urllib

1、载入网页

import urllib

page = urllib.urlopen('http://www.baidu.com')
page_ct = page.read()

print page.info()            
print page.getcode()  #状态信息？ 200
print page.geturl()     #请求的url

print page_ct             #网页源码

2、下载网页，显示进度

import urllib

def get_callback(a, b, c)
    ''''''回调函数
    @a:已下载的数据块
    @b：数据块大小
    @c：文件总大小
    '''

    per = 100.0 * a * b / c
    if per > 100:
        per = 100
    
    print '%.2f%%' % per


url_path = 'http://www.cnblogs.com'
local = 'd:\\cnblogs.html'

urllib.urlretrieve(url_path, local, get_callback)

3、url编码

import urllib

data = 'querysql = ~row + 1'

data_encode = urllib.quote(data)
print data_encode   # querysql%20%3D%20%7Erow%20%2B%201
print urllib.uquote(data_encode)


data_e2 = urllib.quote_plus(data)
print data_e2    #querysql+%3D+%7Erow+%2B+1
print urllib.uquote_plus(data_e2)


sql = urllib.urlencode({'name':'xfs', 'age':2})
print sql    #age=2&name=xfs