Python中使用urllib2模块编写爬虫的简单上手示例

import urllib2 
response = urllib2.urlopen('http://www.baidu.com/') 
html = response.read() 
print html

import urllib2 
req = urllib2.Request('http://www.baidu.com') 
response = urllib2.urlopen(req) 
page = response.read() 
print page

import urllib 
import urllib2 
 
url = 'http://www.server.com/register.php' 
 
postData = {'useid' : 'user', 
   'pwd' : '***', 
   'language' : 'Python' } 
 
data = urllib.urlencode(postData) # 编码工作 
req = urllib2.Request(url, data) # 发送请求同时传data 
response = urllib2.urlopen(req) #接受反馈的信息 
page = response.read() #读取反馈的内容

import urllib2 
import urllib 
 
data = {} 
 
data['useid'] = 'user' 
data['pwd'] = '***' 
data['language'] = 'Python' 
 
values = urllib.urlencode(data) 
print values 
 
name=Somebody+Here&language=Python&location=Northampton 
url = 'http://www.example.com/example.php' 
full_url = url + '?' + url_values 
 
data = urllib2.open(full_url)

import urllib 
import urllib2 
 
url = 'http://www.server.com/register.php' 
 
user_agent = 'Mozilla/5.0 (Windows NT 6.1; rv:33.0) Gecko/20100101 Firefox/33.0' 
values = {'useid' : 'user', 
   'pwd' : '***', 
   'language' : 'Python' } 
 
headers = { 'User-Agent' : user_agent } 
data = urllib.urlencode(values) 
req = urllib2.Request(url, data, headers) 
response = urllib2.urlopen(req) 
page = response.read()

import urllib 
import urllib2 
 
url = 'http://www.server.com/register.php' 
 
user_agent = 'Mozilla/5.0 (Windows NT 6.1; rv:33.0) Gecko/20100101 Firefox/33.0' 
values = {'useid' : 'user', 
   'pwd' : '***', 
   'language' : 'Python' } 
 
headers = { 'User-Agent' : user_agent } 
data = urllib.urlencode(values) 
req = urllib2.Request(url, data, headers) 
response = urllib2.urlopen(req) 
page = response.read()

import urllib2 
 
req = urllib2.Request('http://www.python.org/callmewhy') 
 
try: 
 urllib2.urlopen(req) 
 
except urllib2.URLError, e: 
 
 print e.code 

#-*- coding:utf-8 -*-
from urllib2 import Request, urlopen, URLError, HTTPError
 
req = Request('http://www.python.org/callmewhy')
 
try: 
 
 response = urlopen(req) 
 
except URLError, e: 
 
 if hasattr(e, 'code'): 
 
  print '服务器不能正常响应这个请求！' 
 
  print 'Error code: ', e.code 
 
 elif hasattr(e, 'reason'): 
 
  print '无法与服务器建立连接' 
 
  print 'Reason: ', e.reason 
 
 
else: 
 
 print '没有出现异常'