如何获取HTML页面中的图片地址并将图片下载保存到自己的网站目录？

　　做文章类的网站，难免存在抄袭或修改别人的文章，占为己有的可能！

　　并非是偷者有罪，而是奉行拿来主义；毕竟个人的观点和学问都有所限制，不可能面面俱到；拿别人的不等于偷，更有可能的就是，在别人的基础之上在进行升华，以求精益求精！

　　为此，众多站长可能遇到过，“抄袭”别人的网站的时候，存在图片，如何将其自动保存到自己网站的目录呢？

　　以下为网上抄的源代码！

using System;
using System.Text;
using System.Text.RegularExpressions;
using System.IO;

namespace zhang.Common
{
    public class HanlerFiles
    {
        private string[] GetImgTag(string htmlStr)
        {
            Regex regObj = new Regex("<img.+?>", RegexOptions.Compiled | RegexOptions.IgnoreCase);
            string[] strAry = new string[regObj.Matches(htmlStr).Count];
            int i = 0;
            foreach (Match matchItem in regObj.Matches(htmlStr))
            {
                strAry[i] = GetImgUrl(matchItem.Value);
                i++;
            }
            return strAry;
        }

        private string GetImgUrl(string imgTagStr)
        {
            string str = "";
            Regex regObj = new Regex("http://.+.(?:jpg|gif|bmp|png)", RegexOptions.Compiled | RegexOptions.IgnoreCase);
            foreach (Match matchItem in regObj.Matches(imgTagStr))
            {
                str = matchItem.Value;
            }
            return str;
        }

        /**//// <summary>
        /// 根椐Html内空自动识别图像文件,并下载到服务器指定目录
        /// </summary>
        /// <param name="strHTML"></param>
        /// <param name="path"></param>
        /// <returns></returns>
        public int SaveUrlPics(ref string strHTML, string path)
        {
            string[] imgurlAry = GetImgTag(strHTML);
            try
            {
                for (int i = 0; i < imgurlAry.Length; i++)
                {
                    //WebRequest req = WebRequest.Create(imgurlAry[i]);
                    string preStr = System.DateTime.Now.ToString() + "_";
                    preStr = preStr.Replace("-", "");
                    preStr = preStr.Replace(":", "");
                    preStr = preStr.Replace(" ", "");
                    WebClient wc = new WebClient();
                    wc.DownloadFile(imgurlAry[i], HttpContext.Current.Server.MapPath(path) + "/" + preStr + imgurlAry[i].Substring(imgurlAry[i].LastIndexOf("/") + 1));
                    strHTML = strHTML.Replace(imgurlAry[i], path + preStr + imgurlAry[i].Substring(imgurlAry[i].LastIndexOf("/") + 1));
                }
               
            }
            catch (Exception ex)
            {
                //return ex.Message;
            }
            return imgurlAry.Length;
        }

    }
}

Copyright ＠ 2007-2012 敏韬网(敏而好学，文韬武略--MinTao.Net)（学习笔记） Inc All Rights Reserved.
闵涛 E_mail:admin@mintao.net(欢迎提供学习资源)

鄂公网安备 42011102001154号

站长：MinTao ICP备案号：鄂ICP备11006601号-18