爬网页哦

# -*- coding: UTF-8-*- 
import urllib2,re

mylist = []

p = re.compile( r"<a.+?href=.+?>.+?</a>")
pname = re.compile( r"(？<=>).*？（？=</a>）" )
phref = re.compile( r"(?<=href\=\")http.*?(?=\")")

html_c = urllib2.urlopen("http://www.baidu.com/?vit=1").read()

def geturltest(str):
    html_c = urllib2.urlopen(str).read()
    arr = p.findall(html_c)
    for ever in arr:
        con = phref.findall(ever)
        if len(con) > 0:
            print con[0]
        
def geturl(str):
    html_c = urllib2.urlopen(str).read()
    arr = p.findall(html_c)
    for ever in arr:
        con = phref.findall(ever)
        if len(con) == 0:
            continue
        else:
            print con[0]
            if mylist.__contains__(con[0]) == False:
                mylist.append(con[0])
                geturl(con[0])
            else:
                pass
def main():
    geturl("http://www.baidu.com/?vit=1")

if __name__ == '__main__': main()