使用Python自动填写问卷星(pyppeteer反爬虫版)

写此文的目的是为了方便寒假自己忘记填问卷星

一开始的想法和去年一样,去年就写过一版,想着今年不过就是改改数据,换换id而已,另外没想到的事情发生了。。。

满怀信心的写完代码

from selenium import webdriver
import time
import random

def run():
    browser = webdriver.Chrome()
    browser.get("网址")

    # 1
    js = "document.getElementById(\"q1\").click()"
    browser.execute_script(js)
    browser.switch_to.frame("__calendarIframe")
    js2 = "document.getElementById(\"selectTodayButton\").click()"
    browser.execute_script(js2)
    browser.switch_to.parent_frame()


    # 2
    js = "document.getElementById(\"q2\").click()"
    browser.execute_script(js)
    browser.switch_to.frame("__calendarIframe")
    js2 = "document.getElementById(\"selectTodayButton\").click()"
    browser.execute_script(js2)
    browser.switch_to.parent_frame()


    # 3
    js = "document.getElementById(\"q3_1\").click()"
    browser.execute_script(js)

    # 4
    browser.find_element_by_id("q4").send_keys("学号")

    # 5
    browser.find_element_by_id("q5").send_keys("姓名")

    # 6
    js = "document.getElementById(\"q6_1\").click()"
    browser.execute_script(js)

    # 7
    js = "document.getElementById(\"q7_3\").click()"
    browser.execute_script(js)

    # 8
    js = "document.getElementById(\"q8_1\").click()"
    browser.execute_script(js)
    browser.find_element_by_class_name("underline").send_keys("第一次1月9日阴性")

    # 9
    js = "document.getElementById(\"q9_2\").click()"
    browser.execute_script(js)

    # 10
    js = "document.getElementById(\"q10_2\").click()"
    browser.execute_script(js)

    # 11
    js = "document.getElementById(\"q12_2\").click()"
    browser.execute_script(js)

    # 12
    browser.find_element_by_id("q14").send_keys("36."+str(random.randint(0,5))+"/36."+str(random.randint(0,5)))

    #13
    js = "document.getElementById(\"q15_2\").click()"
    browser.execute_script(js)

    #14
    js = "document.getElementById(\"q17_2\").click()"
    browser.execute_script(js)

    #15
    browser.find_element_by_id("q19").click()
    time.sleep(1)
    browser.switch_to.frame("PDF_i_chezchenz")
    browser.find_element_by_id("txtInput").send_keys("地址")
    js3="document.getElementById(\"btnSearch\").click()"
    browser.execute_script(js3)
    time.sleep(1)
    browser.find_element_by_css_selector("a.ensure_btn").click()
    time.sleep(1)
    browser.switch_to.default_content()

    # 16
    js = "document.getElementById(\"q20_2\").click()"
    browser.execute_script(js)

    # 17
    browser.find_element_by_id("q22").send_keys("")


    # 18
    browser.find_element_by_id('select2-q23-container').click()
    # js = "document.getElementById('select2-q23-container').click()"
    # browser.execute_script(js)
    browser.find_element_by_xpath("//li[@class='select2-results__option'][1]").click()
    # js = "document.getElementById(\"select2-q23-result-ei9q-1\").click()"
    # browser.execute_script(js)

    # submit
    js = "document.getElementById(\"submit_button\").click()"
    browser.execute_script(js)


if __name__ == "__main__":
    while True:
        run()
        time.sleep(4)
        break

数据都填上了,可他来了一个这玩意

 

 然后

 

 之后了解到用用pyppeteer解决反爬的方法,安装python第三方库asynciopyppeteerpyppeteer_stealth

完整代码如下:

import asyncio
from pyppeteer import launch
from pyppeteer_stealth import stealth #反爬
import random
import time
async def run():
    driver = await launch({
        # 谷歌浏览器的安装路径
        'executablePath': 'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe',
        # Pyppeteer 默认使用的是无头浏览器
        'headless': False,
        # 设置Windows-size和Viewport大小来实现网页完整显示
        'args': ['--no-sandbox', '--window-size=1024,768']
    })
    page = await driver.newPage()
    await page.setViewport({'width': 1024, 'height': 768})
    # 反爬虫跳入网页
    await stealth(page)
    await page.goto('网址')
    time.sleep(1)
    #1 问卷填报日期
    date=await page.querySelector('#q1')
    await date.click()
    frame =page.frames
    date2= await frame[1].querySelector('#selectTodayButton')
    await date2.click()
    #2 体温测量日期
    date = await page.querySelector('#q2')
    await date.click()
    frame = page.frames
    date2 = await frame[1].querySelector('#selectTodayButton')
    await date2.click()
    #3 班级
    await page.click('#divquestion3 > ul > li > a')
    #4 学号
    await page.type('#q4','学号')
    #5 姓名
    await page.type('#q5','姓名')
    # 6 性别
    await page.click('#divquestion6 > ul:nth-child(2) > li:nth-child(1) > a')
    #7 所在地区
    await page.click('#divquestion7 > ul > li:nth-child(3) > a')
    #8 核酸
    await page.click('#divquestion8 > ul > li:nth-child(1) > a')
    await page.type('#divquestion8 > ul > li:nth-child(1) > input.underline','第一次1月9日阴性')
    #9 隔离情况
    await page.click('#divquestion9 > ul > li:nth-child(2) > a')
    #10 密切接触
    await page.click('#divquestion10 > ul:nth-child(2) > li:nth-child(2) > a')
    #12 病例
    await page.click('#divquestion12 > ul:nth-child(2) > li:nth-child(2) > a')
    #14 体温
    temperature="36."+str(random.randint(2,6))+'/'+"36."+str(random.randint(2,6))
    print(temperature)
    await page.type('#q14',temperature)
    #15 同住人员密切接触
    await page.click('#divquestion15 > ul:nth-child(2) > li:nth-child(2) > a')
    #17 同住人员病例
    await page.click('#divquestion17 > ul:nth-child(2) > li:nth-child(2) > a')
    #19 地理位置
    address= await page.querySelector('#q19')
    await address.click()
    time.sleep(5)
    frame=page.frames
    await frame[2].type('#txtInput','地址')
    time.sleep(1)
    await frame[2].click('#btnSearch')
    time.sleep(1)
    await frame[2].click('.ensure_btn')
    #20 居住地变化
    await page.click('#divquestion20 > ul:nth-child(2) > li:nth-child(2) > a')
    # 22 异常情况
    await page.type('#q22','')
    #23 同住人员
    await page.click('#select2-q23-container')
    persion=await page.xpath("//li[@class='select2-results__option'][1]")
    await persion[0].click()
    time.sleep(2)
    #提交
    await page.click('#submit_button')
if __name__ == '__main__':
    asyncio.get_event_loop().run_until_complete(run())

就提交成功了!!!

Tags: