파이썬에서 이미지를 텍스트로 변환하는 방법

#进一步优化  1. 底部添加label   2.对识别后的文本处理，去空格


from PIL import Image as PImage
from PIL import ImageTk
import pytesseract
from tkinter import *
from tkinter import filedialog
from tkinter.scrolledtext import ScrolledText
import re

# 将图片内容翻译为文字，显示在文本框内
def trans():
    contents.delete('1.0', END)
    transTxt = pytesseract.image_to_string(PImage.open(filePath.get()),lang='chi_sim')
    #对transTxt进行处理  去空格，换行符去重
    transTxt = transTxt.strip('\n\r')   #无参数可以删除开头结尾的空格\n\t\r
    print(transTxt)
    contents.insert( INSERT, transTxt.replace(' ','').replace('\n\n','\n').replace('\r',''))

#打开图片文件，显示路径，并将图片展现
def openfile():
    filename.delete('1.0', END)
    filePath.set(filedialog.askopenfilename())
    filename.insert(1.0,filePath.get())
    org_img = PImage.open(filePath.get())
    #调整图片显示大小 600*800
    w,h = org_img.size
    if w>600:
        h=int(h*600/w)
        w=600
    if h>800:
        w=int(w*800/h)
        h=800
    img = ImageTk.PhotoImage(org_img.resize((w,h)))
    showPic.config(image=img)
    showPic.image = img       #保持一个引用才能显示图片，tkinter的BUG
    

#设置主窗口
top = Tk()
top.title("OCR图片转文字  引擎：Tesseract-OCR  Made by: kaivis")
#top.iconbitmap("./pic/y1.ico")
top.geometry("1200x800")

filePath=StringVar()

bt_img1 = ImageTk.PhotoImage( file= "./pic/Outbox1.png")
bt_img2 = ImageTk.PhotoImage( file= "./pic/bt_img2.png")

#第一个窗体
frame1 = Frame (top, relief=RAISED, borderwidth=2)
frame1.pack(side=TOP, fill=BOTH,  ipady=5, expand=0)
Label(frame1,height=1,text="图片路径：").pack(side=LEFT)
filename = Text(frame1,height=2)
filename.pack(side=LEFT,padx=1, pady=0,expand=True, fill=X)
Button(frame1,text="打开文件", image=bt_img1, command=openfile).pack(side=LEFT,padx=5, pady=0)
Button(frame1,text="中文识别", image=bt_img2, command=trans).pack(side=LEFT,padx=5, pady=0)

#第二个窗体
frame2 = Frame (top, relief=RAISED, borderwidth=2)
frame2.pack (side=LEFT, fill=BOTH,  expand=1)
Label(frame2,text='图片显示：',borderwidth=5).pack(side=TOP,padx=20,pady=5)
showPic = Label(frame2,text='图片显示区')
showPic.pack(side=BOTTOM,expand=1,fill=BOTH)

#第三个窗体
frame3 = Frame (top)
frame3.pack (side=RIGHT, fill=BOTH,  expand=1)
#contents = ScrolledText(frame3)
Label(frame3,text='识别结果：',borderwidth=5).pack(side=TOP,padx=20,pady=10)
contents = Text(frame3,font=('Arial',15))
contents.pack(side=TOP,expand=1,fill=BOTH)
Label(frame3,text='Copyright 2021 baidu.com ALL Rights Reserved',borderwidth=5).pack(side=BOTTOM,padx=20,pady=10)

top.mainloop()