如何打造网站克隆、仿站工具（C#版）

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，虽然网上也很多网站克隆工具，但我觉得作为一个程序员，要有点研究精神，哈哈哈，可以根据自己的需要随意编写自己需要的功能。

下面我将我写的“网站克隆工具”实现方法分享给大家，源码在文末有下载链接，有需要的朋友可以下载来玩，也可以根据自己的需要做相应的修改或优化。

一睹为快，先看看界面：

 

简单的工作流程：

 

项目代码目录结构：

 

下面一步步实现程序功能：

 

1.新建主界面窗体（mainform.cs）：

2.新建模型类（urlmodel.cs）

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; }
    }

3.新建服务类（services）

urlparser：

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;
        }
    }

webpageservice：

/// <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.网页源码扒取类

public class httptool
    {
        public static string httpget(string url, string referer, string encoding, out string msg)
        {
            msg = string.empty;
            string result = string.empty;
            try
            {
                httpwebrequest request = (httpwebrequest)webrequest.create(url);

                //request.contenttype = "application/x-www-form-urlencoded";
                request.accept = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8";
                request.referer = referer;
                request.method = "get";
                request.useragent = "mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/38.0.2125.122 safari/537.36";
                //request.headers.add("accept-language", "zh-cn");
                //request.headers.add("accept-encoding", "gzip,deflate");

                request.timeout = 60000;//一分钟

                httpwebresponse response = (httpwebresponse)request.getresponse();
                stream responsestream = response.getresponsestream();
                if (responsestream != null)
                {
                    streamreader reader = new streamreader(responsestream, system.text.encoding.getencoding(encoding));
                    result = reader.readtoend();
                    reader.close();
                    responsestream.close();
                    request.abort();
                    response.close();
                    return result.trim();
                }
            }
            catch (exception ex)
            {
                msg = ex.message + ex.stacktrace;
            }

            return result;
        }

        public static void downfile(string urladdress, string localpath, string filename)
        {
            webclient client = new webclient();
            stream str = client.openread(urladdress);
            streamreader reader = new streamreader(str);
            byte[] mbyte = new byte[1000000];
            int allmybyte = (int)mbyte.length;
            int startmbyte = 0;

            while (allmybyte > 0)
            {
                int m = str.read(mbyte, startmbyte, allmybyte);
                if (m == 0)
                {
                    break;
                }
                startmbyte += m;
                allmybyte -= m;
            }

            reader.dispose();
            str.dispose();

            string path = path.combine(localpath, filename);
            filestream fstr = new filestream(path, filemode.openorcreate, fileaccess.write);
            fstr.write(mbyte, 0, startmbyte);
            fstr.flush();
            fstr.close();
        }
    }

5.网站克隆主类

接口：

interface iwebcloneworker
    {
        void start();
        void cancel();
    }

 

 

实现类：

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
        }
    }

 

6.一些事件、委托类：

public delegate void urlchangedeventhandler(object sender, urlchangedeventargs e);
    public delegate void filesavedsuccesseventhandler(object sender, filesavedsuccesseventargs e);
    public delegate void filesavedfaileventhandler(object sender, filesavedfaileventargs e);
    public delegate void downloadcompletedeventhandler(object sender, downloadcompletedeventargs e);
    public delegate void collectingurleventhandler(object sender, collectingurleventargs e);
    public delegate void collectedurleventhandler(object sender, collectedurleventargs e);
    public delegate void progresschangedeventhandler(object sender, progresschangedeventargs e);

 

public class collectedurleventargs : eventargs
public class collectingurleventargs : eventargs
public class downloadcompletedeventargs : eventargs
public class filesavedfaileventargs : eventargs
public class filesavedsuccesseventargs : eventargs
public class urlchangedeventargs : eventargs

 

代码有点多，各位有需要的还是下载源码查看并运行吧，由于赶时间，没时间仔细测试程序的各个功能，难免有不足的地方。

百度网盘：链接：https://pan.baidu.com/s/1hja1rl9uecl0dztqvft0dg 密码：7s6r