多线程下载图片为什么我查看图片提示图片已经损坏。。

tanaichuan 2013-07-15 06:00:00

程序在运行的时候会有图片查看是损坏，然后运行完毕所有图片都没有了。。。





using System;

using System.Collections.Generic;

using System.Linq;

using System.Web;

using System.Web.UI;

using System.Web.UI.WebControls;

using System.Net;

using System.Text;

using System.Collections;

using System.Text.RegularExpressions;

using System.Threading;

namespace TacCs2013.Caiji

{

    public partial class Caiji : System.Web.UI.Page

    {

        protected void Page_Load(object sender, EventArgs e)

        {

            if (!IsPostBack)

            {



            }

        }



        protected void btnOK_Click(object sender, EventArgs e)

        {









     





            //  取得输入的URL地址 

             string PageUrl = txtUrl.Text;

            WebClient wc = new WebClient();

            //把已登录的用户或正被模拟的用户的用户凭据赋给用于对向Internet资源的请求进行身份验证的网络凭据 

            wc.Credentials = CredentialCache.DefaultCredentials;

            ///从指定的URI下载数据 

            Byte[] pageData = wc.DownloadData(PageUrl);

            //把下载到的字符型数组数据转换成字符串类型 

            // lblc.Text = Encoding.UTF8.GetString(pageData); 

            string sHTML = Encoding.UTF8.GetString(pageData);



            //取得网站路径

            ArrayList alURL = GetHyperLinks(sHTML);//取得所有网站链接

            string sUrl = "";//网站链接路径

            int alurlcount = alURL.Count;//共有多少链接路径。创建多少个线程

            countUl.Text = "共有" + alurlcount + "条路径。";

            Thread[] thurl = new Thread[alurlcount];

            string urlName = "";

            for (int i = 0; i < alURL.Count; i++)

            {

                sUrl = alURL[i].ToString();

                urlName += "||" + sUrl;

                thurl[i] = new Thread(new ParameterizedThreadStart(delegate { images(htmls(sUrl), sUrl); }));

                thurl[i].Start();



            }



        







             lblurlname.Text = urlName;



        }



  







        /// <summary>

        /// 取得网站源码

        /// </summary>

        /// <param name="urlName">要获取的网站</param>

        /// <returns>返回源码</returns>

        public string htmls(string urlName)

        {

            //取得输入的URL地址 

            string PageUrl = txtUrl.Text;

            WebClient wc = new WebClient();

            //把已登录的用户或正被模拟的用户的用户凭据赋给用于对向Internet资源的请求进行身份验证的网络凭据 

            wc.Credentials = CredentialCache.DefaultCredentials;

            ///从指定的URI下载数据 

            Byte[] pageData = wc.DownloadData(PageUrl);

            //把下载到的字符型数组数据转换成字符串类型 

            // lblc.Text = Encoding.UTF8.GetString(pageData); 

            string sHTML = Encoding.UTF8.GetString(pageData);



            return sHTML;

        }

        /// <summary>

        /// 取得网站图片

        /// </summary>

        /// <param name="shtml">网站源码</param>

        /// <param name="PageUrl">当前网站地址</param>

        public void images(string sHTML, string PageUrl)

        {



            //取得网站图片路径

            string imageurl = "";

            string[] Simages = GetHtmlImageUrlList(sHTML);



            int cg = 0;//成功多少张图片

            string fromURL = "";

            lblc.Text = "共有：" + Simages.Length + "张图片。";

            WebClient myWebClient = new WebClient();











            string savePath = "";//图片路径

            string filetac = @"D:\\caiji\\";//文件路径

            for (int i = 0; i < Simages.Length; i++)

            {



                imageurl = Simages[i].ToString();

                //存入图片

                fromURL = "http://www.baidu.com/img/lm.gif";

                if (imageurl.Length > 7)

                {

                    if (imageurl.ToString().Substring(0, 7) != "http://")

                    {

                        if (imageurl.Substring(0, 2) == "..")

                            imageurl = imageurl.Substring(2, imageurl.Length - 2);

                        else if (imageurl.Substring(0, 1) != "/")

                            imageurl = "/" + imageurl;



                        fromURL = PageUrl + imageurl;

                    }



                    else

                        fromURL = imageurl;

                }

                else

                {

                    fromURL = imageurl;

                }

              

              



                try

                {

                 string fileName = imageurl.Substring(imageurl.LastIndexOf("/"));

                 fileName = new DateTime().Millisecond + fileName.Substring(1, fileName.Length - 1);

                    savePath = Server.MapPath(fileName);

                    cg++;

                    myWebClient.DownloadFile(fromURL, filetac + fileName);

                }

                catch (Exception ex)

                {

                    continue;

                }

                finally

                {



                    myWebClient.Dispose();

                }









            }



            lblcg.Text = "成功了：" + cg + "张图片。其中" + (Simages.Length - cg) + "张图片路径不符。跳出了下载！";

            lblImageURL.Text = "图片路径为：" + filetac;

        }



        //遍历网站的链接

        public ArrayList GetHyperLinks(string htmlCode)

        {

            ArrayList al = new ArrayList();



            string strRegex = @"http://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?";



            Regex r = new Regex(strRegex, RegexOptions.IgnoreCase);

            MatchCollection m = r.Matches(htmlCode);



            for (int i = 0; i <= m.Count - 1; i++)

            {

                bool rep = false;

                string strNew = m[i].ToString();



                // 过滤重复的URL 

                foreach (string str in al)

                {

                    if (strNew == str)

                    {

                        rep = true;

                        break;

                    }

                }



                if (!rep) al.Add(strNew);

            }



            al.Sort();



            return al;

        }



        /// <summary>

        /// 取得HTML中所有图片的 URL。

        /// </summary>

        /// <param name="sHtmlText">HTML代码</param>

        /// <returns>图片的URL列表</returns>

        public static string[] GetHtmlImageUrlList(string sHtmlText)

        {

            // 定义正则表达式用来匹配 img 标签

            Regex regImg = new Regex(@"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);



            // 搜索匹配的字符串

            MatchCollection matches = regImg.Matches(sHtmlText);



            int i = 0;

            string[] sUrlList = new string[matches.Count];



            // 取得匹配项列表

            foreach (Match match in matches)

                sUrlList[i++] = match.Groups["imgUrl"].Value;



            return sUrlList;

        }



        //取得网站迅雷下载连接

        public static string[] GetHtmlXunlei(string sHtmlText)

        {





            // 定义正则表达式用来匹配 img 标签

            Regex regImg = new Regex(@"/^thunder:\/\//", RegexOptions.IgnoreCase);



            // 搜索匹配的字符串

            MatchCollection matches = regImg.Matches(sHtmlText);



            int i = 0;

            string[] sUrlList = new string[matches.Count];



            // 取得匹配项列表

            foreach (Match match in matches)

                sUrlList[i++] = match.Groups["imgUrl"].Value;



            return sUrlList;

        }





    }

}