学习爬虫的day03 (通过代理去爬去数据)

代理的IP通过去网上找
# -*- coding: utf-8 -*-
import re
import _thread
from time import sleep, ctime
from urllib.request import urlopen
from urllib.request import Request
from urllib.request import ProxyHandler
from urllib.request import build_opener
from lxml import etree

url = "http://sou.zhaopin.com/jobs/searchresult.ashx?jl=%%E5%%8C%%97%%E4%%BA%%AC&kw=java&sm=0&p=%i"%(1)
#设置代理ip
proxy = {'http':'1.60.114.151:6673'}# 这里的HTTPS 后写啥都可以访问，可能是还用自己的ip去访问
proxy_support = ProxyHandler(proxy)
opener = build_opener(proxy_support)
#设置访问http协议头,模拟浏览器
opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6')]
r = opener.open(url)
html = r.read().decode('utf-8')
print(html)