diff --git a/flask_app/general/读取文件/按页读取pdf.py b/flask_app/general/读取文件/按页读取pdf.py
index 8b3b10f..3f12648 100644
--- a/flask_app/general/读取文件/按页读取pdf.py
+++ b/flask_app/general/读取文件/按页读取pdf.py
@@ -47,7 +47,7 @@ def extract_text_by_page(file_path):
         return result
 
 
-def process_pages(get_text, total_pages):
+def process_pages(get_text, common_header, total_pages):
     """
     扫描所有页面，返回第一个和最后一个包含有效文本的页面索引。
     如果所有页面都为空，则返回 0 到 total_pages - 1。
@@ -57,6 +57,7 @@ def process_pages(get_text, total_pages):
     for page_num in range(total_pages):
         try:
             text = get_text(page_num)
+            cleaned_text = clean_page_content(text, common_header)
         except Exception as e:
             print(f"读取第 {page_num} 页失败: {e}")
             continue
@@ -75,12 +76,13 @@ def process_pages(get_text, total_pages):
     return start_page, end_page
 
 def read_pdf_main(pdf_path):
+    common_header=extract_common_header(pdf_path)
     try:
         with open(pdf_path, "rb") as f:
             pdf_document = PdfReader(f)
             total_pages = len(pdf_document.pages)
             get_text = create_get_text_function('pypdf2', pdf_document)
-            start_page, end_page = process_pages(get_text, total_pages)
+            start_page, end_page = process_pages(get_text, common_header,total_pages)
             return start_page, end_page
     except Exception as e_pypdf2:
         print(f"extract_pages_generic: 使用 PyPDF2 读取 PDF 失败: {e_pypdf2}")
@@ -90,7 +92,7 @@ def read_pdf_main(pdf_path):
         with fitz.open(pdf_path) as pdf_document:
             total_pages = pdf_document.page_count
             get_text = create_get_text_function('fitz', pdf_document)
-            start_page, end_page = process_pages(get_text, total_pages)
+            start_page, end_page = process_pages(get_text, common_header,total_pages)
         return start_page, end_page
     except Exception as e_pypdf2:
         print(f"extract_pages_generic: 使用 fitz 读取 PDF 失败: {e_pypdf2}")