通過URL取得網頁內容

来源：互联网发布：淘宝小二旺旺怎么识别编辑：程序博客网时间：2024/05/23 18:04

using System;
using System.IO;
using System.Net;
using System.Text;

namespace WebDB.Common.Mail
{
    /// <summary>
    /// 取得網頁內容類別
    /// </summary>
    public sealed class PageContent
    {
        private static PageContent content = null;

        /// <summary>
        /// 設定編碼為 UTF8
        /// </summary>
        private Encoding coding = Encoding.UTF8;

       /// <summary>
        /// 取得指定網頁內容
        /// </summary>
        /// <param name="strUrl">要擷取內容的網址</param>
        /// <returns>網頁內容</returns>
        public string GetHtml(string strUrl)
        {
            StringBuilder sbContent = new StringBuilder();

WebResponse resp = null;

StreamReader sr = null;

            try
            {
                Uri uri = new Uri(strUrl);

WebRequest req = WebRequest.Create(uri);

//req.PreAuthenticate = true;

// 使用預設認證機制(Windows 憑證)
req.Credentials = CredentialCache.DefaultCredentials;

req.Proxy = WebRequest.DefaultWebProxy;

resp = req.GetResponse();

Stream stream = resp.GetResponseStream();

sr = new StreamReader(stream, coding);

string strTmp = "";

                while ((strTmp = sr.ReadLine()) != null)
                {
                    sbContent.Append(strTmp.Trim());
                }
            }
            catch (Exception e)
            {
                 throw new ArgumentException("取得網頁內容有誤！", e);
            }
            finally
            {
                if (sr != null)
                {
                    sr.Close();
                }

                if (resp != null)
                {
                    resp.Close();
                }
            }

return sbContent.ToString();
}