通過(guò)百度文字識(shí)別的API來(lái)實(shí)現(xiàn)把圖片內(nèi)容寫入到txt文件

1、首先去百度注冊(cè)一個(gè)賬戶，然后選擇對(duì)應(yīng)的識(shí)別類型創(chuàng)建對(duì)應(yīng)的應(yīng)用，獲取AppID,APIKey,SecretKey,請(qǐng)參考百度官方接入文檔http://ai.baidu.com/docs#/Begin/top
2、官方使用文檔http://ai.baidu.com/docs#/OCR-Python-SDK/top

#-*- coding: UTF-8 -*-
#前提是python已安裝aip庫(kù)--》pip install baidu-aip

import os
from aip import AipOcr
import json
APP_ID = '你注冊(cè)賬號(hào)創(chuàng)建應(yīng)用后得到的APPID'
API_KEY = '你注冊(cè)賬號(hào)創(chuàng)建應(yīng)用后得到的API_KEY'
SECRET_KEY = '你注冊(cè)賬號(hào)創(chuàng)建應(yīng)用后得到的SECRET_KEY '
aipOcr = AipOcr(APP_ID, API_KEY, SECRET_KEY)
os.chdir("E:\\office\\src_pic")  #你需要轉(zhuǎn)換的圖片目錄
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('開始處理，共'+str(len(dirs))+"張圖片。")
flag=0
T = 0 #統(tǒng)計(jì)處理圖片成功的數(shù)量
for filePath in dirs:
    if filePath.split('.')[-1]=='txt':continue
    flag+=1
    print('正在處理第'+str(flag)+'張圖片')
    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('處理完成')
print('{}全部處理完成！{}'.format("="*30,"="*30))
print('處理成功的圖片有{}張,處理失敗的圖片有{}張'.format(T,len(dirs)-T))