java如何建立爬虫代理ip池

这篇文章主要介绍了java如何建立爬虫代理ip池，具有一定借鉴价值，感兴趣的朋友可以参考下，希望大家阅读完这篇文章之后大有收获，下面让小编带着大家一起了解一下。

步骤说明

1、要从提供代理ip的网站上抓取ip。

2、初步过滤捕获的ip。例如，从一开始就过滤IP类型不是HTTPS，IP链接速度超过2秒。

3、对于符合要求的IP，进行质量检查，判断是否可用。这一步是检查IP的质量，也就是说这一步刷掉了很多IP。

4、将符合要求的ip写入Redis数据库，并以List形式存储在Redis中。

5、设置一个抓取周期来更新您的IP代理池(抓取并处理新的IP后，我们清空原始数据库，并将新的IP写入其中)

实例

#!/usr/bin/env python3# -*- coding: utf-8 -*-import requests,threading,datetimefrom bs4 import BeautifulSoupimport random """1、抓取代理网站的代理ip2、并根据指定的目标url,对抓取到ip的有效性进行验证3、最后存到指定的path""" # ------------------------------------------------------文档处理--------------------------------------------------------# 写入文档def write(path,text):    with open(path,'a', encoding='utf-8') as f:        f.writelines(text)        f.write('\n')# 清空文档def truncatefile(path):    with open(path, 'w', encoding='utf-8') as f:        f.truncate()# 读取文档def read(path):    with open(path, 'r', encoding='utf-8') as f:        txt = []        for s in f.readlines():            txt.append(s.strip())    return txt# ----------------------------------------------------------------------------------------------------------------------# 计算时间差,格式: 时分秒def gettimediff(start,end):    seconds = (end - start).seconds    m, s = divmod(seconds, 60)    h, m = divmod(m, 60)    diff = ("d:d:d" % (h, m, s))    return diff# ----------------------------------------------------------------------------------------------------------------------# 返回一个随机的请求头 headersdef getheaders():    user_agent_list = [ \        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" \        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", \        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", \        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", \        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", \        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", \        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", \        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"    ]    UserAgent=random.choice(user_agent_list)    headers = {'User-Agent': UserAgent}    return headers# -----------------------------------------------------检查ip是否可用----------------------------------------------------def checkip(targeturl,ip):    headers =getheaders()  # 定制请求头    proxies = {"http": "http://"+ip, "https": "http://"+ip}  # 代理ip    try:        response=requests.get(url=targeturl,proxies=proxies,headers=headers,timeout=5).status_code        if response == 200 :            return True        else:            return False    except:        return False #-------------------------------------------------------获取代理方法----------------------------------------------------# 免费代理 XiciDailidef findip(type,pagenum,targeturl,path): # ip类型,页码,目标url,存放ip的路径    list={'1': 'http://www.xicidaili.com/nt/', # xicidaili国内普通代理          '2': 'http://www.xicidaili.com/nn/', # xicidaili国内高匿代理          '3': 'http://www.xicidaili.com/wn/', # xicidaili国内https代理          '4': 'http://www.xicidaili.com/wt/'} # xicidaili国外http代理    url=list[str(type)]+str(pagenum) # 配置url    headers = getheaders() # 定制请求头    html=requests.get(url=url,headers=headers,timeout = 5).text    soup=BeautifulSoup(html,'lxml')    all=soup.find_all('tr',class_='odd')    for i in all:        t=i.find_all('td')        ip=t[1].text+':'+t[2].text        is_avail = checkip(targeturl,ip)        if is_avail == True:            write(path=path,text=ip)            print(ip) #-----------------------------------------------------多线程抓取ip入口---------------------------------------------------def getip(targeturl,path):     truncatefile(path) # 爬取前清空文档     start = datetime.datetime.now() # 开始时间     threads=[]     for type in range(4):   # 四种类型ip,每种类型取前三页,共12条线程         for pagenum in range(3):             t=threading.Thread(target=findip,args=(type+1,pagenum+1,targeturl,path))             threads.append(t)     print('开始爬取代理ip')     for s in threads: # 开启多线程爬取         s.start()     for e in threads: # 等待所有线程结束         e.join()     print('爬取完成')     end = datetime.datetime.now() # 结束时间     diff = gettimediff(start, end)  # 计算耗时     ips = read(path)  # 读取爬到的ip数量     print('一共爬取代理ip: %s 个,共耗时: %s \n' % (len(ips), diff)) #-------------------------------------------------------启动-----------------------------------------------------------if __name__ == '__main__':    path = 'ip.txt' # 存放爬取ip的文档path    targeturl = 'http://www.cnblogs.com/TurboWay/' # 验证ip有效性的指定url    getip(targeturl,path)

感谢你能够认真阅读完这篇文章，希望小编分享的"java如何建立爬虫代理ip池"这篇文章对大家有帮助，同时也希望大家多多支持，关注行业资讯频道，更多相关知识等着你来学习!