lqq-agent-study/02_RAG_study/test_pdf.py

"""测试PDF文件是否能正常加载"""
import fitz  # PyMuPDF

# 打开PDF文件
pdf_path = r"D:\investment\疯狂的里海 · 投资方法论 — 基于 367 篇投资周记提炼.pdf"

try:
    doc = fitz.open(pdf_path)
    
    print(f"PDF文件: {pdf_path}")
    print(f"总页数: {len(doc)}")
    print(f"元数据: {doc.metadata}")
    
    # 查看前几页的内容
    for i in range(min(3, len(doc))):
        page = doc[i]
        text = page.get_text()
        print(f"\n=== 第 {i+1} 页 ===")
        print(f"文本长度: {len(text)}")
        print(f"内容预览:\n{text[:500]}...")
        
    doc.close()
    
except Exception as e:
    print(f"错误: {e}")
    import traceback
    traceback.print_exc()