获取表格

import re

if "result" in json_response and "markdown" in json_response["result"]:
    markdown_content = json_response["result"]["markdown"]
    # 提取所有表格
    tables = re.findall(r'(?:\|.*\n)+', markdown_content)
    tables_md = '\n'.join(tables)
    
    # 保存为md文件
    with open("tables.md", "w", encoding="utf-8") as f:
        f.write(tables_md)

        
tables_json = []

for page in json_response["result"]["pages"]:
    for block in page.get("structured", []):
        if block.get("type") == "table":
            tables_json.append(block)

# 保存为 json 文件
with open("tables.json", "w", encoding="utf-8") as f:
    json.dump(tables_json, f, ensure_ascii=False, indent=2)   

import base64

if "result" in json_response and "excel_base64" in json_response["result"]:
    excel_base64 = json_response["result"]["excel_base64"]
    excel_bytes = base64.b64decode(excel_base64)
    with open("result.xlsx", "wb") as f:
        f.write(excel_bytes)
    print("Excel 文件已保存为 result.xlsx")
else:
    print("未检测到 excel_base64 字段，可能 PDF 中没有表格或参数设置有误。")