163 新闻页面网络爬虫简单抓取数据

#coding=utf-8
from bs4 import BeautifulSoup
import urllib2
import re
def searchurl(url):
    url = urllib2.urlopen(url)
    soup = BeautifulSoup(url)
    return soup
def search163(soup,divs,di):
    tags=soup.select(divs)
    a= tags[0].select(di)
    list1=list()
    for i in a:
        print "标题:",i.get_text()
        print "标题连接:",i["href"]
        list1.append(i["href"])
    return list1
    pass
def searchhold(i,divs,di):
    for a in i:
        soup=searchurl(a)
        cont=search66(soup,divs,di)
        #print cont
def search66(soup,divs,di):
        s=soup.select(divs)
        so= s[0].select(di)
        for i in so:
            print re.sub('\s','',i.get_text()).strip()
if __name__ == '__main__':
    s=searchurl("http://news.163.com/world/")
    i=search163(s,".today_news","a")
    #searchhold(i,"#endText","p")
    pass