diff options
| author | Matthew <coletdjnz@protonmail.com> | 2022-10-14 17:32:52 +1300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-10-14 04:32:52 +0000 |
| commit | 6dca2aa66de8a142543d5c8b6ccadd251339648e (patch) | |
| tree | 5997b112459e0d25001e2b328eece7af5943bc19 /yt_dlp/extractor/generic.py | |
| parent | 6678a4f0b3074f41f02e968d1d48d7c64e48ef07 (diff) | |
| download | hypervideo-pre-6dca2aa66de8a142543d5c8b6ccadd251339648e.tar.lz hypervideo-pre-6dca2aa66de8a142543d5c8b6ccadd251339648e.tar.xz hypervideo-pre-6dca2aa66de8a142543d5c8b6ccadd251339648e.zip | |
[extractor/generic:quoted-html] Add extractor (#5213)
Extracts embeds from escaped HTML within `data-html` attribute.
Related: https://github.com/ytdl-org/youtube-dl/issues/21294, https://github.com/yt-dlp/yt-dlp/pull/5121
Authored by: coletdjnz
Co-authored-by: pukkandan <pukkandan.ytdlp@gmail.com>
Diffstat (limited to 'yt_dlp/extractor/generic.py')
| -rw-r--r-- | yt_dlp/extractor/generic.py | 22 |
1 files changed, 0 insertions, 22 deletions
diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py index ad4e3c5b8..b7a5ffb5b 100644 --- a/yt_dlp/extractor/generic.py +++ b/yt_dlp/extractor/generic.py @@ -1980,22 +1980,6 @@ class GenericIE(InfoExtractor): }, 'playlist_count': 6, }, - { - # Squarespace video embed, 2019-08-28 - 'url': 'http://ootboxford.com', - 'info_dict': { - 'id': 'Tc7b_JGdZfw', - 'title': 'Out of the Blue, at Childish Things 10', - 'ext': 'mp4', - 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f', - 'uploader_id': 'helendouglashouse', - 'uploader': 'Helen & Douglas House', - 'upload_date': '20140328', - }, - 'params': { - 'skip_download': True, - }, - }, # { # # Zype embed # 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', @@ -2784,12 +2768,6 @@ class GenericIE(InfoExtractor): # There probably should be a second run of generic extractor on unescaped webpage. # webpage = urllib.parse.unquote(webpage) - # Unescape squarespace embeds to be detected by generic extractor, - # see https://github.com/ytdl-org/youtube-dl/issues/21294 - webpage = re.sub( - r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>', - lambda x: unescapeHTML(x.group(0)), webpage) - # TODO: Move to respective extractors bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage) if bc_urls: |