remove leading and trailing \n for HtmlConverter
This commit is contained in:
parent
05b78e7ce1
commit
08a45fa4bd
1 changed files with 3 additions and 0 deletions
|
|
@ -223,6 +223,9 @@ class HtmlConverter(DocumentConverter):
|
|||
|
||||
assert isinstance(webpage_text, str)
|
||||
|
||||
# remove leading and trailing \n
|
||||
webpage_text = webpage_text.strip()
|
||||
|
||||
return DocumentConverterResult(
|
||||
title=None if soup.title is None else soup.title.string,
|
||||
text_content=webpage_text,
|
||||
|
|
|
|||
Loading…
Reference in a new issue