赞
踩
最近有一个社会实践需要做问卷调查,突发奇想搞一个自动化脚本,省事省米
selenium是一款网页爬虫重要的工具。
这里需要准备chrome浏览器以及对应的驱动。需要注意的是驱动的版本需要和chrome保持一致。
chrome浏览器版自行查看本机安装版本。
chrome驱动下载链接 chrome驱动链接找到对应版本的驱动。
下载后将安装包解压(解压后为.exe文件)在这个文件夹下
- from selenium import webdriver
- import time
- import random
- from selenium.webdriver.common.by import By
- import pyautogui
- option = webdriver.ChromeOptions()
- option.add_experimental_option('excludeSwitches', ['enable-automation'])
- option.add_experimental_option('useAutomationExtension', False)
-
- browser = webdriver.Chrome(options=option)
-
- browser.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument',
- {'source': 'Object.defineProperty(navigator, "webdriver", {get: () => undefined})'})
- browser.maximize_window() # 窗口最大化
- # 这行代码的作用是将webdriver这个属性置为undefined
- browser.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument',
- {'source': 'Object.defineProperty(navigator, "webdriver", {get: () => undefined})'
- })
-
- browser.get(url)
- time.sleep(2)
- # -*- coding: utf-8 -*-
- # @Time : 2023/1/26 11:34
- # @Author : wkk
- # @File : Python自动化填问卷星.py
- from selenium import webdriver
- import time
- import random
- from selenium.webdriver.common.by import By
- import pyautogui
-
-
- def run(num, url):
- for i in range(num):
- option = webdriver.ChromeOptions()
- option.add_experimental_option('excludeSwitches', ['enable-automation'])
- option.add_experimental_option('useAutomationExtension', False)
-
- browser = webdriver.Chrome(options=option)
-
- browser.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument',
- {'source': 'Object.defineProperty(navigator, "webdriver", {get: () => undefined})'})
- browser.maximize_window() # 窗口最大化
- # 这行代码的作用是将webdriver这个属性置为undefined
- browser.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument',
- {'source': 'Object.defineProperty(navigator, "webdriver", {get: () => undefined})'
- })
-
- browser.get(url)
- time.sleep(2)
- num1 = random.randint(1, 2)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q1_{num1}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q1_{num1}']").click()
- time.sleep(0.5)
- num2 = random.randint(1, 3)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q2_{num2}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q2_{num2}']").click()
- time.sleep(0.5)
- num3 = random.randint(1, 3)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q3_{num3}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q3_{num3}']").click()
- time.sleep(0.5)
- num4 = random.randint(1, 3)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q4_{num4}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q4_{num4}']").click()
- time.sleep(0.5)
- num5 = random.randint(1, 2)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q5_{num5}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q5_{num5}']").click()
- time.sleep(0.5)
- num6 = random.randint(1, 3)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q6_{num6}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q6_{num6}']").click()
- time.sleep(0.5)
- num7 = random.randint(1, 4)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q7_{num7}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q7_{num7}']").click()
- time.sleep(0.5)
- # num8 = random.randint(1, 3)
- # if browser.find_element(by=By.XPATH, value=f"//div[@for='q8_{num8}']"):
- # browser.find_element(by=By.XPATH, value=f"//div[@for='q8_{num8}']").click()
- # time.sleep(0.5)
- # 问题5
- randomId = random.randint(1, 3) # 随机数选择(选多少个)
-
- for i in range(1, randomId + 1): # 循环 实现多选效果
- randomId1 = random.randint(1, 3) # 随机选择第1到第6个选项之一
-
- # 两种js实现方式
- js = "document.getElementById(\"q8_" + str(randomId1) + "\").checked = true"
- browser.execute_script(js)
- # 延时
- time.sleep(1)
- num9 = random.randint(1, 7)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q9_{num9}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q9_{num9}']").click()
- time.sleep(0.5)
- num10 = random.randint(1, 3)
- if browser.find_element(by=By.XPATH, value=f"//div[@for='q10_{num10}']"):
- browser.find_element(by=By.XPATH, value=f"//div[@for='q10_{num10}']").click()
- time.sleep(0.5)
- if browser.find_element(by=By.XPATH, value="//div[@class='submitbtn mainBgColor']"):
- browser.find_element(by=By.XPATH, value="//div[@class='submitbtn mainBgColor']").click()
-
- time.sleep(1)
- try:
- element = browser.find_element(By.CSS_SELECTOR, "#alert_box > div:nth-child(2) > div:nth-child(2) > button")
- element.click()
- time.sleep(1)
- yanz = browser.find_element(By.ID, "rectMask")
- yanz.click()
- time.sleep(4)
- except:
- pass
- # 先点确认
- try:
- browser.find_element(By.XPATH, '//*[@id="layui-layer1"]/div[3]/a[1]').click()
- time.sleep(1)
- except:
- pass
- # 再点智能验证提示框,进行智能验证
- try:
- browser.find_element(By.XPATH, '//*[@id="SM_BTN_WRAPPER_1"]').click()
- time.sleep(3)
- except:
- pass
- # 滑块验证
-
- pyautogui.moveTo(789, 805, duration=1) # 传入屏幕的位置
- time.sleep(0.5)
- pyautogui.dragRel(370, 0, duration=0.8) # 拖动
-
- # pyautogui.moveTo(789, 805, duration=1) # 回到原处
- # pyautogui.moveRel(370, 0, duration=1)
-
- # pyautogui.dragRel(256, 0, duration=0.8)
- # pyautogui.moveTo(789, 805)
- # time.sleep(0.5)
- # pyautogui.dragRel(370, 0, duration=0.8)
- time.sleep(5)
- browser.close()
- print(f"第{i + 1}份已经完成")
-
-
-
- if __name__ == '__main__':
- num = 10 # 填的份数
- url = 'https://www.wjx.cn/vm/tXQkrbD.aspx' # 链接
- run(num, url)
-
-
以上代码是我根据我自己的问卷形式来的,具体参数还得跟着问卷走,代码亲测有效,当短时间内刷的问卷数过多时,可能会出现第二重智能验证,这就要手动验证了哦,所以为了防止出现二重智能验证,在每提交完一份问卷后,要用time.sleep函数用于延时 , 避免提交过快。
本文仅为技术交流,最好不要用来恶意填写别人的问卷,以造成问卷质量低下的情况,请大家还是根据自己的实际情况填写问卷哦。
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。