国产探花免费观看_亚洲丰满少妇自慰呻吟_97日韩有码在线_资源在线日韩欧美_一区二区精品毛片,辰东完美世界有声小说,欢乐颂第一季,yy玄幻小说排行榜完本

首頁(yè) > 編程 > .NET > 正文

asp.net 抓取網(wǎng)頁(yè)源碼三種實(shí)現(xiàn)方法

2024-07-10 12:45:18
字體:
來(lái)源:轉(zhuǎn)載
供稿:網(wǎng)友

方法1 比較推薦  

/// <summary>       /// 用HttpWebRequest取得網(wǎng)頁(yè)源碼      /// 對(duì)于帶BOM的網(wǎng)頁(yè)很有效,不管是什么編碼都能正確識(shí)別      /// </summary>      /// <param name="url">網(wǎng)頁(yè)地址" </param>      /// <returns>返回網(wǎng)頁(yè)源文件</returns>      public static string GetHtmlSource2(string url)    {      //處理內(nèi)容        string html = "";      HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);      request.Accept = "*/*"; //接受任意文件      request.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.1.4322)"; // 模擬使用IE在瀏覽 http://www.52mvc.com      request.AllowAutoRedirect = true;//是否允許302      //request.CookieContainer = new CookieContainer();//cookie容器,      request.Referer = url; //當(dāng)前頁(yè)面的引用        HttpWebResponse response = (HttpWebResponse)request.GetResponse();      Stream stream = response.GetResponseStream();      StreamReader reader = new StreamReader(stream, Encoding.Default);      html = reader.ReadToEnd();      stream.Close();        return html;    }

方法2 

using System;using System.Collections.Generic;using System.Linq;using System.Web;using System.IO;using System.Text;using System.Net;namespace MySql{  public class GetHttpData  {    public static string GetHttpData2(string Url)    {      string sException = null;      string sRslt = null;      WebResponse oWebRps = null;      WebRequest oWebRqst = WebRequest.Create(Url);      oWebRqst.Timeout = 50000;      try      {        oWebRps = oWebRqst.GetResponse();      }      catch (WebException e)      {        sException = e.Message.ToString();      }      catch (Exception e)      {        sException = e.ToString();       }      finally      {        if (oWebRps != null)        {           StreamReader oStreamRd = new StreamReader(oWebRps.GetResponseStream(), Encoding.GetEncoding("utf-8"));          sRslt = oStreamRd.ReadToEnd();          oStreamRd.Close();          oWebRps.Close();        }      }       return sRslt;    }   }}

方法3

public static string getHtml(string url, params string [] charSets)//url是要訪問(wèn)的網(wǎng)站地址,charSet是目標(biāo)網(wǎng)頁(yè)的編碼,如果傳入的是null或者"",那就自動(dòng)分析網(wǎng)頁(yè)的編碼  {    try    {      string charSet = null;      if (charSets.Length == 1) {        charSet = charSets[0];      }      WebClient myWebClient = new WebClient(); //創(chuàng)建WebClient實(shí)例myWebClient      // 需要注意的:      //有的網(wǎng)頁(yè)可能下不下來(lái),有種種原因比如需要cookie,編碼問(wèn)題等等      //這是就要具體問(wèn)題具體分析比如在頭部加入cookie      // webclient.Headers.Add("Cookie", cookie);      //這樣可能需要一些重載方法。根據(jù)需要寫就可以了        //獲取或設(shè)置用于對(duì)向 Internet 資源的請(qǐng)求進(jìn)行身份驗(yàn)證的網(wǎng)絡(luò)憑據(jù)。      myWebClient.Credentials = CredentialCache.DefaultCredentials;      //如果服務(wù)器要驗(yàn)證用戶名,密碼      //NetworkCredential mycred = new NetworkCredential(struser, strpassword);      //myWebClient.Credentials = mycred;      //從資源下載數(shù)據(jù)并返回字節(jié)數(shù)組。(加@是因?yàn)榫W(wǎng)址中間有"/"符號(hào))      byte[] myDataBuffer = myWebClient.DownloadData(url);      string strWebData = Encoding.Default.GetString(myDataBuffer);        //獲取網(wǎng)頁(yè)字符編碼描述信息      Match charSetMatch = Regex.Match(strWebData, "<meta([^<]*)charset=([^<]*)/"", RegexOptions.IgnoreCase | RegexOptions.Multiline);      string webCharSet = charSetMatch.Groups[2].Value;      if (charSet == null || charSet == "")        charSet = webCharSet;        if (charSet != null && charSet != "" && Encoding.GetEncoding(charSet) != Encoding.Default)      {        strWebData = Encoding.GetEncoding(charSet).GetString(myDataBuffer);      }      else {        strWebData = Encoding.GetEncoding("utf-8").GetString(myDataBuffer);      }      return strWebData;    }    catch (Exception e) { return ""; }  }            
發(fā)表評(píng)論 共有條評(píng)論
用戶名: 密碼:
驗(yàn)證碼: 匿名發(fā)表
主站蜘蛛池模板: 革吉县| 吉安县| 成武县| 太仓市| 宜兰市| 永济市| 广丰县| 宁夏| 遂平县| 二连浩特市| 平和县| 镇沅| 平乡县| 黄骅市| 离岛区| 阿坝| 大关县| 巴中市| 万盛区| 宁化县| 霍林郭勒市| 建瓯市| 新邵县| 株洲市| 平谷区| 安多县| 图木舒克市| 章丘市| 长葛市| 广河县| 宣武区| 延庆县| 凤山县| 福贡县| 冕宁县| 开化县| 榆中县| 原平市| 沈阳市| 徐州市| 全椒县|