使用python实现问卷星自动抢答

以前帮朋友做的抢答脚本，虽然最后没有软用(因为最后抢的时候页面压根打不开)，不过在这里分享一下代码以及思路。

首先，说说设计吧，脚本使用的是selenium+python2，因为在抢答之前我连问卷有啥字段都不知道。所以只能建立一个可能的回答，到时候把可能能自动补入的字段填进去。所以脚本是半自动的，当然，如果问卷是固定字段的就可以全自动了。

            
              config_dict = {
'sfz':'33011111111111111', # 太長了
'csrq':u'1993-1-1',
'sjhm':'123456789',
'xm':u'张三',
'qt':'',
'xb':2,
'zz':u'杭州'
}

    for n in range(1,len(question_titles)+1,1):
        question_title = question_titles[n-1]
        print question_title
        if '身份证' in question_title:
            question[n] = 'sfz'
        elif '手机' in  question_title or '联系' in question_title or '电话' in question_title:
            question[n] = 'sjhm'
        elif '姓名' in  question_title:
            question[n] = 'xm'
        elif '性别' in question_title:
            question[n] = 'xb'
        elif '生日' in  question_title or  '出生' in  question_title:
            question[n] = 'csrq'
        elif '地址' in  question_title or '住址' in  question_title:
            question[n] = 'zz'
        else:
            question[n] = 'qt'

            
          

这里碰到一个问题，就是日期插件的自动选择 移除上面的readonly属性即可把选择形式的日期控件改成直接填值。

            
                                  if 'csrq'==qname:
                        cop.exec_js("var setDate=document.getElementById(\"q%s\");setDate.removeAttribute('readonly');"%n);

            
          

还有一个选择性别的单选框插件，这里我默认选择第二个。

            
               elif 'xb' == qname:
                        button = cop.find_elements_by_xpath("//div[@for='q%s_2']"%n)[0]
                        Action = TouchActions(cop.driver)
                        Action.tap(button)
                        Action.perform()

            
          

最后，控制脚本到点才开始刷新页面

            
                  while True:
        time.sleep(1)
        if (datetime.datetime.now().hour>=13 and datetime.datetime.now().minute>=59) or (datetime.datetime.now().hour>=14): # 18点59开抢
            break

            
          

最终效果：在时间点之前运行代码，然后脚本会一秒刷新一次页面，然后能抢了之后会马上自动填写吻合预先设置的字段，然后点击提交。

完整代码

            
              # -*- coding: utf-8 -*-
"""
File Name：     wenjuanxin
Description :
Author :       meng_zhihao
date：          2018/9/4
淘宝店地址 :https://shop560916306.taobao.com/?spm=2013.1.1000126.2.3418ab83wv5Ai2
"""
import requests
from lxml import etree
import json
import urllib
import time
import random
import datetime
import csv
import os
from selenium import webdriver
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.action_chains import  ActionChains
from selenium.webdriver.common.touch_actions import TouchActions
import sys
reload(sys)
sys.setdefaultencoding('utf8')

import ConfigParser
import re
import datetime
import pdb
class Actions(ActionChains):
    def wait(self, time_s):
        self._actions.append(lambda: time.sleep(time_s))
        return self

class ChromeOperate():
    def __init__(self,url='',executable_path='',User_data_dir='',arguments=[],headless=True,mod='pc'):
        option = webdriver.ChromeOptions()
        if User_data_dir:
            option.add_argument( '--user-data-dir=%s'%User_data_dir)  # 设置成用户自己的数据目录
        else:
            import getpass
            username = getpass.getuser()
            default_path = 'C:\Users\%s\AppData\Local\Google\Chrome\User Data'%username  #echo %LOCALAPPDATA%\Google\Chrome\User Data
            if os.path.exists(default_path):
                #option.add_argument('--user-data-dir=%s' % default_path)
                pass
        if mod=='wx':
            mobile_emulation = {'deviceName': 'iPhone 6'}
            option.add_experimental_option("mobileEmulation", mobile_emulation)
        option.add_argument('--start-maximized')
        if headless:option.add_argument('headless')
        option.add_argument('google-base-url=%s' % 'https://www.baidu.com/')
        for argument in arguments:
            option.add_argument(argument)
        if not executable_path:executable_path=r'C:\Users\Administrator\Desktop\chromedriver.exe'
        self.driver = webdriver.Chrome(executable_path=executable_path,chrome_options=option)

        if url:self.open(url)


    def open(self,url):
        self.driver.get(url) #   self.driver.get(url).page_source

    def open_source(self):
        return self.driver.page_source

    def title(self):
        self.title=self.driver.title
        return self.title

    def quit(self):
        self.driver.quit()

    def find_element_by_name(self,name):
        return self.driver.find_element_by_name(name)

    def find_elements_by_xpath(self,xpath): #貌似不能用/text
        return self.driver.find_elements_by_xpath(xpath)

    def find_element_by_id(self,id):
        try:
            return self.driver.find_element_by_id(id)
        except:
            return None

    def input_words(self,element,words):
        element.clear()
        element.send_keys(str(words))

    def click_by_id(self,id):
        self.driver.find_element_by_id(id).click()

    def send_file(self,element,path):
        element.sendKeys(path);

    def wait_element(self,element_id):
        WebDriverWait(self.driver, 10).until(
            EC.presence_of_element_located((By.ID, element_id))
        )

    def get_title(self):
        print(self.driver.title)
        return self.driver.title

    def refresh(self):
        self.driver.refresh()  #

    def exec_js(self,js_script):
        self.driver.execute_script(js_script)




cop = ChromeOperate(executable_path=r'chromedriver.exe',headless=False,mod='wx')


config_dict = {
'sfz':'33011111111111111', # 太長了
'csrq':u'1993-1-1',
'sjhm':'123456789',
'xm':u'张三',
'qt':'',
'xb':2,
'zz':u'杭州'
}
question = {


}


def getXpath(xpath, content, charset='utf8', xml_type='HTML'):  # xpath操作貌似会把中文变成转码&#xxxx;  /text()变unicode编码
    tree = etree.HTML(content)
    out = []
    results = tree.xpath(xpath)
    for result in results:
        if 'ElementStringResult' in str(type(result)) or 'ElementUnicodeResult' in str(type(result)):
            out.append(result)
        else:
            out.append(etree.tostring(result, encoding=charset, method=xml_type))  # 加编码就不会变成html编码了
    return out


def get_questions(page_buf):
    # 解析 q1-q6 都是什么东西
    # pdb.set_trace()
    question_titles = getXpath('//div[@class="field-label"]',page_buf)

    for n in range(1,len(question_titles)+1,1):
        question_title = question_titles[n-1]
        print question_title
        if '身份证' in question_title:
            question[n] = 'sfz'
        elif '手机' in  question_title or '联系' in question_title or '电话' in question_title:
            question[n] = 'sjhm'
        elif '姓名' in  question_title:
            question[n] = 'xm'
        elif '性别' in question_title:
            question[n] = 'xb'
        elif '生日' in  question_title or  '出生' in  question_title:
            question[n] = 'csrq'
        elif '地址' in  question_title or '住址' in  question_title:
            question[n] = 'zz'
        else:
            question[n] = 'qt'


if __name__=='__main__':
    timestamp=datetime.datetime.now().strftime("%Y%m%d%H%M%S")
    print timestamp
    #max_num = int(mainconf.get('conf', 'max_num'))
    while True:
        time.sleep(1)
        if (datetime.datetime.now().hour>=13 and datetime.datetime.now().minute>=59) or (datetime.datetime.now().hour>=14): # 18点59开抢
            break
    while True:
        cop.open('https://www.wjx.top/m/34952592.aspx')
        try:
            source = cop.open_source()
            if '到时再重新打开' in source:
                time.sleep(1)
                continue # 检测是否可以填写
            get_questions(source)
            qn = len(question.keys())+1
            for n in range(1,qn,1):
                try:
                    qname = question[n]
                    print qname
                    if 'csrq'==qname:
                        cop.exec_js("var setDate=document.getElementById(\"q%s\");setDate.removeAttribute('readonly');"%n);
                    qvalue = config_dict.get(qname,'')
                    data_ele = cop.find_element_by_id('q%s'%n)
                    if data_ele:
                        data_ele.send_keys(qvalue)
                    elif 'xb' == qname:
                        button = cop.find_elements_by_xpath("//div[@for='q%s_2']"%n)[0]
                        Action = TouchActions(cop.driver)
                        Action.tap(button)
                        Action.perform()
                except Exception as e:
                    print str(e)
            #pdb.set_trace()
            # cop.click_by_id('ctlNext')  # 为啥
            time.sleep(0.5)
            button = cop.find_element_by_id('ctlNext')
            Action = TouchActions(cop.driver)
            Action.tap(button)
            Action.perform()
            break
        except Exception as e:
            print str(e)
            time.sleep(100)
        time.sleep(6000) # 全流程重试间隔


# 据说不频繁是不会出验证码的！
# 填不出来的用不详？
# 选项不够的情况下不要继续点击 ，暂停掉
# 系统时间核对

# 半自动思路 手动复制字段就可以在粘贴板里生成对应信息