asp.net 抓取網頁源碼三種實現方法

方法1 比較推薦

複製代碼 代碼如下:/// <summary>

/// 用HttpWebRequest取得網頁源碼
/// 對於帶BOM的網頁很有效，不管是什麼編碼都能正確識別
/// </summary>
/// <param name="url">網頁地址" </param>
/// <returns>返回網頁源檔案</returns>
public static string GetHtmlSource2(string url)
{
//處理內容
string html = "";
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
request.Accept = "*/*"; //接受任意檔案
request.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.1.4322)"; // 類比使用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; //當前頁面的引用

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

複製代碼 代碼如下: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複製代碼 代碼如下: public static string getHtml(string url, params string [] charSets)//url是要訪問的網站地址，charSet是目標網頁的編碼，如果傳入的是null或者""，那就自動分析網頁的編碼
{
try
{
string charSet = null;
if (charSets.Length == 1) {
charSet = charSets[0];
}
WebClient myWebClient = new WebClient(); //建立WebClient執行個體myWebClient
// 需要注意的：
//有的網頁可能下不下來，有種種原因比如需要cookie,編碼問題等等
//這是就要具體問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。根據需要寫就可以了

//擷取或設定用於對向 Internet 資源的請求進行身分識別驗證的網路憑據。
myWebClient.Credentials = CredentialCache.DefaultCredentials;
//如果伺服器要驗證使用者名稱,密碼
//NetworkCredential mycred = new NetworkCredential(struser, strpassword);
//myWebClient.Credentials = mycred;
//從資源下載資料並返回位元組數組。（加@是因為網址中間有"/"符號）
byte[] myDataBuffer = myWebClient.DownloadData(url);
string strWebData = Encoding.Default.GetString(myDataBuffer);

//擷取網頁字元編碼描述資訊
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 ""; }
}