')
         data = json.loads(data_json)
 
         video_url = data['downloadLink']
         data = json.loads(data_json)
 
         video_url = data['downloadLink']
+        if not video_url:
+            video_url = '%s/%s' % (data['streamer'].replace('rtmp', 'http'), data['mediaLocation'])
         uploader = data['podcast']
         title = data['title']
         thumbnail = data['imageLocation']
         uploader = data['podcast']
         title = data['title']
         thumbnail = data['imageLocation']
-        duration = int(data['length'] / 1000.0)
+        duration = int_or_none(data.get('length'), 1000)
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,