代理的IP通過去網上找
# -*- 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)
#設置代理ip
proxy = {‘http‘:‘1.60.114.151:6673‘}# 這裏的HTTPS 後寫啥都可以訪問，可能是還用自己的ip去訪問
proxy_support = ProxyHandler(proxy)
opener = build_opener(proxy_support)
#設置訪問http協議頭,模擬瀏覽器
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)

學習爬蟲的day03 (通過代理去爬去數據)