mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-20 22:03:52 +00:00
Change WebBaseLoader metadata parsing to set missing metadata to descriptive string instead of None
(#8175)
Solves #8174 & #3542 Co-authored-by: mevans <mevans@palantir.com>
This commit is contained in:
parent
1a7d8667c8
commit
72eb4fa4e8
@ -30,9 +30,9 @@ def _build_metadata(soup: Any, url: str) -> dict:
|
||||
if title := soup.find("title"):
|
||||
metadata["title"] = title.get_text()
|
||||
if description := soup.find("meta", attrs={"name": "description"}):
|
||||
metadata["description"] = description.get("content", None)
|
||||
metadata["description"] = description.get("content", "No description found.")
|
||||
if html := soup.find("html"):
|
||||
metadata["language"] = html.get("lang", None)
|
||||
metadata["language"] = html.get("lang", "No language found.")
|
||||
return metadata
|
||||
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user