疫情期间闲着无聊,每天都要填写问卷星来报告健康情况,于是就拿python爬虫写了一个问卷星自动填写系统,一起来看看吧_

import requests
import re
import time
import random
class WenJuanXing:
def __init__(self, url,name,num,phone,address,map):
""" :param url:要填写的问卷的url """
self.wj_url = url
self.post_url = None
self.header = None
self.cookie = None
self.data = None
self.name = name
self.num = num
self.phone = phone
self.address = address
self.map = map
def get_Tem(self, a):
T = random.uniform(36.0, 37.0)
T = str(format(T, '.1f'))
if a:
T = '父亲' + T
return T
else:
return T
def set_data(self):
""" 这个函数中生成问卷的结果,可根据问卷结果,随机生成答案 :return: """
temp = '1$'
a = str(time.strftime('%Y-%m-%d', time.localtime(time.time())))
temp = temp + a + '}2$' + self.name + '}3$' + self.num + '}4$5}5$' + self.phone + '}6$'+self.address+'}7$'
temp = temp + self.map + '}8$' + self.get_Tem(False) + '}9$2}10$}11$'
temp = temp + self.get_Tem(True) + '}12$2'
self.data = { 
'submitdata': temp
}
def set_header(self):
""" 随机生成ip,设置X-Forwarded-For ip需要控制ip段,不然生成的大部分是国外的 :return: """
ip = '{}.{}.{}.{}'.format(112, random.randint(64, 68), random.randint(0, 255), random.randint(0, 255))
self.header = { 
'X-Forwarded-For': ip,
'Origin': 'https: // www.wjx.cn',
'Host': 'www.wjx.cn',
'Referer': self.wj_url,
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko\
) Chrome/71.0.3578.98 Safari/537.36'
}
def get_ktimes(self):
""" 随机生成一个ktimes,ktimes是构造post_url需要的参数,为一个整数 :return: """
return random.randint(15, 50)
def get_response(self):
""" 访问问卷网页,获取网页代码 :return: get请求返回的response """
response = requests.get(url=self.wj_url, headers=self.header)
self.cookie = response.cookies
return response
def get_jqnonce(self, response):
""" 通过正则表达式找出jqnonce,jqnonce是构造post_url需要的参数 :param response: 访问问卷网页,返回的reaponse :return: 找到的jqnonce """
jqnonce = re.search(r'.{8}-.{4}-.{4}-.{4}-.{12}', response.text)
return jqnonce.group()
def get_rn(self, response):
""" 通过正则表达式找出rn,rn是构造post_url需要的参数 :param response: 访问问卷网页,返回的reaponse :return: 找到的rn """
rn = re.search(r'\d{9,10}\.\d{8}', response.text)
return rn.group()
def get_id(self, response):
""" 通过正则表达式找出问卷id,问卷是构造post_url需要的参数 :param response: 访问问卷网页,返回的reaponse :return: 找到的问卷id """
id = re.search(r'\d{8}', response.text)
return id.group()
def get_jqsign(self, ktimes, jqnonce):
""" 通过ktimes和jqnonce计算jqsign,jqsign是构造post_url需要的参数 :param ktimes: ktimes :param jqnonce: jqnonce :return: 生成的jqsign """
result = []
b = ktimes % 10
if b == 0:
b = 1
for char in list(jqnonce):
f = ord(char) ^ b
result.append(chr(f))
return ''.join(result)
def get_start_time(self, response):
""" 通过正则表达式找出问卷starttime,问卷是构造post_url需要的参数 :param response: 访问问卷网页,返回的reaponse :return: 找到的starttime """
start_time = re.search(r'\d+?/\d+?/\d+?\s\d+?:\d{2}', response.text)
return start_time.group()
def set_post_url(self):
""" 生成post_url :return: """
self.set_header()  # 设置请求头,更换ip
response = self.get_response()  # 访问问卷网页,获取response
ktimes = self.get_ktimes()  # 获取ktimes
jqnonce = self.get_jqnonce(response)  # 获取jqnonce
rn = self.get_rn(response)  # 获取rn
id = self.get_id(response)  # 获取问卷id
jqsign = self.get_jqsign(ktimes, jqnonce)  # 生成jqsign
start_time = self.get_start_time(response)  # 获取starttime
time_stamp = '{}{}'.format(int(time.time()), random.randint(100, 200))  # 生成一个时间戳,最后三位为随机数
url = 'https://www.wjx.cn/joinnew/processjq.ashx?curID={}&t={}&starttim' \
'e={}&source=directphone&submittype=1&ktimes={}&hlv=1&rn={}&jpm=13&jqnonce={}&j'\
'qsign={}'.format(id, time_stamp, start_time, ktimes, rn, jqnonce, jqsign)
self.post_url = url  # 设置url
print(self.post_url)
def post_data(self):
""" 发送数据给服务器 :return: 服务器返回的结果 """
self.set_data()
response = requests.post(url=self.post_url, data=self.data, headers=self.header, cookies=self.cookie)
return response
def run(self):
""" 填写一次问卷 :return: """
self.set_post_url()
result = self.post_data()
print(result.content.decode())
def mul_run(self, n):
""" 填写多次问卷 :return: """
for i in range(n):
time.sleep(1)
self.run()
if __name__ == '__main__':
''' 注意: 1.后面两个地址注意格式 2.第二个地址后面参数为该地区经纬度,需要获取请到百度地图开发平台->解决方案->坐标拾取器中获取 '''
w = WenJuanXing('问卷星网址','姓名','学号','手机号','地址比如(河北-张家口市-怀来县)','地址精度比如(河北省\
张家口市怀来县土木镇太平堡村[115.575849, 40.384272])')
w.mul_run(3)

本文地址:https://blog.csdn.net/IP_yihui/article/details/110226868