remove leading and trailing \n for HtmlConverter (#262)
This commit is contained in:
@@ -236,6 +236,9 @@ class HtmlConverter(DocumentConverter):
|
|||||||
|
|
||||||
assert isinstance(webpage_text, str)
|
assert isinstance(webpage_text, str)
|
||||||
|
|
||||||
|
# remove leading and trailing \n
|
||||||
|
webpage_text = webpage_text.strip()
|
||||||
|
|
||||||
return DocumentConverterResult(
|
return DocumentConverterResult(
|
||||||
title=None if soup.title is None else soup.title.string,
|
title=None if soup.title is None else soup.title.string,
|
||||||
text_content=webpage_text,
|
text_content=webpage_text,
|
||||||
|
|||||||
Reference in New Issue
Block a user