模拟登陆教务处获取成绩

刚开学时班长发了每个人的身份证号码，被别有用心的boy存到了本地。教务处密码是身份证后六位，然后我就悄悄地（偷偷地）制作了一张均分排名(⊙v⊙)。

过程中学习了模拟登陆以及正则表达式的基本应用。本来是用库urllib的，结果遇到重定向302问题不会提取响应报文，然后就用了第三方库requests（顺便解决了编码问题）. 还加入了第三方库xlrd用来读取本地的excel.

代码如下：

# -*- coding: utf-8 -*-
import re
import xlrd
change_sum = 0 #用以存储密码修改的人数
grade_course = ['*************'] 用以存储计算均分的科目
class course():
    '''the class of course'''
    def __init__(self,L):
        self.name = L[2] #学科名称
        self.credit = L[3]  #学科学分
        self.grade = L[8] #学科分数
        self.rank = L[9] #学科排名
class person():
    '''the class of person'''
    def __init__(self,name,S):
        self.name = name
        self.courses = S
        Grade = 0
        Credit = 0
        for key,value in S.items():
            global grade_course
            if key in grade_course:
                try:
                    t = float(value.grade)
                    Credit += float(value.credit)
                    Grade += t*float(value.credit)
                except:
                    pass
        self.average = Grade/Credit #均分
def save(Path,Data):
    '''save Data in Path'''
    file_obj = open(Path,'a')
    try:
        file_obj.write(Data)
    finally:
        file_obj.close()
def gettext(username,password):
    '''input username & password, return marks text'''
    import requests
    
    def getlt(data):
        '''获取学校教务处hidden的参数lt'''
        cer = re.findall('(?<=name="lt" value=").+?(?=")',data)
        return cer[0]
    def getexecution(data):
        '''获取学校教务处hidden的参数execution'''
        cer = re.findall('(?<=name="execution" value=").+?(?=")', data)
        return cer[0]
    
    header = { #伪装浏览器
        'Connection' : 'Keep-Alive',
        'Accept-Language' : 'zh-CN',
        'Accept' : 'image/jpeg, application/x-ms-application, image/gif, application/xaml+xml, image/pjpeg, application/x-ms-xbap, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, */*',
        'User-Agent' : 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.3; WOW64; Trident/7.0; .NET4.0E; .NET4.0C; .NET CLR 3.5.30729; .NET CLR 2.0.50727; .NET CLR 3.0.30729; InfoPath.2; Tablet PC 2.0; GWX:DOWNLOADED; GWX:RESERVED; GWX:QUALIFIED; SMJB)',
        'Accept-Encoding' : 'gzip, deflate',
        'Host' : '*********',
        'DNT': '1'
    }

    url = '**********' #学校教务处网址
    s = requests.session() #保存cookies
    r = s.get(url,headers=header)

    lt = getlt(r.text)
    execution = getexecution(r.text)
    payload = { #构造请求头
        'username' : username,
        'password': password,
        'submit' : '',
        'lt' : lt,
        'execution' : execution,
        '_eventId' : 'submit',
        'rmShown' : '1'
    }

    login = s.post(url,data=payload,headers=header)

    if login.status_code == 200:
        print('%s login success!'%name)
        temp = s.get('**************',headers=header)
        preurl = '**************'
        dox = '************' #存放成绩的地址
        newurl = preurl + dox
        temp = s.get(newurl,headers=header)
        return temp.text
    else:
        print('%s login failed, login.status_code:'%name+login.status_code)
        return ''
def textanal(name,text):
    '''analysis the text of name, and save its grades'''
    if text :
        prepath = '***********' #保存个人成绩的地址
        path = prepath + name +'.txt'
        
        #从网页中获取成绩
        marks = text.split('''<tr class="odd" onMouseOut="this.className='even';" onMouseOver="this.className='evenfocus';">''')
        courses = {}
        n = 0
        for cours in marks:
            if n > 0 :
                L = re.findall('(?<=s)[^<|s][^>]*?(?=s)',cours)
                if len(L) >= 10 :
                    while len(L) > 10 :
                        del L[3]
                    key = L[2]
                    value = course(L)
                    save(path,' '.join(L)+'
')
                    courses[key] = value
                elif len(L) != 10 :
                    print('Error : wrong course')
            n += 1
        if courses :
            one = person(name,courses)
            path = prepath + 'allmarks.txt'
            save(path,name+' '+str(one.average)+'
') #记录此人均分
        else :
            global change_sum
            change_sum += 1
            print('%s password changed or exist verification code!'%name)

#读取每个人的username和password        
book = xlrd.open_workbook('************')
sheet = book.sheet_by_index(0)
nrows = sheet.nrows
for x in range(nrows):
    row = sheet.row_values(x)
    name = row[5]
    username = row[2]
    password = row[15][-6:]
    text = gettext(username,password)
    textanal(name,text)
print(change_sum) #输出修改密码的人的个数

最后用excel处理下数据就好啦！

然而最后发现修改了密码的人好少= =只有个位数