C # Crawl Web page of img src with parameter image link and download

usingSystem;usingSystem.Collections.Generic;usingSystem.ComponentModel;usingSystem.Data;usingSystem.Drawing;usingSystem.IO;usingSystem.Linq;usingSystem.Net;usingSystem.Text;usingSystem.Text.RegularExpressions;usingSystem.Threading;usingSystem.Windows.Forms;namespaceimagecollection{ Public Partial classForm1:form {Private Static stringPath = AppDomain.CurrentDomain.BaseDirectory +"img";  PublicForm1 () {InitializeComponent (); }        Private voidBtnshuaqu_click (Objectsender, EventArgs e) {            stringURL =Txturl.            Text.trim (); if(string. IsNullOrEmpty (URL)) {MessageBox.Show ("Please enter a URL"); return; } txtimg. AppendText ("start the crawl: \ r \ n"); Thread th=NewThread (() = Shuaqu (URL)) {IsBackground =true }; Th.        Start (); }        Private voidShuaqu (stringURL) {DirectoryInfo di=NewDirectoryInfo (Path); if(System.IO.Directory.Exists (Path)) {di. Delete (true);            } System.IO.Directory.CreateDirectory (Path); stringresult = Webhttp.httpget (URL,NULL,3); string[] str =gethtmlimageurllist (Result); Txtimg. Invoke (NewAction (() ={txtimg. AppendText ("data has been obtained!"+str. Count () +"\ r \ n");            })); //Create a regular expression to get the page titleString regex =@"<title>.+</title>"; //return page titleString title =Regex.match (result, Regex).            ToString (); Txttitle. Invoke (NewAction (() ={txttitle. Text= Regex.Replace (title,@"[\""]+","");            })); foreach(stringSinchstr) {Uri U=NewUri (s); if(U.host = ="www.xxx.com") {Thread downimg=NewThread (() = Get_img (s)) {IsBackground =true }; Downimg.                    Start (); Txtimg. Invoke (NewAction (() ={txtimg. AppendText (S+"\ r \ n");                })); }} txtimg. Invoke (NewAction (() ={txtimg. AppendText ("Full Crawl complete!\r\n");        })); }         Public voidGet_img (stringImgpath) {                        string[] File = Imgpath. Split ('?'); stringName = System.IO.Path.GetFileName (file[0]); WebClient mywebclient=NewWebClient (); Mywebclient. DownloadFile (Imgpath, Path+@"\"+name); //Bitmap img = null; //HttpWebRequest req; //HttpWebResponse res = null; //Try//{            //System.Uri httpurl = new System.Uri (Imgpath); //req = (HttpWebRequest) (WebRequest.Create (Httpurl)); //req. Timeout = 180000; //set timeout value 10 seconds//req.            useragent = "XXXXX"; //req.            Accept = "XXXXXX"; //req.            Method = "GET"; //res = (HttpWebResponse) (req.            GetResponse ()); //img = new Bitmap (res. GetResponseStream ());//Get Picture Stream//img. Save (Path + @ "\" +name);//Random Name//}            //catch (Exception ex)//{            //string aa = ex.            Message; //}            //finally//{            //Res.            Close (); //}        }        /// <summary>         ///gets the URL of all the pictures in the HTML. /// </summary>         /// <param name= "Shtmltext" >HTML code</param>         /// <returns>List of URLs for pictures</returns>         Private string[] Gethtmlimageurllist (stringShtmltext) {            //define a regular expression to match an IMG tagRegex regimg =NewRegex (@"]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*["'"? [\s\t\r\n]* (? [^\s\t\r\n "" ' <>]* ") [^<>]*?/? [\s\t\r\n]*>", regexoptions.ignorecase); //search for matching stringsMatchCollection matches =regimg.matches (Shtmltext); inti =0; string[] Surllist =New string[matches.            Count]; //get a list of matches            foreach(Match matchinchmatches) Surllist[i+ +] = match. groups["Imgurl"].            Value; returnsurllist; }    }}

#region Download image to imagepublicstatic image Urltoimage (string  url) {      New  WebClient ();     byte [] Bytes = mywebclient. Downloaddata (URL);     using New MemoryStream (Bytes)) {        = Image.fromstream (ms);         return outputimg;}    } #endregion

C # Crawl Web page of img src with parameter image link and download