pdf_title_image/textmind_ocr.py

import requests, os, time, json, base64

def create_task(url, file_path, file_url):
    """
    Args:
        url: string, 服务请求链接
        file_path: 本地文件路径
        file_url: 文件链接
    Returns: 响应
    """
    file = open(file_path, 'rb').read()

    # 文件请求
    body = {
        "file": (os.path.basename(file_path), file, "multipart/form-data"),
    }

    data = {
        "file_name": os.path.basename(file_path),
        "return_para_nodes": True
    }

    response = requests.post(url, data=data, files=body)
    return response.json()

def create_task_1(url, file_path, file_url):
    """
    Args:
        url: string, 服务请求链接
        file_path: 本地文件路径
        file_url: 文件链接
    Returns: 响应
    """
   # 文件请求
    with open(file_path, "rb") as f:
        file_data = base64.b64encode(f.read())
    data = {
        "file_data": file_data,
        "file_url": file_url,
        "file_name": os.path.basename(file_path)
    }
    
    # 文档切分参数，非必传
    # return_doc_chunks = json.dumps({"switch": True, "chunk_size": -1})
    # data["return_doc_chunks"] = return_doc_chunks
    
    headers = {'Content-Type': 'application/x-www-form-urlencoded'}

    response = requests.post(url, headers=headers, data=data)
    return response.json()


def query_task(url, task_id):
    """
    Args:
        url: string, 请求链接
        task_id: string, task id
    Returns: 响应
    """
    data = {
        "task_id": task_id
    }

    response = requests.post(url, data=data, files=data)
    return response.json()

def query_task_1(url, task_id):
    """
    Args:
        url: string, 请求链接
        task_id: string, task id
    Returns: 响应
    """
    data = {
        "task_id": task_id
    }
    headers = {'Content-Type': 'application/x-www-form-urlencoded'}

    response = requests.post(url, headers=headers, data=data)
    return response.json()

def request1(bidderFile,nums:int=1):
    try:
        response = create_task_1(request_host, bidderFile, "")
        print('res1  :',response)
        task_id = response['result']['task_id']
        if not task_id: raise ValueError('task_id is None')
    except Exception as e:
        print("request1 :",e)
        time.sleep(10)
        nums += 1
        if nums > 100: return 
        task_id = request1(bidderFile, nums)
    return task_id
    
def request2(task_id,nums:int=1):
    try:
        resp = query_task_1(request_query_host, task_id)
        print('res2  :',resp)
        url = resp['result']['parse_result_url']
        response = requests.get(url)
        response.encoding = 'utf-8'
        response.json()
    except Exception as e:
        print("request2 :",e)
        time.sleep(20)
        nums += 1
        if nums > 500: return 
        response = request2(task_id,nums)
    return response


token = "24.87693e5dd8c2d7d7accf260bb2d265d2.2592000.1733970962.282335-86574608"
# request_host = f"https://aip.baidubce.com/file/2.0/brain/online/v1/parser/task?access_token={token}"
request_host = f"https://aip.baidubce.com/rest/2.0/brain/online/v2/parser/task?access_token={token}"  # 更新
# request_query_host = f"https://aip.baidubce.com/file/2.0/brain/online/v1/parser/task/query?access_token={token}"
request_query_host = f"https://aip.baidubce.com/rest/2.0/brain/online/v2/parser/task/query?access_token={token}"  # 更新
# 测试pdf文件
# file_path = "/mnt/d/Work_PWS/24y_04_SanXia/data/甲方提供材料/结果测试数据/1-监控系统自主可控大型PLC适配研究_中控技术产品_采购程序文件_2/投标文件/北京中天华拓工程技术有限公司-投标文件.pdf"
file_path = "data/zhaocai_datasets/30份数据整理/1-2021_2022年三峡电站左岸厂房中央空调系统主机设备改造/投标文件/广东申菱环境系统股份有限公司.pdf"

# time.sleep(5)
task_id = request1(file_path)
print('1   :',task_id)

time.sleep(10)
response = request2(task_id)
print('2 file_name :',response.json()['file_name'])

# 保存textmind解析结果
with open('data/预审查数据/textmind_result/2021_2022年三峡电站左岸厂房中央空调系统主机设备改造_广东申菱环境系统股份有限公司.json', 'w', encoding='utf-8') as fp:
    json.dump(response.json(), fp, indent=4, ensure_ascii=False)