Python学习之urlib模块和urllib2模块学习
一 urlib模块
利用urllib模块可以打开任意个url。
urlopen() 打开一个url返回一个文件对象，可以进行类似文件对象的操作。
In [308]: import urllib
In [309]: file=urllib.urlopen('
In [310]: file.readline()
Out[310]: '<!DOCTYPE html><!--STATUS OK--><html><head><meta http-equiv="content-type" content="text/html;charset=utf-8"><meta http-equiv="X-UA-Compatible" content="IE=Edge"><link rel="dns-prefetch" href="//s1.bdstatic.com"/><link rel="dns-prefetch" href="//t1.baidu.com"/><link rel="dns-prefetch" href="//t2.baidu.com"/><link rel="dns-prefetch" href="//t3.baidu.com"/><link rel="dns-prefetch" href="//t10.baidu.com"/><link rel="dns-prefetch" href="//t11.baidu.com"/><link rel="dns-prefetch" href="//t12.baidu.com"/><link rel="dns-prefetch" href="//b1.bdstatic.com"/><title>\xe7\x99\xbe\xe5\xba\xa6\xe4\xb8
可以用read(),readlines(),fileno(),close()这些函数
In [337]: file.info() Out[337]: <httplib.HTTPMessage instance at 0x2394a70> In [338]: file.getcode() Out[338]: 200 In [339]: file.geturl() Out[339]: 'http://www.baidu.com/'
2.urlretrieve() 将url对应的html页面保存为文件
In [404]: filename=urllib.urlretrieve('http://www.baidu.com/',filename='/tmp/baidu.html')
In [405]: type (filename)
Out[405]: <type 'tuple'>
In [406]: filename[0]
Out[406]: '/tmp/baidu.html'
In [407]: filename
Out[407]: ('/tmp/baidu.html', <httplib.HTTPMessage instance at 0x23ba878>)
In [408]: filename[1]
Out[408]: <httplib.HTTPMessage instance at 0x23ba878>
3.urlcleanup() 清除由urlretrieve()产生的缓存
In [454]: filename=urllib.urlretrieve('http://www.baidu.com/',filename='/tmp/baidu.html')
In [455]: urllib.urlcleanup()
4.urllib.quote()和urllib.quote_plus() 将url进行编码
In [483]: urllib.quote('http://www.baidu.com')
Out[483]: 'http%3A//www.baidu.com'
In [484]: urllib.quote_plus('http://www.baidu.com')
Out[484]: 'http%3A%2F%2Fwww.baidu.com'
5.urllib.unquote()和urllib.unquote_plus() 将编码后的url解码
In [514]: urllib.unquote('http%3A//www.baidu.com')
Out[514]: 'http://www.baidu.com'
In [515]: urllib.unquote_plus('http%3A%2F%2Fwww.baidu.com')
Out[515]: 'http://www.baidu.com'
6.urllib.urlencode() 将url中的键值对以&划分，可以结合urlopen()实现POST方法和GET方法
In [560]: import urllib
In [561]: params=urllib.urlencode({'spam':1,'eggs':2,'bacon':0})
In [562]: f=urllib.urlopen("http://python.org/query?%s" %params)
In [563]: f.readline()
Out[563]: '<!doctype html>\n'
In [564]: f.readlines()
Out[564]:
['<!--[if lt IE 7]> <html class="no-js ie6 lt-ie7 lt-ie8 lt-ie9"> <![endif]-->\n',
'<!--[if IE 7]> <html class="no-js ie7 lt-ie8 lt-ie9"> <![endif]-->\n',
'<!--[if IE 8]> <html class="no-js ie8 lt-ie9"> <![endif]-->\n',
'<!--[if gt IE 8]><!--><html class="no-js" lang="en" dir="ltr"> <!--<![endif]-->\n',
'\n',
二 urllib2模块
urllib2比urllib多了些功能，例如提供基本的认证，重定向，cookie等功能
https://docs.python.org/2/library/urllib2.html
https://docs.python.org/2/howto/urllib2.html
In [566]: import urllib2
In [567]: f=urllib2.urlopen('http://www.python.org/')
In [568]: print f.read(100)
--------> print(f.read(100))
<!doctype html>
<!--[if lt IE 7]> <html class="no-js ie6 lt-ie7 lt-ie8 lt-ie9"> <![endif]-->
打开python的官网并返回头100个字节内容
HTTP基于请求和响应，客户端发送请求，服务器响应请求。urllib2使用一个Request对象代表发送的请求，调用urlopen()打开Request对象可以返回一个response对象。reponse对象是一个类似文件的对象，可以像文件一样进行操作
In [630]: import urllib2
In [631]: req=urllib2.Request('http://www.baidu.com')
In [632]: response=urllib2.urlopen(req)
In [633]: the_page=response.read()
In [634]: the_page
Out[634]: '<!DOCTYPE html><!--STATUS OK--><html><head><meta http-equiv="content-type" content="text/html;charset=utf-8"><meta http-equiv="X-UA-Compatible" content="IE=Edge"><link rel="dns-prefetch" href="//s1.bdstatic.com"/><link rel="dns-prefetch" href="//t1.baidu.com"/><link rel="dns-prefetch" href="//t2.baidu.com"/><link rel="dns-prefetch" href="//t3.baidu.
通常情况下需要向一个url以POST的方式发送数据。
In [763]: import urllib
In [764]: import urllib2
In [765]: url='http://xxxxxx/login.php'
In [766]: values={'ver' : '1.7.1', 'email' : 'xxxxx', 'password' : 'xxxx', 'mac' : '111111111111'}
In [767]: data=urllib.urlencode(values)
In [768]: req=urllib2.Request(url,data)
In [769]: response=urllib2.urlopen(req)
In [770]: the_page=response.read()
In [771]: the_page
如果不使用urllib2.Request()发送data参数，urllib2使用GET请求，GET请求和POST请求差别在于POST请求常有副作用，POST请求会通过某些方式改变系统的状态。也可以通过GET请求发送数据。
In [55]: import urllib2
In [56]: import urllib
In [57]: url='http://xxx/login.php'
In [58]: values={'ver' : 'xxx', 'email' : 'xxx', 'password' : 'xxx', 'mac' : 'xxx'}
In [59]: data=urllib.urlencode(values)
In [60]: full_url=url + '?' + data
In [61]: the_page=urllib2.urlopen(full_url)
In [63]: the_page.read()
Out[63]: '{"result":0,"data":0}'
默认情况下,urllib2使用Python-urllib/2.6 表明浏览器类型，可以通过增加User-Agent HTTP头
In [107]: import urllib
In [108]: import urllib2
In [109]: url='http://xxx/login.php'
In [110]: user_agent='Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
In [111]: values={'ver' : 'xxx', 'email' : 'xxx', 'password' : 'xxx', 'mac' : 'xxxx'}
In [112]: headers={'User-Agent' : user_agent}
In [114]: data=urllib.urlencode(values)
In [115]: req=urllib2.Request(url,data,headers)
In [116]: response=urllib2.urlopen(req)
In [117]: the_page=response.read()
In [118]: the_page
当给定的url不能连接时，urlopen()将报URLError异常，当给定的url内容不能访问时，urlopen()会报HTTPError异常
#/usr/bin/python
from urllib2 import Request,urlopen,URLError,HTTPError
req=Request('http://10.10.41.42/index.html')
try:
response=urlopen(req)
except HTTPError as e:
print 'The server couldn\'t fulfill the request.'
print 'Error code:',e.code
except URLError as e:
print 'We failed to fetch a server.'
print 'Reason:',e.reason
else:
print "Everything is fine"
这里需要注意的是在写异常处理时，HTTPError必须要写在URLError前面
#/usr/bin/python
from urllib2 import Request,urlopen,URLError,HTTPError
req=Request('http://10.10.41.42')
try:
response=urlopen(req)
except URLError as e:
if hasattr(e,'reason'):
print 'We failed to fetch a server.'
print 'Reason:',e.reason
elif hasattr(e,'code'):
print 'The server couldn\'t fulfill the request.'
print 'Error code:',e.code
else:
print "Everything is fine"
hasattr()函数判断一个对象是否有给定的属性