Python爬虫自动查询教务处课程成绩

# -*- coding:utf-8 -*-
'''
Created on 2017年10月30日


@summary: 利用Python爬虫爬取研究生教务系统信息


@author: dreamhome
'''
import urllib
import urllib2
import cookielib
import re
import json


import matplotlib.pyplot as plt
import matplotlib.image as mpimg # mpimg 用于读取图片


from bs4 import BeautifulSoup


loginUrl = "http://gms.lzu.edu.cn/graduate/j_acegi_security_check"


#cookie
cookie = cookielib.CookieJar()
handler = urllib2.HTTPCookieProcessor(cookie)
opener = urllib2.build_opener(handler)
#postdata
values = {
    'j_username':'',
    'j_password':'',
    'j_captcha':''
}
#headers
header = {
    'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36',
    'Referer':'http://gms.lzu.edu.cn/graduate/j_acegi_security_check'
}


#输入学号
print "请输入学号："
values['j_username']=raw_input()
#输入密码
print "请输入密码："
values['j_password']=raw_input()


#获取验证码


validate_number=opener.open("http://gms.lzu.edu.cn/graduate/getCaptcha.do?")
validate_number_data=validate_number.read()
validate_number_pic=file("validate.jpg",'wb')
validate_number_pic.write(validate_number_data)
validate_number_pic.close()


#显示验证码


validate = mpimg.imread('validate.jpg')
plt.imshow(validate)
plt.axis('off') # 不显示坐标轴
plt.show()


#输入验证码
print '请输入验证码：'
values['j_captcha']=raw_input()


#模拟登陆
postdata = urllib.urlencode(values)
request = urllib2.Request(loginUrl,postdata,header)
response = opener.open(request)
score_url = 'http://gms.lzu.edu.cn/graduate/studentscore/queryScore.do?groupId=&moduleId=25011'
response = opener.open(score_url)
html=response.read()




#判断登录是否成功
if "权限不够,访问被拒绝" in html:
    print "登录信息错误，请重新登录"
    exit()


#简单数据解析
soup = BeautifulSoup(html.decode('utf8'),'lxml')  
trs = soup.findAll('tr')
score_data=[]
for tr in trs:  
    row=tr.get_text().split()
    temp_row=[]
    for x in row:
         temp_row.append(x.strip())
    score_data.append(temp_row)


#输出成绩信息
for x in range(len(score_data)):
    for y in score_data[x]:
        print y,
    print

1.tesseract-ocr安装 
sudo apt-get install tesseract-ocr


2.pytesseract安装 
sudo pip install pytesseract

from PIL import Image
import pytesseract


# 自动识别验证码
image=Image.open('validate.jpg')
code= pytesseract.image_to_string(image)
print code