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

"""检查PDF是否为图片型PDF"""
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)}")
    
    # 检查前几页
    for i in range(min(5, len(doc))):
        page = doc[i]
        
        # 获取文本
        text = page.get_text()
        
        # 获取图片
        images = page.get_images()
        
        print(f"\n=== 第 {i+1} 页 ===")
        print(f"文本长度: {len(text)}")
        print(f"图片数量: {len(images)}")
        
        if len(text) == 0 and len(images) > 0:
            print("  → 这页是图片型PDF，需要OCR处理")
        elif len(text) > 0:
            print(f"  → 文本内容: {text[:100]}...")
            
    doc.close()
    
except Exception as e:
    print(f"错误: {e}")
    import traceback
    traceback.print_exc()