[byutv] Rely on _match_id and _parse_json
authorDéstin Reed <trox1972@users.noreply.github.com>
Fri, 30 Sep 2016 17:59:08 +0000 (19:59 +0200)
committerSergey M․ <dstftw@gmail.com>
Sat, 1 Oct 2016 17:41:18 +0000 (00:41 +0700)
youtube_dl/extractor/byutv.py

index 3aec601f8e7179570088e1ea5ad1f7b6d30f219d..b2d25eec0189681532472590400ae40862bedee0 100644 (file)
@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -8,7 +7,7 @@ from ..utils import ExtractorError
 
 
 class BYUtvIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
+    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<id>[^/?#]+)'
     _TEST = {
         'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
         'md5': '05850eb8c749e2ee05ad5a1c34668493',
@@ -27,15 +26,15 @@ class BYUtvIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         episode_code = self._search_regex(
             r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
-        episode_json = re.sub(
-            r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
-        ep = json.loads(episode_json)
+
+        ep = self._parse_json(
+            episode_code, video_id, transform_source=lambda s:
+            re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
 
         if ep['providerType'] == 'Ooyala':
             return {