百度文字识别OCR识别图片文字内容

AI接入

参考官方文档：AI接入指南

参考：网络图片文字识别申请

参考：鉴权认证机制，用于获取access token

网络文字识别示例代码

下面是官方给的示例代码，从代码中我们可以看出，只要获取到access_token就可以进行API调用，进行本地图片的识别了。

# encoding:utf-8

import requests
import base64


request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/webimage"
# 二进制方式打开图片文件
f = open('[本地文件]', 'rb')
img = base64.b64encode(f.read())

params = {"image":img}
access_token = '[调用鉴权接口获取的token]'
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:
    print (response.json())

调用API

• 准备测试图片
  
• 完整代码

# coding=utf-8

import requests
import base64


class ImageDistinguish:
    def __init__(self):
        # 获取access_token的url，client_id是应用的API Key，client_secret是应用的Secret Key
        self.url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=XXXXXXXXXX&client_secret=XXXXXXXXXX"

    def get_ak(self):
        res = requests.get(self.url)
        return res.json().get('access_token')

    def distinguish(self):
        request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/webimage"
        # 二进制方式打开图片文件
        with open('test.jpg', 'rb') as f:
            img = base64.b64encode(f.read())
        params = {"image": img}
        access_token = self.get_ak()
        request_url = request_url + "?access_token=" + access_token
        headers = {'content-type': 'application/x-www-form-urlencoded'}
        try:
            response = requests.post(request_url, data=params, headers=headers)
            # 返回识别结果，并提取对应识别的内容
            return response.json().get("words_result")[0].get('words')
        except Exception as e:
            print(e)


if __name__ == '__main__':
    img = ImageDistinguish()
    result = img.distinguish()
    print(result)

• 结果

C:\Python36\python.exe C:/Users/Administrator/PycharmProjects/T/webIMAGE.py
致富十年功