youtube-dl

commit 2f1983572659415354c88743130a303af8188caf
parent 533f3e3557af85e28afd72d291cb51a769c7dd7a
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sat, 11 Apr 2020 20:07:12 +0700

[thisoldhouse] Improve video id extraction (closes #24549)

Diffstat:
M
youtube_dl/extractor/thisoldhouse.py
 | 
20
+++++---------------

1 file changed, 5 insertions(+), 15 deletions(-)
diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py
@@ -20,20 +20,6 @@ class ThisOldHouseIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
-        'url': 'https://www.thisoldhouse.com/21083431/seaside-transformation-the-westerly-project',
-        'note': 'test for updated video URL',
-        'info_dict': {
-            'id': '5e2b70e95216cc0001615120',
-            'ext': 'mp4',
-            'title': 'E12 | The Westerly Project | Seaside Transformation',
-            'description': 'Kevin and Tommy take the tour with the homeowners and Jeff. Norm presents his pine coffee table. Jenn gives Tommy the garden tour. Everyone meets at the flagpole to raise the flags.',
-            'timestamp': 1579755600,
-            'upload_date': '20200123',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
         'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
         'only_matching': True,
     }, {
@@ -45,6 +31,10 @@ class ThisOldHouseIE(InfoExtractor):
     }, {
         'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost',
         'only_matching': True,
+    }, {
+        # iframe www.thisoldhouse.com
+        'url': 'https://www.thisoldhouse.com/21083431/seaside-transformation-the-westerly-project',
+        'only_matching': True,
     }]
     _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe'
 
@@ -52,6 +42,6 @@ class ThisOldHouseIE(InfoExtractor):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
         video_id = self._search_regex(
-            r'<iframe[^>]+src=[\'"](?:https?:)?//(?:www\.|)thisoldhouse(?:\.chorus\.build|\.com)/videos/zype/([0-9a-f]{24})',
+            r'<iframe[^>]+src=[\'"](?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})',
             webpage, 'video id')
         return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id)