From 188f01ce820c8d1974261bbef57cb858b2299486 Mon Sep 17 00:00:00 2001 From: Pomin Wu Date: Sun, 8 Dec 2019 22:11:28 +0800 Subject: [PATCH] fix: unicode problem --- readability/readability.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/readability/readability.py b/readability/readability.py index fc682318..117b6b8a 100755 --- a/readability/readability.py +++ b/readability/readability.py @@ -464,7 +464,7 @@ def transform_misused_divs_into_paragraphs(self): # This results in incorrect results in case there is an # buried within an for example if not REGEXES["divToPElementsRe"].search( - str_(b"".join(map(tostring, list(elem)))) + str_("".join(map(tounicode, list(elem)))) ): # log.debug("Altering %s to p" % (describe(elem))) elem.tag = "p"