python中urllib库简单使用

# coding : utf-8
import urllib

url = 'http://cnblogs.com'

#代理服务器
proxies = {'http':'http://127.0.0.1:8087'}#这里的代理地址必须使用dictionary
#使用代理服务器打开
r = urllib.urlopen(url,proxies = proxies)

print r.info()#取响应header头所有信息

print r.info().getheader('Content-Type')#取响应header某一项信息
print r.getcode()#返回http状态码
print r.geturl()#返回请求的url

#打开本地文件

#>>> urllib.url2pathname.__doc__
#"OS-specific conversion from a relative URL of the 'file' scheme\n    to a file system path; not recommended for general use."
#>>> urllib.pathname2url.__doc__
#"OS-specific conversion from a file system path to a relative URL\n    of the 'file' scheme; not recommended for general use."
#可以使用上面两个函数对url和本地路径进行转换
f = urllib.urlopen(url = 'file:/home/ma6174/a.sh')
print f.read()

#打开ftp
# f = urllib.urlopen(url = 'ftp://username:password@ftpaddress')

#保存网页并显示进度
def cbk(a, b, c):
        '''
        a: num
        b: size
        c: total
         '''
        per = 100.0*a*b/c
        if per > 100:
                per = 100
        print '%.2f%%' % per

local = 'cnblogs.html'
urllib.urlretrieve(url,local,cbk)#将服务器文件取回本地保存为local

#get方法
params = urllib.urlencode({'spam': 1, 'eggs': 2, 'bacon': 0})

#将dict或者包含两个元素的元组列表转换成url参数。例如

#字典 {'name': 'wklken', 'pwd': '123'}将被转换为"name=wklken&pwd=123"（会有无序问#题）
f = urllib.urlopen("http://www.musi-cal.com/cgi-bin/query?%s" % params)
print f.read()

#post方法
params = urllib.urlencode({'spam': 1, 'eggs': 2, 'bacon': 0})
f = urllib.urlopen("http://www.musi-cal.com/cgi-bin/query", params)
print f.read()

#编码解码

#>>> print urllib.quote.__doc__
#quote('abc def') -> 'abc%20def'

#   Each part of a URL, e.g. the path info, the query, etc., has a
#    different set of reserved characters that must be quoted.

#    RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
#    the following reserved characters.

#    reserved    = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
#                  "$" | ","

#    Each of these characters is reserved in some component of a URL,
#    but not necessarily in all of them.

#    By default, the quote function is intended for quoting the path
#    section of a URL.  Thus, it will not encode '/'.  This character
#    is reserved, but in typical usage the quote function is being
#    called on a path where the existing slash characters are used as
#    reserved characters.

data = 'name = ~a+3'  

data1 = urllib.quote(data)   
print data1 # result: name%20%3D%20%7Ea%2B3   
print urllib.unquote(data1) # result: name = ~a+3   
  
data2 = urllib.quote_plus(data)   
print data2 # result: name+%3D+%7Ea%2B3   
print urllib.unquote_plus(data2)    # result: name = ~a+3   
  
data3 = urllib.urlencode({ 'name': 'dark-bull', 'age': 200 })   
print data3 # result: age=200&name=dark-bull   
  
data4 = urllib.pathname2url(r'd:/a/b/c/23.php')   
print data4 # result: ///D|/a/b/c/23.php   
print urllib.url2pathname(data4)    # result: D:/a/b/c/23.ph