From b768f58c19079d37547e707df40e8138d3e40fec Mon Sep 17 00:00:00 2001 From: Dnomd343 Date: Sun, 16 Oct 2022 02:00:10 +0800 Subject: [PATCH] fix: unsuited segmentation --- src/ixsw.la/extract.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/ixsw.la/extract.py b/src/ixsw.la/extract.py index 72318c5..44cb0ef 100644 --- a/src/ixsw.la/extract.py +++ b/src/ixsw.la/extract.py @@ -23,7 +23,7 @@ def splitHtml(rawHtml: str) -> dict: # extract from raw html content div = '\n'.join(div.prettify().split('\n')[1: -2]) return { 'title': '%s %s' % (title[1], title[2].strip()), - 'content': [x.strip() for x in div.split('
\n
\n')] + 'content': [x.strip() for x in div.split('\n
\n
') if x.strip() != ''] }