import urllib
r = urllib.urlopen('//www.jb51.net/')
datatLine = r.readline() #读取html页面的第一行
data=file.read() #读取全部
f=open("./1.html","wb") # 网页保存在本地
f.write(data)
f.close()

import urllib.request
import urllib.parse
url = 'https://passport.jb51.net/user/signin"htmlcode">

import urllib.request
import urllib.parse
url = 'https://passport.jb51.net/user/signin"htmlcode">

def use_proxy(proxy_addr,url):
import urllib.request
#构建代理
proxy=urllib.request.ProxyHandler({'http':proxy_addr})
# 构建opener对象
opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandler)
# 安装到全局
# urllib.request.install_opener(opener)
# data=urllib.request.urlopen(url).read().decode('utf8') 以全局方式打开
data=opener.open(url) # 直接用句柄方式打开
return data
proxy_addr='61.163.39.70:9999'
data=use_proxy(proxy_addr,'//www.jb51.net')
print(len(data))
## 异常处理以及日输出


opener通常是build_opener()创建的opener对象。
install_opener(opener) 安装opener作为urlopen()使用的全局URL opener
cookie的使用
获取Cookie保存到变量


import http.cookiejar, urllib.request
#使用http.cookiejar.CookieJar()创建CookieJar对象
cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
#使用HTTPCookieProcessor创建cookie处理器，并以其为参数构建opener对象
opener = urllib.request.build_opener(handler)
#将opener安装为全局
urllib.request.install_opener(opener)
response = urllib.request.urlopen('//www.jb51.net')
#response = opener.open('//www.jb51.net')
for item in cookie:
print 'Name = '+item.name
print 'Value = '+item.value


首先我们必须声明一个 CookieJar 对象，接下来我们就需要利用 HTTPCookieProcessor 来构建一个 handler ，最后利用 build_opener 方法构建出 opener ，执行 open() 即可。 最后循环输出cookiejar
获取Cookie保存到本地


import cookielib
import urllib
#设置保存cookie的文件，同级目录下的cookie.txt
filename = 'cookie.txt'
#声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件
cookie = cookielib.MozillaCookieJar(filename)
#利用urllib库的HTTPCookieProcessor对象来创建cookie处理器
handler = urllib.request.HTTPCookieProcessor(cookie)
#通过handler来构建opener
opener = urllib.request.build_opener(handler)
#创建一个请求，原理同urllib2的urlopen
response = opener.open("//www.jb51.net")
#保存cookie到文件
cookie.save(ignore_discard=True, ignore_expires=True)


异常处理
异常处理结构如下


try:
# 要执行的代码
print(...)
except:
#try代码块里的代码如果抛出异常了，该执行什么内容
print(...)
else:
#try代码块里的代码如果没有跑出异常，就执行这里
print(...)
finally:
#不管如何，finally里的代码，是总会执行的
print(...)


URLerror产生原因：
1、网络未连接（即不能上网）


from urllib import request, error
try:
r=request.urlopen('//www.jb51.net')
except error.URLError as e:
print(e.reason)


2、访问页面不存(HTTPError)
客户端向服务器发送请求，如果成功地获得请求的资源，则返回的状态码为200，表示响应成功。如果请求的资源不存在， 则通常返回404错误。


from urllib imort request, error
try:
response = request.urlopen('//www.jb51.net')
except error.HTTPError as e:
print(e.reason, e.code, e.headers, sep='\n')
else:
print("Request Successfully')
# 加入 hasattr属性提前对属性,进行判断原因
from urllib import request,error
try:
response=request.urlopen('http://blog.jb51.net')
except error.HTTPError as e:
if hasattr(e,'code'):
print('the server couldn\'t fulfill the request')
print('Error code:',e.code)
elif hasattr(e,'reason'):
print('we failed to reach a server')
print('Reason:',e.reason)
else:
print('no exception was raised')
# everything is ok


下面为大家列出几个urllib模块很有代表性的实例
1、引入urllib模块


import urllib.request
response = urllib.request.urlopen('http://jb51.net/')
html = response.read()


2、使用 Request


import urllib.request
req = urllib.request.Request('http://jb51.net/')
response = urllib.request.urlopen(req)
the_page = response.read()


3、发送数据


#! /usr/bin/env python3
import urllib.parse
import urllib.request
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
'act' : 'login',
'login[email]' : 'yzhang@i9i8.com',
'login[password]' : '123456'
}
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data)
req.add_header('Referer', '//www.jb51.net/')
response = urllib.request.urlopen(req)
the_page = response.read()
print(the_page.decode("utf8"))


4、发送数据和header


#! /usr/bin/env python3
import urllib.parse
import urllib.request
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
'act' : 'login',
'login[email]' : 'yzhang@i9i8.com',
'login[password]' : '123456'
}
headers = { 'User-Agent' : user_agent }
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data, headers)
response = urllib.request.urlopen(req)
the_page = response.read()
print(the_page.decode("utf8"))


5、http 错误


#! /usr/bin/env python3
import urllib.request
req = urllib.request.Request('//www.jb51.net ')
try:
urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
print(e.code)
print(e.read().decode("utf8"))


6、异常处理


#! /usr/bin/env python3
from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request("//www.jb51.net /")
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 reach a server.')
print('Reason: ', e.reason)
else:
print("good!")
print(response.read().decode("utf8"))


7、异常处理


from urllib.request import Request, urlopen
from urllib.error import URLError
req = Request("//www.jb51.net /")
try:
response = urlopen(req)
except URLError as e:
if hasattr(e, 'reason'):
print('We failed to reach 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("good!")
print(response.read().decode("utf8"))


8、HTTP 认证


#! /usr/bin/env python3
import urllib.request
# create a password manager
password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()
# Add the username and password.
# If we knew the realm, we could use it instead of None.
top_level_url = "https://www.jb51.net /"
password_mgr.add_password(None, top_level_url, 'rekfan', 'xxxxxx')
handler = urllib.request.HTTPBasicAuthHandler(password_mgr)
# create "opener" (OpenerDirector instance)
opener = urllib.request.build_opener(handler)
# use the opener to fetch a URL
a_url = "https://www.jb51.net /"
x = opener.open(a_url)
print(x.read())
# Install the opener.
# Now all calls to urllib.request.urlopen use our opener.
urllib.request.install_opener(opener)
a = urllib.request.urlopen(a_url).read().decode('utf8')
print(a)


9、使用代理


#! /usr/bin/env python3
import urllib.request
proxy_support = urllib.request.ProxyHandler({'sock5': 'localhost:1080'})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)
a = urllib.request.urlopen("//www.jb51.net ").read().decode("utf8")
print(a)


10、超时


#! /usr/bin/env python3
import socket
import urllib.request
# timeout in seconds
timeout = 2
socket.setdefaulttimeout(timeout)
# this call to urllib.request.urlopen now uses the default timeout
# we have set in the socket module
req = urllib.request.Request('//www.jb51.net /')
a = urllib.request.urlopen(req).read()
print(a)


11.自己创建build_opener


header=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36')]
#创建opener对象
opener=urllib.request.build_opener()
opener.addheaders=header
#设置opener对象作为urlopen()使用的全局opener
urllib.request.install_opener(opener)
response =urllib.request.urlopen('//www.jb51.net/')
buff = response.read()
html = buff .decode("utf8")
response.close()
print(the_page)


12.urlib.resquest.urlretrieve远程下载


header=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36')]
#创建opener对象
opener=urllib.request.build_opener()
opener.addheaders=header
#设置opener对象作为urlopen()使用的全局opener
urllib.request.install_opener(opener)
#下载文件到当前文件夹
urllib.request.urlretrieve('//www.jb51.net/','baidu.html')
#清除urlretrieve产生的缓存
urlib.resquest.urlcleanup()


13.post请求


import urllib.request
import urllib.parse
url='//www.jb51.net/mypost/'
#将数据使用urlencode编码处理后，使用encode()设置为utf-8编码
postdata=urllib.parse.urlencode({name:'测试名',pass:"123456"}).encode('utf-8')
#urllib.request.quote()接受字符串，
#urllib.parse.urlencode()接受字典或者列表中的二元组[(a,b),(c,d)],将URL中的键值对以连接符&划分
req=urllib.request.Request(url,postdata)
#urllib.request.Request(url, data=None, header={}, origin_req_host=None, unverifiable=False, #method=None)
#url：包含URL的字符串。
#data：http request中使用，如果指定，则发送POST而不是GET请求。
#header：是一个字典。
#后两个参数与第三方cookie有关。
req.add_header('user-agent','User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/
537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0')
data=urllib.request.urlopen(req).read()
//urlopen（）的data参数默认为None，当data参数不为空的时候，urlopen（）提交方式为Post。


14.cookie的使用
1.获取Cookie保存到变量


 import urllib.request
 import http.cookie
 # 声明一个CookieJar对象实例来保存cookie
 cookie = cookielib.CookieJar()
 # 利用urllib库的HTTPCookieProcessor对象来创建cookie处理器
 handler = urllib.request.HTTPCookieProcessor(cookie)
 # 通过handler来构建opener
 opener = urllib.request.build_opener(handler)
 # 此处的open方法同urllib.request的urlopen方法，也可以传入request
 urllib.request.install_opener(opener)
 #使用opener或者urlretrieve方法来获取需要的网站cookie
 urllib.request.urlretrieve('//www.jb51.net/','baidu.html')
 # data=urllib.request.urlopen('//www.jb51.net/')



2.保存cookies到文件


import http.cookie
import urllib.request
# 设置保存cookie的文件，同级目录下的cookie.txt
filename = 'cookie.txt'
# 声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件
cookie = http.cookie.MozillaCookieJar(filename)
# 利用urllib库的HTTPCookieProcessor对象来创建cookie处理器
handler = urllib.request.HTTPCookieProcessor(cookie)
# 通过handler来构建opener
opener = urllib.request.build_opener(handler)
# 创建一个请求，原理同urllib的urlopen
response = opener.open("//www.jb51.net")
# 保存cookie到文件
cookie.save(ignore_discard=True, ignore_expires=True)



3.从文件中获取cookies并访问


import http.cookielib
import urllib.request
# 创建MozillaCookieJar实例对象
cookie = http.cookie.MozillaCookieJar()
# 从文件中读取cookie内容到变量
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
# 创建请求的request
req = urllib.Request("//www.jb51.net")
# 利用urllib的build_opener方法创建一个opener
opener = urllib.build_opener(urllib.request.HTTPCookieProcessor(cookie))
response = opener.open(req)
print (response.read())


15.代理服务器设置


import socket
#设置Socket连接超时时间,同时决定了urlopen的超时时间
socket.setdefaulttimeout(1)
import urllib.request
#代理服务器信息，http代理使用地址
startime = time.time()
#设置http和https代理
proxy=request.ProxyHandler({'https':'175.155.25.91:808','http':'175.155.25.91:808'})
opener=request.build_opener(proxy)
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64; rv:53.0) Gecko/20100101 Firefox/53.0'),
# ("Accept","text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"),
# ("Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3"),
# ("Accept-Encoding","gzip, deflate, br"),
# ("Connection","keep-alive"),
# ("Pragma","no-cache"),
# ("Cache-Control","no-cache")
  ]
request.install_opener(opener)
# data = request.urlopen('https://www.jb51.net/find-ip-address').read()
data = request.urlopen( 'http://www.ipip.net/' ).read().decode('utf-8')
# data=gzip.decompress(data).decode('utf-8','ignore')
endtime = time.time()
delay = endtime-startime
print(data)


有时在urlopen的data数据直接decode(‘utf-8')会失败，必须要使用gzip.decompress(‘utf-8','ignore')才能打开，猜测应该是header的问题，换一个有时会好
本文主要讲解了python爬虫模块urllib详细使用方法与实例全解，更多关于python爬虫模块urllib详细使用方法与实例请查看下面的相关链接