菜鳥用Python 識別批量圖片,再讀取文字(用百度文字識別)
阿新 • • 發佈:2019-01-31
直接上程式碼吧,本人菜鳥剛學的,有問題指教
MyPath = "G:\\python\\xxxxx\\"#這是讀取的圖片存放的資料夾的路徑,可以改為要讀取的資料夾 filesoure = MyPath def baiduduqu(filesoure,filename): from aip import AipOcr import re import os APP_ID = 'xxxx' API_KEY = 'xxxxx' SECRET_KEY = 'xxxx' client = AipOcr(APP_ID, API_KEY, SECRET_KEY) dakai = open(filename,'rb') duqu = dakai.read() message = client.basicGeneral(duqu) for duqu in message.get('words_result'): print(duqu.get('words')) def filename (fielsoure,filetype): import os pathDir = os.listdir(filesoure) for allDir in pathDir: child = os.path.join('%s%s' % (filesoure,allDir)) print(child) baiduduqu(filesoure,child) def run(): import os os.chdir(filesoure) for i in os.listdir(os.getcwd()): postfix = os.path.splitext(i)[1] if postfix == '.jpeg' or postfix == '.png': filename(filesoure,postfix) if __name__ == '__main__': run()
實現以上程式碼需要安裝
AipOcr
如果已安裝pip,執行pip install baidu-aip
即可,參考http://yuyin.baidu.com/docs/tts/196