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')
#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)
if len(d):
FileName=''.join(d)
print(FileName)
print("transform...please wait.")
text=pytesseract.image_to_string(Image.open(FileName),lang='chi_sim')
print(text)
file = open(FileName+'.txt','w')
file.write(text)
file.close()
else:
print("no new file....")
time.sleep(2)
OLD = NEW
将文件夹下新增jpeg文件转换成文字保存为txt文件
最新推荐文章于 2024-06-17 15:14:34 发布