urllib2基础操作

Urllib2基础操作

1、打开网页(urlopen)

打开一个网页

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

urlopen一般常用的有三个参数，它的参数如下：

urllib.requeset.urlopen(url,data,timeout)

data参数的使用(GET)

import urllib  
import urllib2  

data = {'email':'myemail', 'password':'password'}  
params = urllib.urlencode(params) 
response= urllib.urlopen("%s?%s"%(uri, params))
code = response.getcode() 

 data参数的使用(POST)

import urllib  
import urllib2  

data = {'email':'myemail', 'password':'password'}  
params = urllib.urlencode(data) 
response= urllib.urlopen(uri, params)
code = response.getcode() 

 所以如果我们添加data参数的时候就是以post请求方式请求，如果没有data参数就是get请求方式

timeout参数的使用

在某些网络情况不好或者服务器端异常的情况会出现请求慢的情况，请求设置一个超时时间

import urllib2

response = urllib2.urlopen('http://www.baidu.com', timeout=1)
print(response.read())

 2、打开网页(request)

打开一个网页

import urllib.request

request = urllib.request.Request('https://www.baidu.com')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

 指定请求头

import urllib2

# 制定请求头
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64)"}

# 封装请求
request = urllib2.Request(url=url, headers=headers)
response = urllib2.urlopen(request)
content = response.read().decode('utf-8')
print content

 3、进阶

增加代理

# 自定义headers
headers = {
    'Host':'www.dianping.com',
    'Cookie': 'JSESSIONID=F1C38C2F1A7F7BF3BCB0C4E3CCDBE245 aburl=1; cy=2;'
    'User-Agent': "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
    }

proxy_handler = urllib2.ProxyHandler({'http': 'http://host:port'})
opener = urllib2.build_opener(proxy_handler)
urllib2.install_opener(opener)
request = urllib2.Request(url, headers=headers)
response = urllib2.urlopen(request)
content = response.read().decode('utf-8')

 操作cookie

import urllib2
import cookielib
import json

cookie = cookielib.CookieJar()
cookie_s = urllib2.HTTPCookieProcessor(cookie)  # 创建cookie处理器
opener = urllib2.build_opener(cookie_s)
# 构建opener
urllib2.install_opener(opener)
response= urllib2.urlopen('http://www.dianping.com').read()  # 读取指定网站的内容  cj = urllib2.HTTPCookieProcessor(cookie)
print response    # 网页HTML

# 查看cookie
print cookie, type(cookie)
for item in cookie:
    print 'name:' + item.name + '-value:' + item.value

 保存cookie

def saveCookie():
    # 设置保存cookie的文件
    filename = 'cookie.txt'
    # 声明一个MozillaCookieJar对象来保存cookie，之后写入文件
    cookie = cookielib.MozillaCookieJar(filename)
    # 创建cookie处理器
    handler = urllib2.HTTPCookieProcessor(cookie)
    # 构建opener
    opener = urllib2.build_opener(handler)
    # 创建请求
    res = opener.open('http://www.baidu.com')
    # 保存cookie到文件
    # ignore_discard的意思是即使cookies将被丢弃也将它保存下来
    # ignore_expires的意思是如果在该文件中cookies已经存在，则覆盖原文件写入
    cookie.save(ignore_discard=True, ignore_expires=True)

 在文件中取出cookie

def getCookie():
    # 创建一个MozillaCookieJar对象
    cookie = cookielib.MozillaCookieJar()
    # 从文件中的读取cookie内容到变量
    cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
    # 打印cookie内容,证明获取cookie成功
    for item in cookie:
        print 'name:' + item.name + '-value:' + item.value
    # 利用获取到的cookie创建一个opener
    handler = urllib2.HTTPCookieProcessor(cookie)
    opener = urllib2.build_opener(handler)
    res = opener.open('http://www.baidu.com')
    print res.read()

 来个实例

def my_cookie_test():
    headers = {
        'User-Agent': "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4',
        'Connection': 'keep-alive',
        'Cookie': 'cy=2; _lxsdk_cuid=16000a1a16cc8-0629d2ca3b9f7-40544230-100200-16000a1a16dc8; _lxsdk=16000a1a16cc8-0629d2ca3b9f7-40544230-100200-16000a1a16dc8; _lxsdk_s=16000a1a16f-c56-870-2aa%7C%7C23; _hc.v=44792549-7147-7394-ac0a-eefed1fa19a2.1511839081; s_ViewType=10',
        'Host': 'www.dianping.com',
        'Referer': 'http://www.dianping.com/shop',
        'Upgrade-Insecure-Requests': 1
    }
    # 请求cookie
    cj_a = cookielib.CookieJar()
    cj_s = urllib2.HTTPCookieProcessor(cj_a)
    proxy_s = urllib2.ProxyHandler({'http': '0.0.0.0:8080'})
    opener = urllib2.build_opener(proxy_s, cj_s)
    urllib2.install_opener(opener)
    try:
        request = urllib2.Request("http://www.dianping.com/shop/000000/", headers=headers)
        response = urllib2.urlopen(request)
        content = response.read().decode('utf-8')
        # HTML
        print content
        cookie_data = {}
        for item in cj_a:
            # print '请求之后：name:' + item.name + '-value:' + item.value
            cookie_data[item.name] = item.value
        cookie_str = json.dumps(cookie_data)
        with open('cookie.txt', 'w') as f:
            f.write(cookie_str)
        print("cookies信息已保存到本地")
    except Exception as e:
        print e

网页信息抽取。。。待下期。。。