administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 03:10:38 +00:00
Code Issues Projects Releases Wiki Activity

[GlomexEmbed] Avoid large match objects

Browse Source 
Closes #2512
Authored by: zmousm
This commit is contained in:
Zenon Mousmoulas 2022-01-30 15:35:39 +02:00 committed by GitHub
parent b72270d27e
commit 19afd9ea51
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
yt_dlp/extractor/glomex.py
View File

@ -198,8 +198,13 @@ class GlomexEmbedIE(GlomexBaseIE):
)+</script>
)''' % {'quot_re': r'["\']', 'url_re': VALID_SRC}
for mobj in re.finditer(EMBED_RE, webpage):
mdict = mobj.groupdict()
for mtup in re.findall(EMBED_RE, webpage):
# re.finditer causes a memory spike. See https://github.com/yt-dlp/yt-dlp/issues/2512
mdict = dict(zip((
'url', '_',
'html_tag', '_', 'integration_html', '_', 'id_html', '_', 'glomex_player',
'script_tag', '_', '_', 'integration_js', '_', 'id_js',
), mtup))
if mdict.get('url'):
url = unescapeHTML(mdict['url'])
if not cls.suitable(url):