教你用python爬虫监控教务系统，查成绩快人一步！

import datetime
import time
from email.header import Header
import requests
import re
import smtplib
from email.mime.text import MIMEText
from bs4 import BeautifulSoup

def listener():
    #在这里我通过模拟登陆的方式登陆
    #一般来说这里填写的是username跟password
    #但我们学校后台将用户名和密码进行了加密
    #通过观察浏览器的请求数据跟页面源码猜出学校后台的加密方式
    data={
        #出于学校安全考虑，这里就不给出加密方式了
        ‘encoded‘:‘xxxxxxxxxxxxxxxxxxx‘
    }
    session = requests.Session()
    session.post(‘http://jwc.sgu.edu.cn/jsxsd/xk/LoginToXk‘,data=data)
    #请求2019-2020-1学期的所有成绩
    r_data = {
        ‘kksj‘: ‘2019-2020-1‘,
        ‘kcxz‘: ‘‘,
        ‘kcmc‘: ‘‘,
        ‘xsfs‘: ‘all‘
    }
    r = session.post(‘http://jwc.sgu.edu.cn/jsxsd/kscj/cjcx_list‘, data=r_data)
    #对爬回来数据进行封装
    soup = BeautifulSoup(r.text, ‘html.parser‘)
    #返回已有的成绩列表
    oldList = toList(soup)
    max = len(oldList)
    #这里用死循环定时爬取成绩页面分析是否分布新成绩
    while (True):
        #post跟get方式不能乱用，不然数据会出错
        r = session.post(‘http://jwc.sgu.edu.cn/jsxsd/kscj/cjcx_list‘,data=r_data)
        soup = BeautifulSoup(r.text, ‘lxml‘)
        #print(soup.prettify())
        length = len(soup.find_all(string=re.compile(‘2019-2020-1‘)))-1
        print("course_length: ",length)
        if (r.status_code == 200 and length != 0):
            if (length > max):
                #查询新出的成绩列表
                newlist = toList(soup)
                #获取两个列表不同之处，不同的就是新成绩
                diflist = compareTwoList(oldList, newlist)
                oldList=newlist
                if diflist==‘‘:
                    send("unkowned Error","unkowned Error")
                else:
                    #有新成绩了，发送邮件通知我
                    send(‘you have new course sorce!!‘, diflist)
                max = length
            print(‘last running time was:‘,datetime.datetime.now())
            #定时作用，500s查一次
            time.sleep(500)
        else:
            # 发送邮件断开连接了 print("had disconnected...")
            send("your server is disconnected!!!","your server is disconnected!!!")
            break

def send(title,msg):
    mail_host = ‘smtp.qq.com‘
    # 你的qq邮箱名，没有.com
    mail_user = ‘你的qq邮箱名，没有.com‘
    # 密码(部分邮箱为授权码)
    mail_pass = ‘授权码‘
    # 邮件发送方邮箱地址
    sender = ‘发送方邮箱地址‘
    # 邮件接受方邮箱地址，注意需要[]包裹，这意味着你可以写多个邮件地址群发
    receivers = [‘yoletpig@qq.com‘]

    # 设置email信息
    # 邮件内容设置
    message = MIMEText(msg, ‘plain‘, ‘utf-8‘)
    # 邮件主题
    message[‘Subject‘] = Header(title,‘utf-8‘)
    # 发送方信息
    message[‘From‘] = sender
    # 接受方信息
    message[‘To‘] = receivers[0]

    # 登录并发送邮件
    try:
        # smtpObj = smtplib.SMTP()
        # # 连接到服务器
        # smtpObj.connect(mail_host, 25)
        smtpObj = smtplib.SMTP_SSL(mail_host)
        # 登录到服务器
        smtpObj.login(mail_user, mail_pass)
        # 发送
        smtpObj.sendmail(
            sender,receivers,message.as_string())
        # 退出
        smtpObj.quit()
        print(‘success‘)
    except smtplib.SMTPException as e:
        print(‘error‘, e)  # 打印错误

def toList(soup):
    flag = True
    list = []
    strs = ‘‘
    #对tr标签下的td进行遍历并取值
    for tr in soup.find_all(‘tr‘):
        if flag:
            flag = False;
            continue
        i = 1
        for td in tr.stripped_strings:
            if (i == 1 or i == 2):
                i += 1
                continue
            strs += "_" + td
            i += 1
        list.append(strs)
        strs = ‘‘
    return list

def compareTwoList(oldList,newList):
    diflist=‘‘
    for sub in newList:
        #判断是否唯一
        if(oldList.count(sub)==0):
            diflist = sub
            break
    return diflist

if __name__ == ‘__main__‘:
    listener()