[thisoldhouse] Fix video id extraction (closes #24548)

Added support for:
with of without "www."
and either  ".chorus.build" or ".com"

It now validated correctly on older URL's
```
<iframe src="https://thisoldhouse.chorus.build/videos/zype/5e33baec27d2e50001d5f52f
```
and newer ones
```
<iframe src="https://www.thisoldhouse.com/videos/zype/5e2b70e95216cc0001615120
```
This commit is contained in:
AndrewMBL 2020-03-31 15:25:04 +11:00 committed by Sergey M․
parent 75294a5ed0
commit 533f3e3557
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -19,6 +19,20 @@ class ThisOldHouseIE(InfoExtractor):
'params': {
'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,
@ -38,6 +52,6 @@ def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'<iframe[^>]+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/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)