东华大学教务处python爬虫

最新推荐文章于 2021-11-07 18:28:53 发布

mowayao

最新推荐文章于 2021-11-07 18:28:53 发布

阅读量3.2k

点赞数

本文链接：https://blog.youkuaiyun.com/mowayao/article/details/16105095

版权

'''
Created on 2013-11-12

@author: mowayao
'''

import urllib  
import urllib2
import cookielib
import re
def SubTitle(web):
    key = "<title>.+</title>"
    title = re.findall(key,web)
    return title
cookie = cookielib.CookieJar()  
headers = {
    'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'
}
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
postdata=urllib.urlencode({  
    'userName':'XXXXX',  
    'userPwd':'XXXXX'  
})
req = urllib2.Request(  
    url = 'http://jw.dhu.edu.cn/dhu/login_zh.jsp',  
    data = postdata,
    headers = headers
)
filename = "es"    
fl = file(filename,'w')
result = opener.open(req)
#print result.read()
#fl.write(result.read())
ref = urllib2.Request(  
    url = 'http://jw.dhu.edu.cn/dhu/student/query/scorequery.jsp?studentId=null', 
    headers = headers
)
html = opener.open(ref).read()
title = SubTitle(html)
problem = re.compile(u'<body.+</body>',re.DOTALL)
style = problem.search(html)
if style:
    print(style.group())
    html = style.group(0)
    tmp = re.sub('<[^>]*>',' ',html)
    tmp = tmp.replace('\s+','')
    tmp = tmp.replace('\s+','')
   #print(tmp)
    fl.write(tmp)