两个无聊的小脚本

tieba1.py

# -*- coding: utf-8 -*-
#过滤最近1月发帖并且12级的用户
import urllib,urllib2,re
from multiprocessing import Pool
from multiprocessing.dummy import Pool as ThreadPool

URLBASE='http://tieba.baidu.com/f?kw=%E5%8D%8E%E4%B8%9C%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6&ie=utf-8&pn='
result=set()
realres=[]
pool = ThreadPool(10)
def conp(s):
    return re.findall(r'&ie=utf-8&fr=frs" target="_blank">(.+?)</a>',s)
def getlevel(s):
    pram=urllib.urlencode({'un':s,'ie':'utf-8','fr':'frs'})
    url='http://tieba.baidu.com/home/main/?'+pram
    pres=urllib2.urlopen(url).read()
    return re.findall(u'<span>华东理工大学</span><span class="forum_level (.+?)">'.encode('GBK'),pres)

def doit(i):
    mk=getlevel(i)
    if len(mk)>0:
        print mk[0],i
        if mk[0]=='lv12':
            realres.append(i)
for i in range(0,2050,50):
    res=urllib2.urlopen(URLBASE+str(i)).read()
    result|=set(conp(res))
    print i,len(result)


l=list(result)

pool.map(doit,l)
pool.close()
pool.join()

print realres

tieba2.py

# -*- coding: utf-8 -*-
#输出指定文件中用户的关注列表
import urllib,urllib2,re
f=open('D:/in.txt','r')
l=f.readlines()
for i in l:
    print i
    m=i.replace('\n','').replace('\r','').replace(' ','')
    pram=urllib.urlencode({'un':m,'ie':'utf-8','fr':'frs'})
    url='http://tieba.baidu.com/home/main/?'+pram
    pres=urllib2.urlopen(url).read()
    print i
    for t in re.findall(r'class="u-f-item unsign"><span>(.+?)</span>',pres):
        print t.decode('GBK')
    print '------------'