用python调用tesseract ocr批量识别图片上的文字

下面的程序可以批量对文件夹下面的图片进行识别，只需要修改相应的文件夹位置即可，有很多文章讲述如何安装tesseract，这里不在赘述如何安装，直接放代码。

from PIL import Image
import pytesseract
import string, re, os
import  codecs

def imgtostr(imgpath):
    '''识别图片中的所有文字'''
    image = Image.open(imgpath,'r')
    text = pytesseract.image_to_string(image, lang='eng+chi_sim')  # 调用字符文件识别
    text = text.replace("\n", " ")  # 去换行
    return text
open('word.txt', 'w').close()
def writefile(image_path, strstr):
    '''将文字累加写入txt文档'''
    with open('word.txt', 'a+', encoding="utf-8") as f:
        f.writelines(strstr)
        f.writelines("\n\n")

if __name__ == '__main__':

    print("\n")
    image_path = './test_images'
    print("\n....start........\n")

    for foldName, subfolders, filenames in os.walk(image_path):
        toltal = 0
        for fe in filenames:
            grpaimg = image_path + '/' + fe
            print(grpaimg)
            textddd = imgtostr(grpaimg)
            writefile(image_path, grpaimg + ":\n" + textddd)
            print(textddd, end="\n\n")

    print("......end........")