爬取百度百科

import urllib.request
from bs4 import BeautifulSoup
import re

def main():
    response= urllib.request.urlopen('http://baike.baidu.com/view/284853.htm').read()
    soup = BeautifulSoup(response,'html.parser')#使用python默认的解析器
    for each in soup.find_all(href = re.compile('view')):
        print(each.text,'->',''.join(['http://baike.baidu.com/',each['href']]))#join函数明显比+提高
if __name__=='__main__':
    main()