這里用到一個(gè)HTML解析輔助類(lèi):HtmlAgilityPack,如果沒(méi)有網(wǎng)上找一個(gè)增加到庫(kù)里,這個(gè)插件有很多版本,如果你開(kāi)發(fā)環(huán)境是使用VS2005就2.0的類(lèi)庫(kù),VS2010就使用4.0,以此類(lèi)推..........然后直接創(chuàng)建一個(gè)控制臺(tái)應(yīng)用,將我下面的代碼COPY替換就可以運(yùn)行,下面就來(lái)講講我兩年前做爬蟲(chóng)經(jīng)歷,當(dāng)時(shí)是給一家公司做,也是用的C#,不過(guò)當(dāng)時(shí)遇到一個(gè)頭痛的問(wèn)題就是抓的圖片有病毒,然后系統(tǒng)掛了幾次。所以抓網(wǎng)站圖片要注意安全,雖然我這里沒(méi)涉及到圖片,但是還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類(lèi) 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; } } //抓去處理方法 static void getProxyList(object pageIndex) { string urlCombin = "http://www.xicidaili.com/wt/" + pageIndex.ToString(); string catchHtml = catchProxIpMethord(urlCombin, "UTF8"); HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument(); doc.LoadHtml(catchHtml); HtmlNode table = doc.DocumentNode.SelectSingleNode("http://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中第一個(gè)是能用的代理標(biāo)題,所以這里從第二行TR開(kāi)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)); //如果速度展示條的值大于90,表示這個(gè)代理速度快。 if (subSpeed > 90) { proxy temp = new proxy(ip, port, subSpeed); masterPorxyList.Add(temp); Console.WriteLine("當(dāng)前是第:" + masterPorxyList.Count.ToString() + "個(gè)代理IP"); } } } } //抓網(wǎng)頁(yè)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) { //多線(xiàn)程同時(shí)抓15頁(yè) for (int i = 1; i <= 15; i++) { ThreadPool.QueueUserWorkItem(getProxyList, i); } Console.Read(); } }以上就是本文的全部?jī)?nèi)容,希望對(duì)大家的學(xué)習(xí)有所幫助,也希望大家多多支持武林網(wǎng)。
新聞熱點(diǎn)
疑難解答
圖片精選
網(wǎng)友關(guān)注