mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-31 10:23:18 +00:00
community: Strip URLs from sitemap. (#30830)
Fixes #30829 - **Description:** Simply strips the loc value when building the element. - **Issue:** Fixes #30829
This commit is contained in:
@@ -185,7 +185,7 @@ class SitemapLoader(WebBaseLoader):
|
||||
|
||||
els.append(
|
||||
{
|
||||
tag: prop.text
|
||||
tag: prop.text.strip()
|
||||
for tag in ["loc", "lastmod", "changefreq", "priority"]
|
||||
if (prop := url.find(tag))
|
||||
}
|
||||
|
Reference in New Issue
Block a user