Python开发简单爬虫学习笔记（2）

urllib2下载网页的几种实现方式

#!/usr/bin/env python
#coding:utf-8
import urllib2
import cookielib


url = "https://www.crummy.com/software/BeautifulSoup/bs4/doc.zh/#beautiful-soup-4-2-0"

def first():
    #直接调用urllib2的urlopen方法打开
    print "======first====="
    response1 = urllib2.urlopen(url) 
    print response1.getcode()
    print len(response1.read())

def second():
    print "======second====="
    #添加请求头，可以将爬虫伪装成浏览器
    request = urllib2.Request(url)
    request.add_header('user-agent', 'Mozilla/5.0')
    response2 = urllib2.urlopen(url) 
    print response2.getcode()
    print len(response2.read())

def third():
    #添加特殊情景的处理器，大概4种情况，有些网页需要cookie，需要代理，需要https支持，需要重定向。这里是引入cookie的情况。
    print "======third====="
    #创建cookie容器
    cj = cookielib.CookieJar()
    #创建opener
    opener =urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
    #给urllib2安装opener
    urllib2.install_opener(opener)
    response3 = urllib2.urlopen(url) 
    print response3.getcode()
    print cj
    print response3.read()


first()
second()
third()