From 4224607c62d14a457ef3f46bf83dca6f271a592d Mon Sep 17 00:00:00 2001 From: Alexandre Flament Date: Fri, 15 Apr 2022 13:37:27 +0200 Subject: [PATCH] searx.utils.html_to_text: replace
by a space --- searx/utils.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/searx/utils.py b/searx/utils.py index 43a7578d7..ffc9a39d6 100644 --- a/searx/utils.py +++ b/searx/utils.py @@ -88,6 +88,8 @@ class _HTMLTextExtractor(HTMLParser): # pylint: disable=W0223 # (see https://b def handle_starttag(self, tag, attrs): self.tags.append(tag) + if tag == 'br': + self.result.append(' ') def handle_endtag(self, tag): if not self.tags: @@ -142,7 +144,7 @@ def html_to_text(html_str: str) -> str: >>> html_to_text('Example') 'Example' """ - html_str = html_str.replace('\n', ' ') + html_str = html_str.replace('\n', ' ').replace('\r', ' ') html_str = ' '.join(html_str.split()) s = _HTMLTextExtractor() try: