百度文字识别API调用

官网获取api和secret key

百度AI智能平台通用文字识别：https://ai.baidu.com/tech/ocr/general
创建应用即可，可选择适合的文字识别类型，如标准版、精确版等等，使用文档会有详细说明和调用方法。

调用API接口

分享源代码（标准版，一天可免费调用50000次）：

# -*- coding: utf-8 -*-

# !/usr/bin/env python

import os
import json
import requests
import base64
import urllib
import urllib.parse
import urllib.request

# client_id 为官网获取的AK， client_secret 为官网获取的SK
client_id = '***'
client_secret = '***'

# 获取token

def get_token():
    host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=' + client_id + '&client_secret=' + client_secret
    request = urllib.request.Request(host)
    request.add_header('Content-Type', 'application/json; charset=UTF-8')
    response = urllib.request.urlopen(request)
    token_content = response.read()
    if token_content:
        token_info = json.loads(token_content.decode("utf-8"))
        token_key = token_info['access_token']
    return token_key

# 读取图片

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

# 获取图片信息

def get_content(path):
    request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic"
    # 二进制方式打开图片文件
    f = open(path, 'rb')
    img = base64.b64encode(f.read())
    params = {"image": img}
    access_token = get_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:
        return response.json()

rootdir=r'D:\book' #遍历该目录下的所有图片
list = os.listdir(rootdir)
words=[]
for i in range(0,len(list)):
    path = os.path.join(rootdir, list[i])
    if os.path.isfile(path):
        content=get_content(path)
        if content:
            words_result = content['words_result']
            for w in words_result:
                word = "".join(map(str, w['words'])).strip()
                words.append(word)
    print(path)
output = "".join(map(str, words)).strip() #将识别内容合成一个字符串
f=open('output.txt','w',encoding='utf8')
f.write(output)