简单的校园网IEEE下载模块，输入论文链接中的ID自动尝试登录下载（只在校园网有效）

gistfile1.py

'''
Created on 2013-5-10

@author: crosslife
'''
from urllib import urlopen
import urllib2
import cookielib
import re
import time
import thread
import threading
 
NAMELIST=[]
def getAbstract(paper_id):    
    requrl = "http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=" + str(paper_id)
    try:
        paperPage = urlopen(requrl)
        paperText = paperPage.read()        
    except Exception:
        paperText = ""
            
    title = re.findall('<h1>\s*(.+?)\s*</h1>',paperText,re.IGNORECASE)        
    abs = re.findall('<h2>Abstract</h2>\s*</a>\s*<p>(.+?)</p>',paperText,re.IGNORECASE)
    print abs #debug
    if title == [] or abs == []:#network exception
        return "empty###empty"
    abs[0] = title[0] + "###" + abs[0]
    return abs[0]
 
#check for auth, if success,save to cookiefile    
def authCheck(cookiefile):    
    cookies = cookielib.MozillaCookieJar(cookiefile)
    cookiehand  = urllib2.HTTPCookieProcessor(cookies)
    opener = urllib2.build_opener(cookiehand)
    opener.addheaders = [("User-Agent","Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"),
                         ("Host","ieeexplore.ieee.org")]
    try:
        opener.open("http://ieeexplore.ieee.org/xpl/conferences.jsp")
    except:
        print "network error"
        return False
    for item in cookies:
        if item.name == "xploreCookies":
            print "auth success!"
            cookies.save(cookiefile, ignore_discard=True, ignore_expires=True)
            return True
    return False
 
def downWithCookies(cookiefile,paper_id):
    abs = getAbstract(paper_id)
    if(abs == "empty###empty"):#mostly caused by network error
            print "None Abstract :%d ,retrying..." % int(paper_id)
            count = 1
            while abs == "empty###empty":                        
                abs = getAbstract(paper_id)                
                count += 1
                if count > 5:
                    print "cann't get the abstract of %d" % int(paper_id) #mostly caused by no abstract
                    break
    cookies = cookielib.MozillaCookieJar(cookiefile)
    cookies.load(cookiefile, ignore_discard=True, ignore_expires=True)
    opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookies))
    page = opener.open("http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=" + str(paper_id))
    pagetext = page.read()
    matchGroup = re.findall('<frame src="(http.*?)"',pagetext,re.IGNORECASE)
    try:
        pdflink = matchGroup[0]   
    except IndexError:
        print "cookies outdated"
        return False 
    pdfpage = opener.open(pdflink)
    pdftext = pdfpage.read()
    f = open(str(paper_id)+".pdf","wb")
    f.write(pdftext)
    f.close()
    return True

def timingDown(seconds,paper_id):
    time.sleep(seconds)
    print "Starting download..."
    count = 1
    while True:        
        print "trying to login %d" % count
        if authCheck("cookies.txt") == True:
            print "auth success!"
            break
        count += 1
        time.sleep(5)
    if downWithCookies("cookies.txt",paper_id):
        print "download success!"
        return True
    return False
 
def threadDown(seconds,paper_id):
    thread.start_new_thread(timingDown,(seconds,paper_id))     
 
def test():
    paper_id = raw_input("Input the id of the paper:")
    timingDown(0, paper_id)
    
    
if __name__ == '__main__':test()