From 5f835443e879e18e3f4319f0552a74cecca6449c Mon Sep 17 00:00:00 2001
From: oscarz <oscar@vip.qq.com>
Date: Sun, 23 Mar 2025 10:25:25 +0800
Subject: [PATCH] modify scripts

---
 aabook/src/scraper.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/aabook/src/scraper.py b/aabook/src/scraper.py
index 302690a..3b84a45 100644
--- a/aabook/src/scraper.py
+++ b/aabook/src/scraper.py
@@ -292,6 +292,10 @@ def parse_content_page(soup, url):
                 cleaned_text = process_paragraph(paragraph)
                 content.append(cleaned_text)
 
+    # 某些页面只有<br>标签，soup.stripped_strings：返回去除空白后的所有文本节点。
+    if len(content) == 0:
+        content = [block.strip() for block in soup.stripped_strings if block.strip()]
+
     return content
 
 # 通用的 HTML 结构验证器