这篇文章重要为大家详细介绍了如何使用Python实现模仿浏览器启动,获取网页内容、自动填表单、自动登录、自动过验证码等功能,需要的可以参考一下
食用前准备
python 3.10.10 #二维码的库ddddocr 需要
库
- import time
- import ddddocr
复制代码 源码
- # import threading # 导入threading模块# from Feishu_SendMsg import *# Identification verification codeimport time
- import ddddocrinterval = 100 * 60# def delayCall(): # 定义方法# SendMsg("选题 快快快!!!")# timer=threading.Timer(interval,delayCall) # 每秒运行# timer.start() # 执行方法 # if __name__ == '__main__': ## t1=threading.Timer(interval,function=delayCall) # 创建定时器# t1.start() # 开始执行线程from selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.common.keys import Keys# SendMsg("自动填表单")options = webdriver.ChromeOptions()options.add_argument('--enable-automation')options.add_argument('--no-sandbox')options.add_argument('--disable-extensions')options.add_argument('--start-maximized')options.add_argument('--disable-infobars')prefs = {"profile.default_content_setting_values.autocomplete_enabled": 2}options.add_experimental_option("prefs", prefs)# SendMsg("创建 Chrome 浏览器实例")# 创建 Chrome 浏览器实例browser = webdriver.Chrome(options=options)# SendMsg("打开网页")browser.get('www.tttttttt.com')# SendMsg("找到账号和密码框元素并输入指定字符串")username = browser.find_element("name","username")password = browser.find_element("name","userpass")usercode = browser.find_element("name","usercode")img_verifycode = browser.find_element("id","img_verifycode")# SendMsg("自动添补账号密码")username.send_keys("11111")password.send_keys("11111")verifycodeBase64 = img_verifycode.screenshot_as_base64ocr = ddddocr.DdddOcr()res = ocr.classification(verifycodeBase64)usercode.send_keys(res)# SendMsg(f"辨认并填写验证码: {res}")# SendMsg("提交表单")password.send_keys(Keys.RETURN)# SendMsg("登陆: 提交表单")
复制代码 知识点增补
下面为大家介绍一下文中用到的ddddocr库的相关使用吧
辨认验证码的python 库有很多,用起来也并不简朴,ddddocr (带带弟弟ocr)库是一个简朴实用的辨认验证码的库,保举给大家
ddddocr具体使用方法
- import os
- import ddddocr
- from time import sleep
- from PIL import Image
- from selenium import webdriver
- from selenium.webdriver.common.by import By
- class GetVerificationCode:
- def __init__(self):
- self.res = None
- url = '要登录的地址'
- self.driver = webdriver.Chrome()
- self.driver.maximize_window() # 将浏览器最大化
- self.driver.get(url)
- # 获取验证码信息
- def getVerification(self):
- # 获取当前文件的位置、并获取保存截屏的位置
- current_location = os.path.dirname(__file__)
- screenshot_path = os.path.join(current_location, "..", "VerificationCode")
- # 截取当前网页并放到自定义目录下,并命名为printscreen,该截图中有我们需要的验证码
- sleep(1)
- self.driver.save_screenshot(screenshot_path + '//' + 'printscreen.png')
- sleep(1)
- # 定位验证码
- imgelement = self.driver.find_element(By.XPATH, '验证码图片的Xpath定位')
- # 获取验证码x,y轴坐标
- location = imgelement.location
- # 获取验证码的长宽
- size = imgelement.size
- # 写成我们需要截取的位置坐标
- rangle = (int(location['x'] + 430),
- int(location['y'] + 200),
- int(location['x'] + size['width'] + 530),
- int(location['y'] + size['height'] + 250))
- # 打开截图
- i = Image.open(screenshot_path + '//' + 'printscreen.png')
- # 使用Image的crop函数,从截图中再次截取我们需要的区域
- fimg = i.crop(rangle)
- fimg = fimg.convert('RGB')
- # 保存我们截下来的验证码图片,并读取验证码内容
- fimg.save(screenshot_path + '//' + 'code.png')
- ocr = ddddocr.DdddOcr()
- with open(screenshot_path + '//' + 'code.png', 'rb') as f:
- img_bytes = f.read()
- self.res = ocr.classification(img_bytes)
- print('识别出的验证码为:' + self.res)
- # 判断验证码错误时的提示信息是否存在
- def isElementPresent(self, by, value):
- try:
- element = self.driver.find_element(by=by, value=value)
- except NoSuchElementException:
- pass
- # 发生了NoSuchElementException异常,说明页面中未找到该元素,返回False
- return False
- else:
- # 没有发生异常,表示在页面中找到了该元素,返回True
- return True
- # 登录
- def login(self):
- self.getVerification()
- self.driver.find_element(By.XPATH, '用户名输入框Xpath定位').send_keys('用户名')
- self.driver.find_element(By.XPATH, '密码输入框Xpath定位').send_keys('密码')
- self.driver.find_element(By.XPATH, '验证码输入框Xpath定位').send_keys(self.res)
- sleep(1)
- self.driver.find_element(By.XPATH, '登录按钮Xpath定位').click()
- sleep(2)
- isFlag = True
- while isFlag:
- try:
- isPresent = self.isElementPresent(By.XPATH, '验证码错误时的提示信息Xpath定位')
- if isPresent is True:
- codeText = self.driver.find_element(By.XPATH, '验证码错误时的提示信息Xpath定位').text
- if codeText == "验证码不正确":
- self.getVerification()
- sleep(2)
- self.driver.find_element(By.XPATH, '验证码输入框Xpath定位').clear()
- sleep(1)
- self.driver.find_element(By.XPATH, '验证码输入框Xpath定位').send_keys(self.res)
- sleep(1)
- self.driver.find_element(By.XPATH, '登录按钮Xpath定位').click()
- sleep(2)
- tips = self.driver.find_element(By.XPATH,
- '未输入验证码时的提示信息Xpath定位').text
- if tips == "请输入验证码":
- self.getVerification()
- sleep(2)
- self.driver.find_element(By.XPATH, '验证码输入框Xpath定位').click()
- sleep(1)
- self.driver.find_element(By.XPATH, '验证码输入框Xpath定位').send_keys(self.res)
- sleep(1)
- self.driver.find_element(By.XPATH, '登录按钮Xpath定位').click()
- sleep(2)
- continue
- else:
- print("验证码正确,登录成功!")
- except NoSuchElementException:
- pass
- else:
- isFlag = False
-
- sleep(5)
- self.driver.quit()
- if __name__ == '__main__':
- GetVerificationCode().login()
复制代码 辨认结果
到此这篇关于Python实现获取网页内容及自动填表单与登录功能的文章就介绍到这了,希望大家以后多多支持!
最后: 下方这份完整的软件测试视频学习教程已经整理上传完成,朋侪们如果需要可以自行免费领取【包管100%免费】
这些资料,对于【软件测试】的朋侪来说应该是最全面最完整的备战堆栈,这个堆栈也伴随上万个测试工程师们走过最艰难的路程,希望也能资助到你!
免责声明:如果侵犯了您的权益,请联系站长,我们会及时删除侵权内容,谢谢合作!更多信息从访问主页:qidao123.com:ToB企服之家,中国第一个企服评测及商务社交产业平台。 |