腾讯ai人工智能OCR文字识别2020.12.18

# -*- coding: utf-8 -*-
"""
Created on Fri Dec 18 15:31:13 2020

@author: Administrator
"""


#以下代码是将【本地图片】进行文字识别
# -*- coding: utf-8 -*-
#pip install tencentcloud-sdk-python
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
from tencentcloud.ocr.v20181119 import ocr_client, models
import base64
import json
import jsonpath
def get_json():
    try:
        cred = credential.Credential("xxxxxx", "xxxxxx") #密钥-输入腾讯上注册的钥匙和密码！！！
        httpProfile = HttpProfile()
        httpProfile.endpoint = "ocr.tencentcloudapi.com"

        clientProfile = ClientProfile()
        clientProfile.httpProfile = httpProfile
        client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)

        req = models.GeneralBasicOCRRequest()
        #对本地图片进行base64转码【本地图片解析需要先转成base64编码】
        with open("c.jpg", 'rb') as f:  #把文件下的图片名写进来
            base64_data = base64.b64encode(f.read())
            s = base64_data.decode()
            ImageBase64_value = 'data:image/jpeg;base64,%s'%s
            #params是字符串，以下进行拼接
            params = '{"ImageBase64":"' + ImageBase64_value + '"}' #以图片Base64编码发送请求
        req.from_json_string(params)

        resp = client.GeneralBasicOCR(req)

        resp = resp.to_json_string()        #<class 'str'>不知道为何，此步无法完成数据提取，于是在下面又写了一个解析的方法

        return resp
    except TencentCloudSDKException as err:
        print(err)

def parse_json(resp):  #解析
    with open('text.txt','w',encoding='utf-8') as f:  #先写入txt中
        f.write(resp)
    with open('text.txt','r',encoding='utf-8') as f:  #然后再读
        str = f.read()
    str = json.loads(str)                              #json.loads：将JSON字符串解码为 Python 对象；json.dumps：将 Python 对象编码成 JSON 字符串
    DetectedText = jsonpath.jsonpath(str, "$..DetectedText")  #解析：通过找到DetectedText获得对应的值
    print(DetectedText)
    print(len(DetectedText))

if __name__ == '__main__':
    resp = get_json()
    parse_json(resp)