youtube-dl

commit 6d2549fb4f2a646b6b6898db5281cde669277626
parent 4da4516973b56bcaa65794a8ae0856cf54740c54
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun,  2 Oct 2016 00:44:54 +0700

[byutv] Fix id and display id

Diffstat:
M
youtube_dl/extractor/byutv.py
 | 
46
++++++++++++++++++++++++++--------------------

1 file changed, 26 insertions(+), 20 deletions(-)
diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py
@@ -7,15 +7,15 @@ from ..utils import ExtractorError
 
 
 class BYUtvIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<id>[^/?#]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?byutv.org/watch/(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
+    _TESTS = [{
         'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
-        'md5': '05850eb8c749e2ee05ad5a1c34668493',
         'info_dict': {
-            'id': 'studio-c-season-5-episode-5',
+            'id': '6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
+            'display_id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'title': 'Season 5 Episode 5',
+            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 1486.486,
         },
@@ -23,28 +23,34 @@ class BYUtvIE(InfoExtractor):
             'skip_download': True,
         },
         'add_ie': ['Ooyala'],
-    }
+    }, {
+        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
         episode_code = self._search_regex(
             r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
 
         ep = self._parse_json(
-            episode_code, video_id, transform_source=lambda s:
+            episode_code, display_id, transform_source=lambda s:
             re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
 
-        if ep['providerType'] == 'Ooyala':
-            return {
-                '_type': 'url_transparent',
-                'ie_key': 'Ooyala',
-                'url': 'ooyala:%s' % ep['providerId'],
-                'id': video_id,
-                'title': ep['title'],
-                'description': ep.get('description'),
-                'thumbnail': ep.get('imageThumbnail'),
-            }
-        else:
+        if ep['providerType'] != 'Ooyala':
             raise ExtractorError('Unsupported provider %s' % ep['provider'])
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % ep['providerId'],
+            'id': video_id,
+            'display_id': display_id,
+            'title': ep['title'],
+            'description': ep.get('description'),
+            'thumbnail': ep.get('imageThumbnail'),
+        }