增值税发票ocr 识别 方法收集

self.client.FlightInvoiceOCR(req)
https://cloud.tencent.com/document/product/1131/42337
ImageBase64
base64.b64encode

TC3-HMAC-SHA256

作为APIcaller识别发票信息
https://blog.csdn.net/weixin_41552148/article/details/102741282

tencentcloud-sdk-python
主要使用的核心库，集中了最主要的命令

https://cloud.tencent.com/document/sdk/Python

#安装tencentcloud-sdk-python库之后方可调用
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
#导入PIL的Image，打开图片，压缩图片用
from PIL import Image
#获取目录下的文件，以及改名必备
import os
#图片转base64，必备
import base64
#腾讯云返回的信息是json格式，我要转回python的字典，才可以方便的操作
import json
import time

#面向对象思维，创建类
class recognition:
    def __init__(self):
    	#requestId和key是腾讯云开通后申请的，我这里保护下隐私，隐藏起来
        self.requestId = "AKIDiBNIFx8aU7JE8n**************"
        self.key = "VllY9VbR1OUJtDH**************"
        #必备参数
        self.Action = "ap-beijing"
	
	#这个方法是把图片转化为base64的方法，并添加类的属性
    def getBase64(self, name):
        with open(name, "rb") as f:
            self.base64_data = base64.b64encode(f.read()).decode()

	#核心部分，图片解析，根据腾讯云的文档来做即可
    def getInformation(self):
        try:
            cred = credential.Credential(self.requestId, self.key)
            httpProfile = HttpProfile()
            httpProfile.endpoint = "ocr.tencentcloudapi.com"
            clientProfile = ClientProfile()
            clientProfile.httpProfile = httpProfile
            client = ocr_client.OcrClient(cred, "ap-beijing", clientProfile)
            req = models.VatInvoiceOCRRequest()
            dic = {"ImageBase64": self.base64_data}
            params = json.dumps(dic)
            req.from_json_string(params)
            self.resp = client.VatInvoiceOCR(req)

        except TencentCloudSDKException as err:
            print(err)

	#解析返回的数据，这个是根据返回的json来做的，他的格式是一个字典列表，即元素是字典的列表，需要遍历，获得想要的发票数据
    def analysis(self):
        self.data = json.loads(self.resp.to_json_string())
        self.fatherName = self.data['VatInvoiceInfos'][6]['Value']
        for i in self.data['VatInvoiceInfos']:
            if i['Name'] == "小写金额":
                self.value = i['Value']
                self.money = self.value.replace("¥", "")
                break

	#方法调用，这里可以开多线程其实，封装在函数里
    def start(self, name):
        self.getBase64(name)
        self.getInformation()
        self.analysis()
        os.rename(name, self.fatherName + "-" + self.money + ".jpg")
        print(self.data)
        print(self.fatherName)
        print(self.money)
#主函数部分应该不用解释了，很easy的方法。
if __name__ == "__main__":
	nameList = os.listdir()
	nameList.remove("main.py")
	for name in nameList:
	    sImg = Image.open(name)
	    w, h = sImg.size
	    dImg = sImg.resize((int(w/2), int(h/2)), Image.ANTIALIAS)
	    dImg.save(name)
	    try:
	        re = recognition()
	        re.start(name)
	    except AttributeError:
	        print(name + "错误")

ImageBase64
client.VatInvoiceOCR
高拍仪

[TencentCloudSDKException] code:AuthFailure.SignatureFailure message:由于请求包大小超过限制，请求签名验证失败，请使用新的签名方法 TC3-HMAC-SHA256
try :
aaa
except Exception as e:
print (e)
增值税发票

增值税发票识别
client.VatInvoiceOCR(req)
机票行程单识别
self.client.FlightInvoiceOCR
{“ImageBase64”: