1、首先去百度注册一个账户,然后选择对应的识别类型创建对应的应用,获取AppID,APIKey,SecretKey,请参考百度官方接入文档http://ai.baidu.com/docs#/Begin/top
2、官方使用文档http://ai.baidu.com/docs#/OCR-Python-SDK/top

#-*- coding: UTF-8 -*-
#前提是python已安装aip库--》pip install baidu-aip

'''
author:多测师_王sir
'''
import os
from aip import AipOcr
APP_ID = '你注册账号创建应用后得到的APPID'
API_KEY = '你注册账号创建应用后得到的API_KEY'
SECRET_KEY = '你注册账号创建应用后得到的SECRET_KEY '
aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY)
os.chdir("E:\\office\\src_pic") #你需要转换的图片目录
dirs = os.listdir()
def get_file_content(filePath):
with open(filePath, 'rb') as fp:
return fp.read()
options = {}
options["language_type"] = "CHN_ENG"
options["detect_direction"] = "true"
options["detect_language"] = "true"
options["probability"] = "true"


print('开始处理,共'+str(len(dirs))+"张图片。")
flag=0
T = 0 #统计处理图片成功的数量
for filePath in dirs:
if filePath.split('.')[-1]=='txt':continue
flag+=1
print('正在处理第'+str(flag)+'张图片')
try:
result = aipOcr.basicGeneral(get_file_content(filePath), options)
except BaseException as e:
print(e)
else:
try:
with open(filePath.split('.')[0]+'.txt','w',encoding='utf-8') as f:
for i in result['words_result']:
f.write(i['words']+'\n')
T += 1
except BaseException as e :
print(e)
else:
print('处理完成')
print('{}全部处理完成!{}'.format("="*30,"="*30))
print('处理成功的图片有{}张,处理失败的图片有{}张'.format(T,len(dirs)-T))