python 爬虫 pytesseract 验证码识别：识别拉勾网验证码

pytesseract

安装pip install pytesseract

如果下载之后没有PIL图片读取的库，需要下载 pip install PIL 或者pip install Pillow

代码

from urllib import request
from time import sleep

import pytesseract
from PIL import Image


def main():
    pytesseract.pytesseract.tesseract_cmd = r'D:\Tesseract-OCR\tesseract.exe'
    url = 'https://passport.lagou.com/vcode/create?from=register&refresh=4'
    while True:
        request.urlretrieve(url, 'y.jpg')
        image = Image.open('y.jpg')
        text = pytesseract.image_to_string(image)
        print(text)
        sleep(3)


if __name__ == '__main__':
    main()