通过百度api和selenium实现验证码识别

最新推荐文章于 2025-04-01 14:57:22 发布

qq_44368866

最新推荐文章于 2025-04-01 14:57:22 发布

阅读量416

点赞数

文章标签： selenium 测试工具

本文链接：https://blog.csdn.net/qq_44368866/article/details/133684953

版权

import re
from aip import AipOcr
from selenium import webdriver
import time
from PIL import Image
from selenium.webdriver.common.by import By


def orc_test():
    driver = webdriver.Edge()
    driver.maximize_window()
    time.sleep(1)
    url = 'http://188.18.18.227:8091'
    driver.get(url)
    driver.save_screenshot('save_screenshot.png')

    code_ele = driver.find_element(By.ID, 's-canvas')

    right = code_ele.size['width'] + 1400  # 上面右边点的坐标
    down = code_ele.size['height'] + 380  # 下面右边点的坐标
    image = Image.open('save_screenshot.png')
    code_image = image.crop((1360, 380, right, down))
    code_image.save('code_image.png')

    APP_ID = ''
    API_KEY = ''
    SECRET_KEY = ''
    client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

    # 读取图片

    def get_file_content(file_path):
        with open(file_path, 'rb') as fp:
            return fp.read()

    image = get_file_content('code_image.png')

    # 调用通用文字识别（高精度版） """
    code_ocr_original_result = client.basicAccurate(image)
    code_ocr_final_result = ''
    for text in code_ocr_original_result['words_result']:
        # print(type(text))
        # print(text)
        for i in text.values():
            code_ocr_final_result = code_ocr_final_result + i
        # print(code_ocr_final_result)

    code_ocr_final_result_with_out = code_ocr_final_result.replace(' ', '')
    result = re.sub('[\W_]', '', code_ocr_final_result_with_out)
    return result


if __name__ == '__main__':
    print(orc_test())