first commit

view_pdf.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+"""
+分析PDF文件结构，查看前几页内容
+"""
+from PyPDF2 import PdfReader
+
+def view_pdf_content(pdf_path, start_page=0, end_page=5):
+    """
+    查看PDF指定页面的内容
+    """
+    reader = PdfReader(pdf_path)
+    total_pages = len(reader.pages)
+    print(f"PDF总页数: {total_pages}")
+    
+    for page_num in range(start_page, min(end_page, total_pages)):
+        page = reader.pages[page_num]
+        text = page.extract_text()
+        print(f"\n{'='*60}")
+        print(f"第 {page_num + 1} 页:")
+        print('='*60)
+        if text:
+            print(text[:2000])
+        else:
+            print("(无文本内容)")
+
+if __name__ == '__main__':
+    pdf_path = '/Users/duguoyou/D365/MB-330_with_discussion.pdf'
+    view_pdf_content(pdf_path, 0, 3)