cfc/docs/参考资料/dan_reports/read_pdf.py

import pdfplumber
import sys
import os

def read_pdf(pdf_path):
    text = ""
    try:
        with pdfplumber.open(pdf_path) as pdf:
            for page in pdf.pages:
                text += page.extract_text() or ""
                text += "\n\n"
        return text
    except Exception as e:
        return f"Error: {e}"

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python read_pdf.py <pdf_file>")
        sys.exit(1)
    
    pdf_file = sys.argv[1]
    if not os.path.exists(pdf_file):
        print(f"File not found: {pdf_file}")
        sys.exit(1)
    
    content = read_pdf(pdf_file)
    # 保存到临时文件，避免编码问题
    import tempfile
    import os
    temp_file = os.path.join(tempfile.gettempdir(), 'pdf_content.txt')
    with open(temp_file, 'w', encoding='utf-8') as f:
        f.write(content)
    print(f"Content saved to: {temp_file}")
    # 只打印关键信息
    print(content[:500] if content else "No content extracted")