[drbonanza] Simplify and fix duration (#4687)

youtube_dl/extractor/drbonanza.py

@@ -1,11 +1,15 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from .common import ExtractorError
-from ..utils import parse_iso8601
 import json
 import re
 
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
 class DRBonanzaIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
 
@@ -17,11 +21,12 @@ class DRBonanzaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Talkshowet - Leonard Cohen',
             'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
             'timestamp': 1295537932,
             'upload_date': '20110120',
-            'duration': 3664000,
+            'duration': 3664,
         },
-    },{
+    }, {
         'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
         'md5': '6dfe039417e76795fb783c52da3de11d',
         'info_dict': {
@@ -29,36 +34,46 @@ class DRBonanzaIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
             'description': 'md5:501e5a195749480552e214fbbed16c4e',
+            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
             'timestamp': 1223274900,
             'upload_date': '20081006',
-            'duration': 7369000,
+            'duration': 7369,
         },
     }]
 
     def _real_extract(self, url):
         url_id = self._match_id(url)
-        
+        webpage = self._download_webpage(url, url_id)
-        webpage = self._download_webpage(url, url_id if url_id else "")
 
         if url_id:
-            info = json.loads(self._html_search_regex(r'({.*?' + url_id + '.*})', webpage, 'json'))
+            info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
         else:
             # Just fetch the first video on that page
             info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
 
         asset_id = str(info['AssetId'])
         title = info['Title'].rstrip(' \'\"-,.:;!?')
-        duration = info['Duration']
+        duration = int_or_none(info.get('Duration'), scale=1000)
-        timestamp = parse_iso8601(re.sub(r'\.\d+$', '', info['Created'])) # First published online. "FirstPublished" contains the date for original airing.
+        # First published online. "FirstPublished" contains the date for original airing.
+        timestamp = parse_iso8601(
+            re.sub(r'\.\d+$', '', info['Created']))
 
         def parse_filename_info(url):
             match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
             if match:
-                return {'width': int(match.group(1)), 'height': int(match.group(2)), 'bitrate': int(match.group(3)), 'ext': match.group(4)}
+                return {
+                    'width': int(match.group('width')),
+                    'height': int(match.group('height')),
+                    'vbr': int(match.group('bitrate')),
+                    'ext': match.group('ext')
+                }
             match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
             if match:
-                return {'bitrate': int(match.group(1)), 'ext': match.group(2)}
+                return {
-            return {'width': None, 'height': None, 'bitrate': None, 'ext': None}
+                    'vbr': int(match.group('bitrate')),
+                    'ext': match.group(2)
+                }
+            return {}
 
         video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
         preferencemap = {
@@ -72,37 +87,33 @@ class DRBonanzaIE(InfoExtractor):
         for file in info['Files']:
             if info['Type'] == "Video":
                 if file['Type'] in video_types:
-                    fileinfo = parse_filename_info(file['Location'])
+                    format = parse_filename_info(file['Location'])
-                    formats.append({
+                    format.update({
                         'url': file['Location'],
                         'format_id': file['Type'].replace('Video', ''),
                         'preference': preferencemap.get(file['Type'], -10),
-                        'width': fileinfo['width'],
-                        'height': fileinfo['height'],
-                        'vbr': fileinfo['bitrate'],
-                        'ext': fileinfo['ext'],
                     })
+                    formats.append(format)
                 elif file['Type'] == "Thumb":
                     thumbnail = file['Location']
             elif info['Type'] == "Audio":
                 if file['Type'] == "Audio":
-                    fileinfo = parse_filename_info(file['Location'])
+                    format = parse_filename_info(file['Location'])
-                    formats.append({
+                    format.update({
                         'url': file['Location'],
                         'format_id': file['Type'],
-                        'abr': fileinfo['bitrate'],
-                        'ext': fileinfo['ext'],
                         'vcodec': 'none',
                     })
+                    formats.append(format)
                 elif file['Type'] == "Thumb":
                     thumbnail = file['Location']
 
-        description = "{}\n{}\n{}\n".format(info['Description'], info['Actors'], info['Colophon'])
+        description = '%s\n%s\n%s\n' % (
+            info['Description'], info['Actors'], info['Colophon'])
 
         for f in formats:
             f['url'] = f['url'].replace('rtmp://vod-bonanza.gss.dr.dk/bonanza/', 'http://vodfiles.dr.dk/')
             f['url'] = f['url'].replace('mp4:bonanza', 'bonanza')
-        
         self._sort_formats(formats)
 
         display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id