From 514f84266e4878537ac53dd73e6a7209c2e4da5e Mon Sep 17 00:00:00 2001 From: ningwenchang Date: Wed, 26 Nov 2025 14:36:33 +0800 Subject: [PATCH] fix:Fixed the whitespace issue caused by pretty_print parameter in etree.tostring function. --- llm_web_kit/main_html_parser/simplify_html/simplify_html.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llm_web_kit/main_html_parser/simplify_html/simplify_html.py b/llm_web_kit/main_html_parser/simplify_html/simplify_html.py index 05b8352e..f2a1391a 100644 --- a/llm_web_kit/main_html_parser/simplify_html/simplify_html.py +++ b/llm_web_kit/main_html_parser/simplify_html/simplify_html.py @@ -887,6 +887,6 @@ def simplify_html(html_str) -> etree.Element: simplified_html = process_paragraphs(paragraphs, original_uid_map) remove_all_uids(original_dom) - original_html = etree.tostring(original_dom, pretty_print=True, method='html', encoding='unicode') + original_html = etree.tostring(original_dom, pretty_print=False, method='html', encoding='unicode') return simplified_html, original_html