From b1eba69085d8b8c8ecdd31eaf1fb68bdf47b9322 Mon Sep 17 00:00:00 2001
From: ldy <1913292237@qq.com>
Date: Fri, 11 Aug 2023 19:16:03 +0800
Subject: [PATCH] Bug Fix: 1. hr_count soup should be article_soup
---
01_EJDE_spider/ejde_main.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/01_EJDE_spider/ejde_main.py b/01_EJDE_spider/ejde_main.py
index 2ea14c9..d13393f 100644
--- a/01_EJDE_spider/ejde_main.py
+++ b/01_EJDE_spider/ejde_main.py
@@ -252,7 +252,7 @@ def process_article(title, article_url):
# If no author table
else:
match_type = 0
- hr_count = len(soup.find_all('hr'))
+ hr_count = len(article_soup.find_all('hr'))
if hr_count < 3:
pattern = r'
(.*?)
'
else: