这里用到一个HTML解析辅助类:HtmlAgilityPack,如果没有网上找一个增加到库里,这个插件有很多版本,如果你开发环境是使用VS2005就2.0的类库,VS2010就使用4.0,以此类推..........然后直接创建一个控制台应用,将我下面的代码COPY替换就可以运行,下面就来讲讲我两年前做爬虫经历,当时是给一家公司做,也是用的C#,不过当时遇到一个头痛的问题就是抓的图片有病毒,然后系统挂了几次。所以抓网站图片要注意安全,虽然我这里没涉及到图片,但是还是提醒下看文章的朋友。
class Program { //存放所有抓取的代理 public static List<proxy> masterPorxyList = new List<proxy>(); //代理IP类 public class proxy { public string ip; public string port; public int speed; public proxy(string pip,string pport,int pspeed) { this.ip = pip; this.port = pport; this.speed = pspeed; } } //抓去处理方法 static void getProxyList(object pageIndex) { string urlCombin = "http://bin, "UTF8"); HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument(); doc.LoadHtml(catchHtml); HtmlNode table = doc.DocumentNode.SelectSingleNode("//div[@id='wrapper']//div[@id='body']/table[1]"); HtmlNodeCollection collectiontrs = table.SelectNodes("./tr"); for (int i = 0; i < collectiontrs.Count; i++) { HtmlAgilityPack.HtmlNode itemtr = collectiontrs[i]; HtmlNodeCollection collectiontds = itemtr.ChildNodes; //table中第一个是能用的代理标题,所以这里从第二行TR开始取值 if (i>0) { HtmlNode itemtdip = (HtmlNode)collectiontds[3]; HtmlNode itemtdport = (HtmlNode)collectiontds[5]; HtmlNode itemtdspeed = (HtmlNode)collectiontds[13]; string ip = itemtdip.InnerText.Trim(); string port = itemtdport.InnerText.Trim(); string speed = itemtdspeed.InnerHtml; int beginIndex = speed.IndexOf(":", 0, speed.Length); int endIndex = speed.IndexOf("%", 0, speed.Length); int subSpeed = int.Parse(speed.Substring(beginIndex + 1, endIndex - beginIndex - 1)); //如果速度展示条的值大于90,表示这个代理速度快。 if (subSpeed > 90) { proxy temp = new proxy(ip, port, subSpeed); masterPorxyList.Add(temp); Console.WriteLine("当前是第:" + masterPorxyList.Count.ToString() + "个代理IP"); } } } } //抓网页方法 static string catchProxIpMethord(string url,string encoding ) { string htmlStr = ""; try { if (!String.IsNullOrEmpty(url)) { WebRequest request = WebRequest.Create(url); WebResponse response = request.GetResponse(); Stream datastream = response.GetResponseStream(); Encoding ec = Encoding.Default; if (encoding == "UTF8") { ec = Encoding.UTF8; } else if (encoding == "Default") { ec = Encoding.Default; } StreamReader reader = new StreamReader(datastream, ec); htmlStr = reader.ReadToEnd(); reader.Close(); datastream.Close(); response.Close(); } } catch { } return htmlStr; } static void Main(string[] args) { //多线程同时抓15页 for (int i = 1; i <= 15; i++) { ThreadPool.QueueUserWorkItem(getProxyList, i); } Console.Read(); } }
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持。