beautifulSoap使用

import db,re,os
import socket
from urllib import urlopen
from BeautifulSoup import BeautifulSoup 

def mkdir(path=''):
    base = '.'
    newpath = base + '\\'+path
    if (os.path.exists(newpath)):
        pass
    else:
        os.mkdir(newpath)

socket.setdefaulttimeout(600)

url="http://www.example.com"
text2 = urlopen(url).read()
text = BeautifulSoup(text2).prettify()

or

text2 = urlopen('http://www.example.com/').read()
text = BeautifulSoup(text2)
[s.extract() for s in text('script')]  #去除 危险的script
[s.extract() for s in text('style')]   #去除样式
print text.prettify()

==========================
安装
wget http://www.crummy.com/software/BeautifulSoup/download/3.x/BeautifulSoup-3.2.1.tar.gz

tar zxf

cd 目录

python setup.py install