Strip URLs from sitemap.

givemelove · web-flow · commit c8c4f17bdc03 · 2025-04-14T16:30:32.000-05:00
Fixes #30829
diff --git a/libs/community/langchain_community/document_loaders/sitemap.py b/libs/community/langchain_community/document_loaders/sitemap.py
@@ -185,7 +185,7 @@ def parse_sitemap(self, soup: Any, *, depth: int = 0) -> List[dict]:
 
             els.append(
                 {
-                    tag: prop.text
+                    tag: prop.text.strip()
                     for tag in ["loc", "lastmod", "changefreq", "priority"]
                     if (prop := url.find(tag))
                 }

Original file line number	Diff line number	Diff line change
`@@ -185,7 +185,7 @@ def parse_sitemap(self, soup: Any, *, depth: int = 0) -> List[dict]:`
`185`	`185`
`186`	`186`	`els.append(`
`187`	`187`	`{`
`188`		`- tag: prop.text`
	`188`	`+ tag: prop.text.strip()`
`189`	`189`	`for tag in ["loc", "lastmod", "changefreq", "priority"]`
`190`	`190`	`if (prop := url.find(tag))`
`191`	`191`	`}`