百度表格识别的使用

申请一个百度开发者账号，新建一个ocr的应用，记录下应用ID和密码ID，分成同步和异步两种，同步的调用需要提申请，异步的可以直接使用，每天可以免费使用50次。
凑合着先用，就是识别率好像没有文字识别那么高。

# encoding:utf-8

import requests
import base64
import time

'''
获取access_token
'''

# 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=[输入你的AK]&client_secret=[输入你的SK]'
response = requests.get(host)
if response:
    res_json = response.json()
    at = res_json['access_token']


'''
表格文字识别(异步接口)
'''


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(r"D:\Python\b4cd4eb05a76fe15828a11d918f3a44.png", 'rb')
img = base64.b64encode(f.read())

params = {"image": img}
access_token = at
request_url = request_url + "?access_token=" + access_token
headers = {'content-type': 'application/x-www-form-urlencoded'}
response = requests.post(request_url, data=params, headers=headers)
if response:
    time.sleep(10)
    res_json2 = response.json()
    print(res_json2['result'])
    request_id = res_json2['result'][0]
    print(request_id)
    url = "https://aip.baidubce.com/rest/2.0/solution/v1/form_ocr/get_request_result" + \
        "?access_token=" + at
    response = requests.post(url, data=request_id, headers=headers)
    if response:
        print(response.json())
        url = response.json()['result']['result_data']
        print(url)
        r = requests.get(url)
        with open("111.xls", "wb") as code:
            code.write(r.content)