多线程爬取CSDN博客 并使用代理

代码如下：

import re
import urllib.error
import urllib.request
import threading
import time
import random

def use_proxy(url,proxy_addr):
	#建立请求头并设为全局变量opener
    proxy=urllib.request.ProxyHandler({"http":proxy_addr})
    opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandler)
    urllib.request.install_opener(opener)
    
    #模拟浏览器的操作
    headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'
    }
    request = urllib.request.Request(url=url, headers=headers)
	
	#获取返回信息
    data=urllib.request.urlopen(url).read().decode("utf-8","ignore")
    pat = re.compile(r'
(.*?)
', re.S)
    data = pat.findall(data)
    return data


class Onr(threading.Thread):#新建Onr线程类
    def __init__(self):
        threading.Thread.__init__(self)
    def run(self):
    	#奇数页爬取
        for i in range(1,20,2):
            try:
            #构建页面的url
                url="https://so.csdn.net/so/search/s.do?p="+str(i)+"&q=ios&t=blog&domain=&o=&s=&u=&l=&rbg=0"
                # pagedata=urllib.request.urlopen(url).read().decode()
                data=use_proxy(url,"1.198.72.44:9999")
                print("第"+str(i)+"页段子是："+str(data))
                span = round(random.random() * 6, 1)
                time.sleep(span)
            except urllib.error.URLError as e:
            	#*except urllib2.HTTPError, e:
				 # print e.code
				#except urllib2.URLError, e:
				 # print e.reason*
				 #下面两个if作用和上面注释的代码作用相同，判断错误属性
                if hasattr(e,"code"):
                    print(e.code)
                if hasattr(e,"reason"):
                    print(e.reason)
                time.sleep(2)
		 except Exception as e:
		         print("exception" + str(e))
		         time.sleep(1)


class Two(threading.Thread):#新建Two 线程类
    def __init__(self):
        threading.Thread.__init__(self)
    def run(self):
    	#访问偶数页
        for i in range(2,20,2):
            try:
            	#构建页面的url
                url = "https://so.csdn.net/so/search/s.do?p=" + str(i) + "&q=ios&t=blog&domain=&o=&s=&u=&l=&rbg=0"
                # pagedata=urllib.request.urlopen(url).read().decode()
                data = use_proxy(url, "1.198.72.44:9999")
                print("第" + str(i) + "页段子是：" + str(data))
                span = round(random.random() * 6, 1)
                time.sleep(span)
            except urllib.error.URLError as e:
                    if hasattr(e, "code"):
                        print(e.code)
                    if hasattr(e, "reason"):
                        print(e.reason)
                    time.sleep(2)
            except Exception as e:
		                print("exception" + str(e))
		                time.sleep(1)

#建立线程
one=Onr()
two=Two()
#开始线程
one.start()
two.start()