前两天朋友叫我模仿一个网站,刚刚开始,我一个页面一个页面查看源码并复制和保存,花了我很多时间,一个字“累”,为了减轻工作量,我写了个网站“克隆工具”,一键克隆,比起人工操作,
效率提高了200%以上,精确度也大大提高,下面我将我写的“网站克隆工具”实现方法分享给大家。
一睹为快,先看看界面:
开发工具:vs2012(winform)
1.新建UrlModel模型
public class UrlModel { public string RelatedPath { get; set; } public string AbsoluteUri { get; set; } public string CurrPath { get; set; } public string RootPath { get; set; } public string Host { get; set; } public int Port { get; set; } public string Scheme { get; set; } }
2.新建UrlParser解析器
public class UrlParser { public static UrlModel Parse(string url) { UrlModel model = new UrlModel(); //默认 if (url.Length < 8) throw new Exception("url参数不正确"); else if (!url.ToLower().StartsWith("http:") && !url.ToLower().StartsWith("https:")) throw new Exception("url格式有误"); if (url.LastIndexOf('/') < 8) url = url + "/"; Regex reg = new Regex("(?<scheme>(http|https))://(?<host>.+?)/", RegexOptions.Singleline); if (reg.IsMatch(url)) { string scheme = reg.Match(url).Groups["scheme"].Value; string host = reg.Match(url).Groups["host"].Value; if (host.Contains(":")) { var aa = host.Split(':'); if (aa.Length == 2) { model.Host = aa[0]; model.Port = int.Parse(aa[1]); } } else { model.Host = host; model.Port = 80; } int index = url.IndexOf('/', 8); model.RelatedPath = url.Substring(index); model.AbsoluteUri = url; model.Scheme = scheme; model.CurrPath = url.Substring(0, url.LastIndexOf("/")); if (80 == model.Port) { model.RootPath = string.Format("{0}://{1}", model.Scheme, model.Host); } else { model.RootPath = string.Format("{0}://{1}:{2", model.Scheme, model.Host, model.Port); } } else { throw new Exception("url解析失败!"); } return model; } }
3.网页处理服务工具
/// <summary> /// 网页处理服务工具 /// </summary> public class WebPageService { private static string[] excludekeys = { "http:", "https:", "//", "#", "javascript:", "?", "tel:", "mailto:" }; /// <summary> /// 获取所有html元素的href属性值,只获取站点本地的链接,站外的不获取 /// </summary> /// <param name="html">页面的html源码</param> /// <returns></returns> public static List<UrlModel> GetLocalHrefs(string url,string html) { if (string.IsNullOrEmpty(html)) return new List<UrlModel>(); Dictionary<string, UrlModel> urls = GetHrefs(url,html); List<UrlModel> newUrls = new List<UrlModel>(); if (null != urls) { foreach (string key in urls.Keys) { string newkey = key.ToLower(); bool iscontained = false; foreach (var exkey in excludekeys) { if (newkey.IndexOf(exkey) == 0) { iscontained = true; break; } } if (!iscontained) { //只获取本地路径 newUrls.Add(urls[key]); } } } return newUrls; } /// <summary> /// 获取所有html元素的src属性值,只获取站点本地的链接,站外的不获取 /// </summary> /// <param name="html">页面的html源码</param> /// <returns></returns> public static List<UrlModel> GetLocalSrcs(string url,string html) { if (string.IsNullOrEmpty(html)) return new List<UrlModel>(); Dictionary<string, UrlModel> urls = GetSrc(url, html); List<UrlModel> newUrls = new List<UrlModel>(); if (null != urls) { foreach (string key in urls.Keys) { string newkey = key.ToLower(); bool iscontained = false; foreach (var exkey in excludekeys) { if (newkey.IndexOf(exkey) == 0) { iscontained = true; break; } } if (!iscontained) { //只获取本地路径 newUrls.Add(urls[key]); } } } return newUrls; } private static Dictionary<string, UrlModel> GetHrefs(string url,string html) { if (string.IsNullOrEmpty(html)) return null; UrlModel currUrl = UrlParser.Parse(url); Dictionary<string, UrlModel> urls = new Dictionary<string, UrlModel>(); Regex reg = new Regex("href=\"(?<Url>.+?)\"", RegexOptions.IgnoreCase); if (currUrl != null) { AddUrlModel(html, currUrl, urls, reg); } return urls; } private static Dictionary<string, UrlModel> GetSrc(string url,string html) { if (string.IsNullOrEmpty(html)) return null; UrlModel currUrl = UrlParser.Parse(url); Dictionary<string, UrlModel> urls = new Dictionary<string, UrlModel>(); Regex reg = new Regex("(src=\"(?<Url>.+?)\"|url\\((?<Url>.+?)\\))", RegexOptions.IgnoreCase); if (currUrl != null) { AddUrlModel(html, currUrl, urls, reg); } return urls; } private static void AddUrlModel(string html, UrlModel currUrl, Dictionary<string, UrlModel> urls, Regex reg) { if (reg.IsMatch(html)) { MatchCollection matchs = reg.Matches(html); foreach (Match item in matchs) { try { string strUrl = item.Groups["Url"].Value; UrlModel model = new UrlModel(); model.RelatedPath = strUrl; model.CurrPath = currUrl.CurrPath; model.RootPath = currUrl.RootPath; model.Scheme = currUrl.Scheme; model.Port = currUrl.Port; model.Host = currUrl.Host; if (strUrl.StartsWith("/")) { //绝对目录情况下 model.AbsoluteUri = string.Format("{0}{1}", model.RootPath, model.RelatedPath); } else { //相对目录情况下 string currPath = model.CurrPath; int depth = 0; string path = model.RelatedPath; if (path.StartsWith("..")) { try { while (path.StartsWith("..")) { depth++; path = path.Substring(3); currPath = currPath.Substring(0, currPath.LastIndexOf("/")); } model.AbsoluteUri = string.Format("{0}/{1}", currPath, path); } catch { } } else { model.AbsoluteUri = string.Format("{0}/{1}", currPath, path); } } strUrl = strUrl.Trim().ToLower(); urls.Add(strUrl, model); } catch { } } } } }
4.新建网站克隆接口
interface IWebCloneWorker { void Start(); void Cancel(); }
5.新建实现
public class WebCloneWorker : IWebCloneWorker { //网站页面克隆深度(如:0-首页,1-分类页,2-详细页面) public static int depth = 0; //要克隆的网站网址 public string Url { get; set; } //克隆后,保存的路径 public string SavePath { get; set; } private BackgroundWorker backgroundWorker1 = null; public event UrlChangedEventHandler UrlChanged; public event FileSavedSuccessEventHandler FileSavedSuccess; public event FileSavedFailEventHandler FileSavedFail; public event DownloadCompletedEventHandler DownloadCompleted; public event CollectingUrlEventHandler CollectingUrl; public event CollectedUrlEventHandler CollectedUrl; public event ProgressChangedEventHandler ProgressChanged; //所有页面、文件资源地址集合 private Dictionary<string, UrlModel> _Hrefs = new Dictionary<string, UrlModel>(); /// <summary> /// 所有页面、文件资源地址集合 /// </summary> public Dictionary<string,UrlModel> Hrefs { get { return _Hrefs; } set { _Hrefs = value; } } //网站页面请求编码,默认为UTF-8 private string _Encoding = "utf-8"; //网站页面请求编码,默认为UTF-8 public string Encoding { get { return _Encoding; } set { _Encoding = value; } } public WebCloneWorker() { } public WebCloneWorker(string url,string path) { //设置网站、保存路径 this.Url = url; this.SavePath = path; if (string.IsNullOrEmpty(this.Url)) throw new Exception("请输入网址"); if (string.IsNullOrEmpty(this.SavePath)) throw new Exception("请选择要保存的目录"); backgroundWorker1 = new BackgroundWorker(); //设置报告进度更新 backgroundWorker1.WorkerReportsProgress = true; backgroundWorker1.WorkerSupportsCancellation = true; //注册线程主体方法 backgroundWorker1.DoWork += backgroundWorker1_DoWork; //注册更新UI方法 backgroundWorker1.ProgressChanged += backgroundWorker1_ProgressChanged; //处理完毕 backgroundWorker1.RunWorkerCompleted += backgroundWorker1_RunWorkerCompleted; } void backgroundWorker1_RunWorkerCompleted(object sender, RunWorkerCompletedEventArgs e) { if (e.Cancelled) { return; } if (this.DownloadCompleted != null) { DownloadCompletedEventArgs eventArgs = new DownloadCompletedEventArgs(e.Result, e.Error, e.Cancelled); this.DownloadCompleted(this, eventArgs); } } void backgroundWorker1_ProgressChanged(object sender, ProgressChangedEventArgs e) { //进度回调 if (this.ProgressChanged != null) this.ProgressChanged(this, e); UrlModel model = (UrlModel)e.UserState; if (this.UrlChanged != null) { //Url改变后,回调 UrlChangedEventArgs eventArgs = new UrlChangedEventArgs(model); this.UrlChanged(this, eventArgs); } try { string dir = this.SavePath; string url = model.AbsoluteUri; string AbsolutePath = url.Substring(url.IndexOf('/', 8)); string fileName = ""; if (url.IndexOf('?') > 0) { string path = AbsolutePath.Substring(0, model.RelatedPath.IndexOf('?')); fileName = System.IO.Path.GetFileName(path); } else { fileName = System.IO.Path.GetFileName(AbsolutePath); } //默认首页 if (string.IsNullOrEmpty(fileName) || fileName.IndexOf(".") < 0) { fileName = "index.html"; if (!AbsolutePath.EndsWith("/")) AbsolutePath = AbsolutePath + "/"; } fileName = System.Web.HttpUtility.UrlDecode(fileName); string localPath = string.Format("{0}{1}", dir, System.IO.Path.GetDirectoryName(AbsolutePath)); if (!System.IO.Directory.Exists(localPath)) { System.IO.Directory.CreateDirectory(localPath); } //判断文件是否存在,存在不再下载 string path2 = Path.Combine(localPath, fileName); if (File.Exists(path2)) { return; } //下载网页、图片、资源文件 HttpTool.DownFile(url, localPath, fileName); //保存成功后,回调 if (this.FileSavedSuccess != null) { FileSavedSuccessEventArgs eventArgs = new FileSavedSuccessEventArgs(model); this.FileSavedSuccess(this, eventArgs); } } catch (Exception ex) { //保存失败后,回调 if (this.FileSavedFail != null) { FileSavedFailEventArgs eventArgs = new FileSavedFailEventArgs(ex); this.FileSavedFail(this, eventArgs); } } } void backgroundWorker1_DoWork(object sender, DoWorkEventArgs e) { //获取资源 GetResource(); int index = 1; if (this.Hrefs.Keys.Count > 0) { foreach (var k in this.Hrefs.Keys) { //取消操作 if (backgroundWorker1.CancellationPending) { e.Cancel = true; return; } backgroundWorker1.ReportProgress(index, this.Hrefs[k]); index++; //挂起当前线程200毫秒 Thread.Sleep(200); } } } public void Start() { if (this.backgroundWorker1.IsBusy) return; this.backgroundWorker1.RunWorkerAsync(); } public void Cancel() { if (this.backgroundWorker1.CancellationPending) return; this.backgroundWorker1.CancelAsync(); } private void GetResource() { string url = this.Url; string referer = this.Url; string msg = ""; string html = HttpTool.HttpGet(url, referer, this.Encoding, out msg); //收集页面链接 GetHrefs(0, url, html); //收集完毕 if (null != CollectedUrl) { UrlModel urlModel = new UrlModel(); CollectedUrlEventArgs eventArgs = new CollectedUrlEventArgs(urlModel); this.CollectedUrl(this, eventArgs); } } private void GetHrefs(int level,string url,string html) { #region 添加当前页 UrlModel currUrl = UrlParser.Parse(url); try { //取消 if (backgroundWorker1.CancellationPending) return; this.Hrefs.Add(currUrl.RelatedPath, currUrl); //收集回调 if (null != CollectingUrl) { CollectingUrlEventArgs eventArgs = new CollectingUrlEventArgs(currUrl); this.CollectingUrl(this, eventArgs); } } catch { } #endregion //获取相关链接(含有href属性的) List<UrlModel> list1 = WebPageService.GetLocalHrefs(url,html); //获取图片,文件等资源文件(含有src属性的) List<UrlModel> listSrcs = WebPageService.GetLocalSrcs(url,html); #region 获取当级资源文件 if (listSrcs != null) { for (int i = 0; i < listSrcs.Count; i++) { UrlModel urlModel = listSrcs[i]; try { //取消 if (backgroundWorker1.CancellationPending) return; this.Hrefs.Add(urlModel.RelatedPath, urlModel); //收集回调 if (null != CollectingUrl) { CollectingUrlEventArgs eventArgs = new CollectingUrlEventArgs(urlModel); this.CollectingUrl(this, eventArgs); } } catch { } } } #endregion #region 获取子级页面资源 //获取第二级 if (list1 != null) { for (int i = 0; i < list1.Count; i++) { UrlModel urlModel = list1[i]; try { //取消 if (backgroundWorker1.CancellationPending) return; this.Hrefs.Add(urlModel.RelatedPath, urlModel); //收集回调 if (null != CollectingUrl) { CollectingUrlEventArgs eventArgs = new CollectingUrlEventArgs(urlModel); this.CollectingUrl(this, eventArgs); } } catch { } string msg = ""; html = HttpTool.HttpGet(urlModel.AbsoluteUri, urlModel.AbsoluteUri, this.Encoding, out msg); #region 获取子级资源文件 /* * 获取二级资源文件 * */ listSrcs = WebPageService.GetLocalSrcs(urlModel.AbsoluteUri, html);//资源文件 if (listSrcs != null) { for (int j = 0; j < listSrcs.Count; j++) { UrlModel urlModel2 = listSrcs[j]; try { //取消 if (backgroundWorker1.CancellationPending) return; this.Hrefs.Add(urlModel2.RelatedPath, urlModel2); //收集回调 if (null != CollectingUrl) { CollectingUrlEventArgs eventArgs = new CollectingUrlEventArgs(urlModel2); this.CollectingUrl(this, eventArgs); } } catch { } //挂起线程20毫秒 Thread.Sleep(20); } } #endregion //挂起线程20毫秒 Thread.Sleep(20); //到达指定深度后,退出 if (level >= depth) return; //递归 GetHrefs(level + 1, urlModel.AbsoluteUri, html); } } #endregion }
6.代码有点多,各位有需要的还是下载源码查看并运行吧。
旧版本有很多问题,有需要新版本的请加我微信:xiaoqiu20121212。