diff options
| author | AndrewMBL <62922222+AndrewMBL@users.noreply.github.com> | 2020-03-31 15:25:04 +1100 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2020-04-11 20:07:32 +0700 |
| commit | 533f3e3557af85e28afd72d291cb51a769c7dd7a (patch) | |
| tree | e8bd4678408c665d42d4f482cea52b8c450e5b8d /youtube_dl/extractor | |
| parent | 75294a5ed03f4443970478f3f4eac572239cec45 (diff) | |
[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
```
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/thisoldhouse.py | 16 |
1 files changed, 15 insertions, 1 deletions
diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py index 387f955ee..33269705f 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -20,6 +20,20 @@ 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, }, { @@ -38,6 +52,6 @@ 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?:)?//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) |