小编给大家分享一下c#如何批量抓取免费代理并且验证有效性，相信大部分人都还不怎么了解，因此分享这篇文章给大家参考一下，希望大家阅读完这篇文章后大有收获，下面让我们一起去了解一下吧！
1.从哪些网页上可以抓取免费的代理IP？
百度一下“免费代理ip”挺多的。
2.代理IP稳定吗？有什么作用？
这种免费的代理ip时效性和有效性都不强，上面这三个免费的代理网站，时效性大概在十几秒到1个小时不等，一般需要自己处理验证后使用，提高命中率。可适用于隐藏网页IP（有些网站还不准使用代理ip，比如豆瓣，其实挺尴尬的，内容这么贵吗），一般常用于空间留言、刷网站流量、网赚任务、批量注册账号等，只要没有其他限制，需要频繁更换ip都可以使用。
3.ping通IP就是有效的吗？如何验证代理是否有效
好吧，这有点废话，进行端口测试才是最有效的，能ping通并不代表代理有效，不能平通也不一定代理不可用。可以使用HttpWebRequest，也可以使用Scoket，当然HttpWebRequest比Socket连接代理ip、port要慢。
4.一次提取多少代理合适？
代理ip时效性不强、并且有效性也不高，所以只能从一些代理ip的网站上批量定时去获取，有的代理在一分钟内使用是有限制的，所以说限制比较多。
5.http代理和https代理有什么区别？
需要访问https的网站就需要使用https代理了，比如百度，需要访问http的代理，可以使用http。这个并不是100%的。
检测代理ip有效性步骤如下：
1.使用HttpWebRequest、HttpWebResponse请求代理ip的网页，获取包含代理的网页内容
2.使用HtmlAgilityPack或者正则表达式对抓取的内容进行截取，保存到代理集合
3.拿到代理集合，多线程发起http请求，比如访问百度，是否成功，成功则存到Redis里面。
效果图如下：
使用HttpWebRequest发起请求
Request.cs如下，主要就是两个方法，一个方法是验证代理ip是否有效，设置HttpWebRequest的Proxy属性，请求百度，看到有些文章大多数会获取响应的内容，如果内容符合请求的网址则证明代理哟有效，实际上根据HttpStatusCode 200就可以判断是否验证有效。
【注意】建的是控制台程序，使用了异步，所以还是建.net core吧，c#语言的版本7.1。C#如何在控制台程序中使用异步
计算
安全
数据库
网络和加速
企业服务
public class Request
{
/// <summary>
/// 验证代理ip有效性
/// </summary>
/// <param name="proxyIp">代理IP</param>
/// <param name="proxyPort">代理IP 端口</param>
/// <param name="timeout">详情超时</param>
/// <param name="url">请求的地址</param>
/// <param name="success">成功的回调</param>
/// <param name="fail">失败的回调</param>
/// <returns></returns>
public static async System.Threading.Tasks.Task getAsync(string proxyIp,int proxyPort, int timeout,string url, Action success, Action<string> fail)
{
System.GC.Collect();
HttpWebRequest request = null;
HttpWebResponse response = null;
try
{
request = (HttpWebRequest)WebRequest.Create(url);
//HttpWebRequest request = HttpWebRequest.CreateHttp(url);
request.Timeout =timeout;
request.KeepAlive = false;
request.Proxy = new WebProxy(proxyIp,proxyPort);
response = await request.GetResponseAsync() as HttpWebResponse;
if (response.StatusCode == HttpStatusCode.OK)
{
success();
}
else
{
fail(response.StatusCode+":"+response.StatusDescription);
}
}
catch (Exception ex)
{
fail("请求异常"+ex.Message.ToString());
}
finally
{
if (request != null)
{
request.Abort();
request = null;
}
if (response != null)
{
response.Close();
}
}
}
/// <summary>
/// 发起http请求
/// </summary>
/// <param name="url"></param>
/// <param name="success">成功的回调</param>
/// <param name="fail">失败的回调</param>
public static void get(string url,Action<string> success,Action<string> fail)
{
StreamReader reader = null;
Stream stream = null;
WebRequest request = null;
HttpWebResponse response = null;
try
{
request = WebRequest.Create(url);
request.Timeout = 2000;
response = (HttpWebResponse)request.GetResponse();
if (response.StatusCode == HttpStatusCode.OK)
{
stream = response.GetResponseStream();
reader = new StreamReader(stream);
string result = reader.ReadToEnd();
success(result);
}
else
{
fail(response.StatusCode+":"+response.StatusDescription);
}
}
catch (Exception ex)
{
fail(ex.ToString());
}
finally
{
if (reader != null)
reader.Close();
if (stream != null)
stream.Close();
if(response!=null)
response.Close();
if(request!=null)
request.Abort();
}
}
}抓取免费代理，并检查是否有效
ProxyIpHelper.cs 中主要有四个方法，检查ip是否可用CheckProxyIpAsync、抓取xicidaili.com的代理GetXicidailiProxy、抓取ip3366.net的代理GetIp3366Proxy、抓取66ip.cn的代理GetIp3366Proxy。如果想多抓取几个网站可以多写几个。
public class ProxyIpHelper
{
private static string address_xicidaili = "http://www.xicidaili.com/wn/{0}";
private static string address_66ip = "http://www.66ip.cn/nmtq.php?getnum=20&isp=0&anonymoustype=0&start=&ports=&export=&ipaddress=&area=1&proxytype=1&api=66ip";
private static string address_ip3366 = "http://www.ip3366.net/?stype=1&page={0}";
/// <summary>
/// 检查代理IP是否可用
/// </summary>
/// <param name="ipAddress">ip</param>
/// <param name="success">成功的回调</param>
/// <param name="fail">失败的回调</param>
/// <returns></returns>
public static async Task CheckProxyIpAsync(string ipAddress, Action success, Action<string> fail)
{
int index = ipAddress.IndexOf(":");
string proxyIp = ipAddress.Substring(0, index);
int proxyPort = int.Parse(ipAddress.Substring(index + 1));
await Request.getAsync(proxyIp, proxyPort, 3000, "https://www.baidu.com/", () =>
{
success();
}, (error) =>
{
fail(error);
});
}
/// <summary>
/// 从xicidaili.com网页上去获取代理IP，可以分页
/// </summary>
/// <param name="page"></param>
/// <returns></returns>
public static List<string> GetXicidailiProxy(int page)
{
List<string> list = new List<string>();
for (int p = 1; p <= page; p++)
{
string url = string.Format(address_xicidaili, p);
Request.get(url,(docText)=> {
if (!string.IsNullOrWhiteSpace(docText))
{
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(docText);
var trNodes = doc.DocumentNode.SelectNodes("//table[@id='ip_list']")[0].SelectNodes("./tr");
if (trNodes != null && trNodes.Count > 0)
{
for (int i = 1; i < trNodes.Count; i++)
{
var tds = trNodes[i].SelectNodes("./td");
string ipAddress = tds[1].InnerText + ":" + int.Parse(tds[2].InnerText); ;
list.Add(ipAddress);
}
}
}
},(error)=> {
Console.WriteLine(error);
});
}
return list;
}
/// <summary>
/// 从ip3366.net网页上去获取代理IP，可以分页
/// </summary>
/// <param name="page"></param>
/// <returns></returns>
public static List<string> GetIp3366Proxy(int page)
{
List<string> list = new List<string>();
for (int p = 1; p <= page; p++)
{
string url = string.Format(address_ip3366, p);
Request.get(url, (docText) => {
if (!string.IsNullOrWhiteSpace(docText))
{
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(docText);
var trNodes1 = doc.DocumentNode.SelectNodes("//table")[0];
var trNodes2 = doc.DocumentNode.SelectNodes("//table")[0].SelectSingleNode("//tbody");
var trNodes = doc.DocumentNode.SelectNodes("//table")[0].SelectSingleNode("//tbody").SelectNodes("./tr");
if (trNodes != null && trNodes.Count > 0)
{
for (int i = 1; i < trNodes.Count; i++)
{
var tds = trNodes[i].SelectNodes("./td");
if (tds[3].InnerHtml == "HTTPS")
{
string ipAddress = tds[0].InnerText + ":" + int.Parse(tds[1].InnerText); ;
list.Add(ipAddress);
}
}
}
}
}, (error) => {
Console.WriteLine(error);
});
}
return list;
}
/// <summary>
/// 从66ip.cn中去获取，不需要分页
/// </summary>
/// <returns></returns>
public static List<string> Get66ipProxy()
{
List<string> list = new List<string>();
Request.get(address_66ip,
(docText)=> {
int count = 0;
if (string.IsNullOrWhiteSpace(docText) == false)
{
string regex = "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\:\\d{1,5}";
Match mstr = Regex.Match(docText, regex);
while (mstr.Success && count < 20)
{
string tempIp = mstr.Groups[0].Value;
list.Add(tempIp);
mstr = mstr.NextMatch();
count++;
}
}
},
(error)=> {
Console.WriteLine(error);
});
return list;
}
}使用Timer定时抓取，并检查，成功则保存到redis
c#有三种定时器，这里定时器是使用System.Threading命名空间， 这个Timer会开启新的线程，抓取三个网页定义了三个Timer对象。每一次抓取都会保存上一次抓取的集合，检查前，会进行对比，取出新的集合也就是没有重复的那部分。有效性的ip比较低，这里没有做统计，如果代码再优化一下，可以做一下统计，看看程序的主入口吧，最终的实现如下：
class Program
{
static bool timer_ip3366_isCompleted = true;
static bool timer_xicidaili_isCompleted = true;
static bool timer_66ip_isCompleted = true;
static Timer timer_ip3366, timer_xicidaili, timer_66ip;
private static List<string> lastListip3366,lastList66ip,lastListxicidaili;//保存上一次抓取的代理，与下一次进行对比，取新的集合进行检查筛选
static async Task Main(string[] args)
{
System.Net.ServicePointManager.DefaultConnectionLimit = 2000;
Console.WriteLine("hellow proxyIp");
Console.ReadLine();
lastList66ip = new List<string>();
lastListip3366 = new List<string>();
lastListxicidaili = new List<string>();
timer_ip3366 = new Timer(async (state) =>
{
await TimerIp3366Async();
}, "processing timer_ip3366 event", 0,1000*30);
timer_xicidaili = new Timer(async (state) =>
{
await TimerXicidailiAsync();
}, "processing timer_xicidaili event", 0, 1000 * 60);
timer_66ip = new Timer(async (state) =>
{
await Timer66ipAsync();
}, "processing timer_66ip event", 0, 1000*30);
Console.ReadLine();
}
private static async Task Timer66ipAsync()
{
if (timer_66ip_isCompleted)
{
timer_66ip_isCompleted = false;
List<string> checkList = new List<string>();
var listProxyIp = ProxyIpHelper.Get66ipProxy();
if (listProxyIp.Count > 0)
{
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("66ip.cn 抓取到" + listProxyIp.Count + "条记录,正在对比.........");
listProxyIp.ForEach(f =>
{
if (!lastList66ip.Contains(f))
{
checkList.Add(f);
}
});
lastList66ip = listProxyIp;
if (checkList.Count > 0)
{
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("66ip.cn 需要检查" + checkList.Count + "条记录,正在进行检测是否有效..........");
for (int i = 0; i < checkList.Count; i++)
{
string ipAddress = checkList[i];
await ProxyIpHelper.CheckProxyIpAsync(ipAddress, () =>
{
bool insertSuccess = RedisHelper.InsertSet(ipAddress);
Console.ForegroundColor = ConsoleColor.White;
Console.WriteLine("66ip.cn");
if (insertSuccess)
{
Console.WriteLine("success" + ipAddress + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
}
Console.WriteLine("重复插入" + ipAddress + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
}, (error) =>
{
Console.ForegroundColor = ConsoleColor.Green;
Console.WriteLine("66ip.cn");
Console.WriteLine("error:" + ipAddress + error + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
});
}
timer_66ip_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("66ip.cn" + checkList.Count + "条记录,已经检测完成，正在进行下一次检查");
}
else
{
timer_66ip_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("66ip.cn没有需要检查的代理ip");
}
}
else
{
timer_66ip_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("66ip.cn没有获取到代理ip");
}
}
}
private static async Task TimerXicidailiAsync()
{
if (timer_xicidaili_isCompleted)
{
//取出需要检查的ip地址，第一次100条则checklist就是100条记录，
//第二次的100条中只有10是和上一次的不重复，则第二次只需要检查这10条记录
timer_xicidaili_isCompleted = false;
List<string> checkList = new List<string>();
var listProxyIp = ProxyIpHelper.GetXicidailiProxy(1);
if (listProxyIp.Count > 0)
{
Console.WriteLine("xicidaili.com 抓取到" + listProxyIp.Count + "条记录,正在对比............");
listProxyIp.ForEach(f =>
{
if (!lastListxicidaili.Contains(f))
{
checkList.Add(f);
}
});
lastListxicidaili = listProxyIp;
if (checkList.Count > 0)
{
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("xicidaili.com 需要检查" + checkList.Count + "条记录,正在进行检测是否有效..........");
for (int i = 0; i < checkList.Count; i++)
{
string ipAddress = checkList[i];
await ProxyIpHelper.CheckProxyIpAsync(ipAddress, () =>
{
bool insertSuccess = RedisHelper.InsertSet(ipAddress);
Console.ForegroundColor = ConsoleColor.White;
Console.WriteLine("xicidaili.com");
if (insertSuccess)
{
Console.WriteLine("success" + ipAddress + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
}
else
Console.WriteLine("重复插入" + ipAddress + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
}, (error) =>
{
Console.WriteLine("xicidaili.com");
Console.ForegroundColor = ConsoleColor.Red;
Console.WriteLine("error:" + ipAddress + error + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
});
}
timer_xicidaili_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("xicidaili.com" + checkList.Count + "条记录,已经检测完成，正在进行下一次检查");
}
else
{
timer_xicidaili_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("xicidaili.com没有需要检查的代理ip");
}
}
else
{
timer_xicidaili_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("xicidaili.com没有获取到代理ip");
}
}
}
private static async Task TimerIp3366Async()
{
if (timer_ip3366_isCompleted)
{
timer_ip3366_isCompleted = false;
List<string> checkList = new List<string>();
var listProxyIp = ProxyIpHelper.GetIp3366Proxy(4);
if (listProxyIp.Count > 0)
{
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("ip3366.net 抓取到" + listProxyIp.Count + "条记录,正在进行检测是否有效..........");
listProxyIp.ForEach(f =>
{
if (!lastListip3366.Contains(f))
{
checkList.Add(f);
}
});
lastListip3366 = listProxyIp;
if (checkList.Count != 0)
{
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("ip3366.net 需要检查" + checkList.Count + "条记录,正在进行检测是否有效..........");
for (int i = 0; i < checkList.Count; i++)
{
string ipAddress = checkList[i];
await ProxyIpHelper.CheckProxyIpAsync(ipAddress, () =>
{
bool insertSuccess = RedisHelper.InsertSet(ipAddress);
Console.ForegroundColor = ConsoleColor.White;
Console.WriteLine("ip3366.net");
if (insertSuccess)
{
Console.WriteLine("success" + ipAddress + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
}
else
{
Console.ForegroundColor = ConsoleColor.Red;
Console.WriteLine("重复插入" + ipAddress + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
}
}, (error) =>
{
Console.ForegroundColor = ConsoleColor.Yellow;
Console.WriteLine("ip3366.net");
Console.WriteLine("error " + ipAddress + "任务编号:" + i + "当前任务线程:" + Thread.CurrentThread.ManagedThreadId);
});
}
timer_ip3366_isCompleted = true;
Console.WriteLine("ip3366.net" + checkList.Count + "条记录,已经检测完成，正在进行下一次检查");
}
else
{
timer_ip3366_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("ip3366.net没有需要检查的代理ip");
}
}
else
{
timer_ip3366_isCompleted = true;
Console.ForegroundColor = ConsoleColor.DarkCyan;
Console.WriteLine("ip3366.net没有获取到代理ip");
}
}
}
}Redis第三库使用的stackoverflow的 StackExchange.Redis，代理ip不能重复储存，所以采用的数据结构是Set。存的值非常简单就一个ip加上port，也可以存入更多相关信息，感觉没必要。即使有这些其他的信息，也很难发挥作用。RedisHelper.cs如下
public class RedisHelper
{
private static readonly object Locker = new object();
private static ConnectionMultiplexer _redis;
private const string CONNECTTIONSTRING = "127.0.0.1:6379,DefaultDatabase=3";
public const string REDIS_SET_KET_SUCCESS = "set_success_ip";
private static ConnectionMultiplexer Manager
{
get
{
if (_redis == null)
{
lock (Locker)
{
if (_redis != null) return _redis;
_redis = GetManager();
return _redis;
}
}
return _redis;
}
}
private static ConnectionMultiplexer GetManager(string connectionString = null)
{
if (string.IsNullOrEmpty(connectionString))
{
connectionString = CONNECTTIONSTRING;
}
return ConnectionMultiplexer.Connect(connectionString);
}
public static bool InsertSet(string value)
{
var db = Manager.GetDatabase();
return db.SetAdd(REDIS_SET_KET_SUCCESS,value);
}
}以上是“c#如何批量抓取免费代理并且验证有效性”这篇文章的所有内容，感谢各位的阅读！相信大家都有了一定的了解，希望分享的内容对大家有所帮助，如果还想学习更多知识，欢迎关注亿速云行业资讯频道！
亿速云免费服务器限时活动，即开即用、新—代英特尔至强铂金CPU、SSD云盘，0元免费领，库存有限，领完即止！ 点击查看>>点击查看>>
免责声明：本站发布的内容（图片、视频和文字）以原创、转载和分享为主，文章观点不代表本网站立场，如果涉及侵权请联系站长邮箱：is@yisu.com进行举报，并提供相关证据，一经查实，将立刻删除涉嫌侵权内容。
