mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-10 10:23:16 +00:00
[GlomexEmbed] Avoid large match objects
Closes #2512 Authored by: zmousm
This commit is contained in:
parent
b72270d27e
commit
19afd9ea51
|
@ -198,8 +198,13 @@ def _extract_urls(cls, webpage, origin_url):
|
|||
)+</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):
|
||||
|
|
Loading…
Reference in a new issue