Ver Fonte

[huffpost] Fix extractor

Philipp Hagemeister há 11 anos atrás
pai
commit
d16076ff3e
1 ficheiros alterados com 16 adições e 4 exclusões
  1. 16 4
      youtube_dl/extractor/huffpost.py

+ 16 - 4
youtube_dl/extractor/huffpost.py

@@ -22,11 +22,12 @@ class HuffPostIE(InfoExtractor):
     _TEST = {
     _TEST = {
         'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677',
         'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677',
         'file': '52dd3e4b02a7602131000677.mp4',
         'file': '52dd3e4b02a7602131000677.mp4',
-        'md5': 'TODO',
+        'md5': '55f5e8981c1c80a64706a44b74833de8',
         'info_dict': {
         'info_dict': {
-            'title': 'TODO',
-            'description': 'TODO',
+            'title': 'Legalese It! with @MikeSacksHP',
+            'description': 'This week on Legalese It, Mike talks to David Bosco about his new book on the ICC, "Rough Justice," he also discusses the Virginia AG\'s historic stance on gay marriage, the execution of Edgar Tamayo, the ICC\'s delay of Kenya\'s President and more.  ',
             'duration': 1549,
             'duration': 1549,
+            'upload_date': '20140124',
         }
         }
     }
     }
 
 
@@ -39,7 +40,8 @@ class HuffPostIE(InfoExtractor):
 
 
         video_title = data['title']
         video_title = data['title']
         duration = parse_duration(data['running_time'])
         duration = parse_duration(data['running_time'])
-        upload_date = unified_strdate(data['schedule']['started_at'])
+        upload_date = unified_strdate(data['schedule']['starts_at'])
+        description = data.get('description')
 
 
         thumbnails = []
         thumbnails = []
         for url in data['images'].values():
         for url in data['images'].values():
@@ -58,11 +60,21 @@ class HuffPostIE(InfoExtractor):
             'url': url,
             'url': url,
             'vcodec': 'none' if key.startswith('audio/') else None,
             'vcodec': 'none' if key.startswith('audio/') else None,
         } for key, url in data['sources']['live'].items()]
         } for key, url in data['sources']['live'].items()]
+        if data.get('fivemin_id'):
+            fid = data['fivemin_id']
+            fcat = str(int(fid) // 100 + 1)
+            furl = 'http://avideos.5min.com/2/' + fcat[-3:] + '/' + fcat + '/' + fid + '.mp4'
+            formats.append({
+                'format': 'fivemin',
+                'url': furl,
+                'preference': 1,
+            })
         self._sort_formats(formats)
         self._sort_formats(formats)
 
 
         return {
         return {
             'id': video_id,
             'id': video_id,
             'title': video_title,
             'title': video_title,
+            'description': description,
             'formats': formats,
             'formats': formats,
             'duration': duration,
             'duration': duration,
             'upload_date': upload_date,
             'upload_date': upload_date,