百度（表格OCR异步接口）API调用流程

目录

1.调用费用：

 2.调用流程

1）注册百度账号并进行个人/企业认证

2）领取免费资源流程

2）1）百度智能云--控制台--产品服务--文字识别

2）2）领取免费资源

 2）3）勾选“通用场景OCR”，0元领取 

 3）获取APP_ID、API_KEY、Secret_Key

3）1）公有云服务--应用列表--创建应用

3）2）应用名称-（接口默认勾选，不需要额外操作）-应用描述--立即创建 

 3）3）成功获得APP_ID、API_KEY、Secret_Key

 4）运行代码（代码根据生成结果形式分为两类excel、json）

4）1）生成结果以excel形式保存

4）2）生成结果以json形式保存

3.json文件主要信息（举例信息以字典形式给出）

---

1.调用费用：

在控制台-免费资源页面，可领取所需接口的免费测试资源。个人认证 500 次/月，企业认证 1,000 次/月。

链接：百度智能云-管理中心 (baidu.com)

超出部分价格：0~5万次-->0.3元/次；5~10万次-->0.26元/次（其他详见表格所示价格）

 2.调用流程

1）注册百度账号并进行个人/企业认证

百度云链接：百度智能云-智能时代基础设施 (baidu.com)

2）领取免费资源流程

2）1）百度智能云--控制台--产品服务--文字识别

2）2）领取免费资源

 2）3）勾选“通用场景OCR”，0元领取 

 3）获取APP_ID、API_KEY、Secret_Key

同2）1）进入控制台界面

3）1）公有云服务--应用列表--创建应用

3）2）应用名称-（接口默认勾选，不需要额外操作）-应用描述--立即创建 

 3）3）成功获得APP_ID、API_KEY、Secret_Key

 4）运行代码（代码根据生成结果形式分为两类excel、json）

代码修改初始信息：APP_ID、API_KEY、Secret_Key、img_path、save_path

4）1）生成结果以excel形式保存

# encoding: utf-8
import os
import sys
import requests
import time
import tkinter as tk
from tkinter import filedialog
from aip import AipOcr
import time

"""定义常量"""
APP_ID = ''
API_KEY = ''
SECRET_KEY = ''
"""初始化AipFace对象"""
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
image_path = 'D:\\table_generation-master\\demo\\table_recog_test'
save_path  = 'D:\\table_generation-master\\demo\\table_recog_test_output'

"""读取图片"""
def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()


"""文件下载函数"""
def file_download(url, file_path):
    r = requests.get(url)
    with open(file_path, 'wb') as f:
        f.write(r.content)


if __name__ == "__main__":
    root = tk.Tk()
    root.withdraw()
    # data_dir = filedialog.askdirectory(title='请选择图片文件夹') + '/'
    # result_dir = filedialog.askdirectory(title='请选择输出文件夹') + '/'
    data_dir  = image_path
    result_dir = save_path
    num = 0
    for name in os.listdir(data_dir):
        print ('{0} : {1} 正在处理：'.format(num+1, name.split('.')[0]))
        image = get_file_content(os.path.join(data_dir, name))
        res = client.tableRecognitionAsync(image, )
        print ("res:", res)
        if 'error_code' in res.keys():
            print ('Error! error_code: ', res['error_code'])
            sys.exit()

        req_id = res['result'][0]['request_id']    #获取识别ID号
        print("ID:", req_id)

        for count in range(1, 20):    #OCR识别也需要一定时间，设定10秒内每隔1秒查询一次
            res = client.getTableRecognitionResult(req_id) #通过ID获取表格文件XLS地址
            print("xls_path{}".format(res))
            print(res['result']['ret_msg'])

            if res['result']['ret_msg'] == '已完成':
                break    #云端处理完毕，成功获取表格文件下载地址，跳出循环
            else:
                time.sleep(1)

        url = res['result']['result_data']
        xls_name = name.split('.')[0] + '.xls'
        file_download(url, os.path.join(result_dir, xls_name))
        num += 1
        print ('{0} : {1} 下载完成。'.format(num, xls_name))
        time.sleep(1)

4）2）生成结果以json形式保存

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import copy
import json

from baidubce import bce_base_client
from baidubce.auth import bce_credentials
from baidubce.auth import bce_v1_signer
from baidubce.http import bce_http_client
from baidubce.http import handler
from baidubce.http import http_methods
from baidubce import bce_client_configuration
import requests
import base64
import time
# from try6 import webimage
from urllib.parse import urlencode
API_KEY = ''
SECRET_KEY = ''
img_path = "D:\\table_generation-master\\demo\\table_recog_test\\0M208145r02110zw_1.png"
save_path  = "D:\\table_generation-master\\demo\\baidu_result\\jit_baidu.json"

def change_img_to_base64(image_path):
    """base64编码图片-->url"""
    with open(image_path, 'rb') as f:
        image_data = f.read()
        base64_data: bytes = base64.b64encode(image_data)  # base64编码
        return base64_data
# def change_base64_to_url(base64_data):

def get_request_di():
    # client_id 为官网获取的AK， client_secret 为官网获取的SK
    host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={}&client_secret={}'.format(API_KEY,SECRET_KEY)
    response = requests.get(host)
    if response:
        access_token_get = response.json()["access_token"]
    request_url = "https://aip.baidubce.com/rest/2.0/solution/v1/form_ocr/request"
    # 二进制方式打开图片文件
    f = open(img_path, 'rb')
    img_base64 = base64.b64encode(f.read())
    # img = webimage(img_base64, access_token_get)
    params = {"image":img_base64}
    request_url = request_url + "?access_token=" + access_token_get
    headers = {'content-type': 'application/x-www-form-urlencoded'}
    response = requests.post(request_url, data=params, headers=headers, json=True)
    if response:
        request_id = response.json()["result"][0]["request_id"]
        print(response.json())
        print(request_id)
    return request_id, access_token_get


class ApiCenterClient(bce_base_client.BceBaseClient):

    def __init__(self, config=None):
        self.service_id = 'apiexplorer'
        self.region_supported = True
        self.config = copy.deepcopy(bce_client_configuration.DEFAULT_CONFIG)

        if config is not None:
            self.config.merge_non_none_values(config)

    def _merge_config(self, config=None):
        if config is None:
            return self.config
        else:
            new_config = copy.copy(self.config)
            new_config.merge_non_none_values(config)
            return new_config

    def _send_request(self, http_method, path,
                      body=None, headers=None, params=None,
                      config=None, body_parser=None):
        config = self._merge_config(config)
        if body_parser is None:
            body_parser = handler.parse_json

        return bce_http_client.send_request(
            config, bce_v1_signer.sign, [handler.parse_error, body_parser],
            http_method, path, body, headers, params)

    def demo(self,request_id, access_tok):
        path = b'/rest/2.0/solution/v1/form_ocr/get_request_result'
        headers = {}
        headers[b'Content-Type'] = 'application/x-www-form-urlencoded;charset=UTF-8'

        params = {}

        params['access_token'] = access_tok

        body = 'request_id={}&result_type=json'.format(request_id)
        return self._send_request(http_methods.POST, path, body, headers, params)


if __name__ == '__main__':
    endpoint = 'https://aip.baidubce.com'
    ak = API_KEY
    sk = SECRET_KEY
    config = bce_client_configuration.BceClientConfiguration(credentials=bce_credentials.BceCredentials(ak, sk),
                                                             endpoint=endpoint)
    client = ApiCenterClient(config)
    request_id, access_tok = get_request_di()
    print("access_token", access_tok)
    print("request_id", request_id)
    for count in range(1, 20):
        res_ = client.demo(request_id, access_tok)
        print(res_.__dict__['raw_data'])
        print(type(res_))
        res = json.loads(res_.__dict__["raw_data"])
        if res['result']['ret_msg'] == '已完成':
            break  # 云端处理完毕，成功获取表格文件下载地址，跳出循环
        else:
            time.sleep(1)

    dict_json = json.dumps(res_, ensure_ascii=False)
    with open(save_path, 'w', encoding='utf-8') as fp:
        fp.write(dict_json+'\r\n')

3.json文件主要信息（举例信息以字典形式给出）

其他信息详见文字识别OCR (baidu.com)

form_num:表格数量
forms:表格内容信息
        footer:表尾信息
        header:表头数据信息
        body:表格主体部分数据
                rect:(top,left)-->左上角坐标；(width,height)-->单元格宽/高
                column:(初值为1)<只显示合并单元格的首位和末尾>
                row:(初值为1)
                word: