跟新显示文件并将文件转换成文字保存txt文件

# -*- coding: utf-8 -*-   
      
import os  
import time

from PIL import Image
import pytesseract

OLD=[]  
NEW=[]
    
def file_name(file_dir):   
    L=[]   
    for root, dirs, files in os.walk(file_dir):  
        for file in files:  
            if os.path.splitext(file)[1] == '.jpeg':  
                L.append(os.path.join(root, file))  
    return L  

fileName=file_name('C:\\Users\\Administrator\\ftp')
print(fileName)


#a.sort()排序
NEW.sort()

while True:
    NEW=file_name('C:\\Users\\Administrator\\ftp')
    c = [x for x in NEW if x in OLD]
    d = [y for y in (NEW+OLD) if y not in c]
    print(d)
    for i in range(d.__len__()):
        print(d[i])
        text=pytesseract.image_to_string(Image.open(d[i]),lang='chi_sim')
        print(text)
        file=open(d[i]+'.txt','w') 
        file.write(text); 
        file.close()
                
    time.sleep(2)
    OLD = NEW    

猜你喜欢

转载自blog.csdn.net/weixin_33595571/article/details/84959939