onemap-implementationSupervision-system-python/pdf/pdf_tables_to_excel.py

# -*- coding: utf-8 -*-
import tabula
import pandas as pd


def pdf_tables_to_excel(pdf_path, excel_path, pages='77-84'):
    """
    使用tabula提取PDF表格
    """
    try:
        # 读取PDF表格
        tables = tabula.read_pdf(pdf_path, pages=pages, multiple_tables=True, lattice=True)

        print("找到 {len(tables)} 个表格")

        with pd.ExcelWriter(excel_path, engine='openpyxl') as writer:
            for i, df in enumerate(tables):
                sheet_name = 'Table_{i + 1}'
                # 确保sheet名称有效
                sheet_name = sheet_name[:31]
                df.to_excel(writer, sheet_name=sheet_name, index=False)

                print("表格 {i + 1}: {df.shape[0]} 行 x {df.shape[1]} 列")

        print("导出完成: {excel_path}")

    except Exception as e:
        print("错误: {e}")


# 使用示例
if __name__ == "__main__":
    pdf_tables_to_excel(
        "E:\projects\通辽市一张图监督实施系统\体检成果\22成果-20240704按部下发实体地域修改后成果\通辽市2022年度城市体检评估报告.pd",
        "E:\projects\通辽市一张图监督实施系统\体检成果\22成果-20240704按部下发实体地域修改后成果\output.xlsx",
        pages='77-84')