本文转自我的csdn原文地址
本文地址
九月份的时候，小编写了一篇关于利用爬虫模拟登陆我们学校教务处抓取课表的帖子（其实姐姐的中心目的是抢课，但由于是非选课阶段，接口不予开放），反响不错。就有考研的学长提议做一个图书馆抢座，其实无论是图书馆抢座还是教务处抢课，他们的原理都是一样，在这里，小编就不赘述了。

思路解析

大致的流程几乎与上一篇帖子是一样的，所以小编只讲下他们的不同。不同之处就在于，这次的抢座是提交两个表单，注意的是为防止网页重定向，我们依然需要保存cookies。登陆部分的内容，小编就不多介绍了，大家可以参考下这篇帖子。登陆成功后的页面如下：

login.PNG

form.PNG

捕获2.PNG

import requests
import http.cookiejar
from bs4 import BeautifulSoup
import pytesseract 
import time

cookies = {} #构建一个空字典用来存放cookies

     
        
headers={
    
        'Connection': 'Keep-Alive',
        'Accept-Language': 'zh-CN,zh;q=0.8',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0',
        'Accept-Encoding': 'gzip, deflate, sdch',
        'Upgrade-Insecure-Requests':'1',
        'Referer': 'http://172.16.47.84/',
        'X-Requested-With': 'XMLHttpRequest',
        'Host': '172.16.47.84',
      }




def login(username, password, code):
    url = 'http://172.16.47.84/'
    form = {
        '__VIEWSTATE': '/wEPDwUKMTM4MDI3NzI1MGRkScbX95yvCTaTc5BiKFlgoJSN0gi9TvPi4as2Sed98Ug=',
        '__EVENTVALIDATION': '/wEWBQLYjc7zAwLs0bLrBgLs0fbZDALs0Yq1BQKM54rGBuOROfeko3/nasulQt/v8ihgd8TDoZ4pgdA4rtbVvanV',
        'TextBox1': username,
        'TextBox2': password,
        'TextBox3': code,
        'Button1': '登录',
       
       
    }      
    resp = requests.post(url, headers=headers, data=form, cookies=cookies)

对了，这个网站也有验证码，而且还极为复杂，表示给用户带来了很不好的体验，用pytesseract识别的时候，成功率几乎为0.在下感觉这个开发者脑子里有坑，作为一个人类的我，倾斜过后的0和o，还有g和数字9 都不分清楚，更不要讲机器了。下面是验证码的处理：

def get_code():
    url = 'http://172.16.47.84/VerifyCode.aspx?'
    resp = requests.get(url, headers=headers)
    cookies['ASP.NET_SessionId'] = resp.cookies.get('ASP.NET_SessionId')
    with open('code.jpg', 'wb') as img:
        img.write(resp.content)
        
def check_show():
     checkcode = Image.open("code.jpg")
     image = Image.open('code.jpg')  
     imgry = image.convert('L')
     imgry.show()

成功登陆后就是选座了：

def cchose_seat():
    try:
        churl = "http://172.16.47.84/DayNavigation.aspx"
        churl_1 = "http://172.16.47.84/AppSTod.aspx?roomid=3207&hei=834&wd=1920"
        responce = requests.get(url)
        form_1 = {
            
                '__VIEWSTATE':'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',
                '__EVENTVALIDATION':"/wEWEwL72v/5BALs0bLrBgLs0fbZDAKPwd2MAQLpu8rPDwKt6srPDwLytq6nDwK6p5TSCwKVpujRCwKVpuzQCwKVpvCRCAKetsSdCgL0p+TRCAL0p5TSCwL0p8CRDwL9h9mtDgKM54rGBgK7q7GGCALWlM+bAudkkeCZYjIbgxcot/UJfplpDini+B9RpiIThosUANI+",
                'TextBox1':"883",
                'TextBox2':"1920",
                "ddlDay":"明日",
                'ddlRoom':"3207001",
                "txtSeats":"",
                "Button1":"手动选座",
               
                }
       

        resp_1 = requests.post(churl, headers=headers, data=form_1, cookies=cookies)                
    except:
        print("####---------登陆失败--------#######")
        ###提交预约座位
        def chseat():
    churl = "http://172.16.47.84/AppSTod.aspx?roomid=3207&hei=834&wd=1920"
    churl_1= "http://172.16.47.84/Skip.aspx?seatid=3207128"
    
    from_2 = {
                
                'roomid' :'3207',
                'hei' :'883',
                'wd' :'1920',
                }
    from_3 = {
                'seatid':'3207128',
                }
    for i in range(0,2):
        resp_2 = requests.post(churl,headers = headers,data = from_2,cookies = cookies)
        resp_3 = requests.post(churl_1,headers = headers,data = from_3,cookies = cookies)
        soup = BeautifulSoup(resp_3.content,'lxml')
        Soup = soup.find_all("script")
    if Soup:
        print(Soup[0])
    else:
        print("正在抢座")
        for i in range(0,50):
            time.sleep(1)  #为防止服务器瘫痪，请求50次，这个大家可以根据需要，自行改动
            resp_2 = requests.post(churl,headers = headers,data = from_2,cookies = cookies)
            resp_3 = requests.post(churl_1,headers = headers,data = from_3,cookies = cookies)

检测是否成功抢座，是根据预约成功后弹出一个页面，告诉“你已经成功预约”， 而这句话是存在于<script>标签下的，用beautifulsoup的find函数查找即可。为了方便，所以小编就稍稍暴力了一点，直接请求两次。
给大家看下结果：

运行结果.PNG

验证结果.PNG