网站抓取

新软件马上就要完成了,先发篇文章YY下

 

 

最近一直都在搞网站抓取方面的开发，闲着无聊逛逛论坛，发现有些帖子还是写的相当不错的，只是一篇一篇的点进去比较麻烦，于是就写了个小软件只是为了方便查看博客园和CSDN上的优秀文章。其实这个还可以拓展的，比如说可以添加RSS功能，查看新闻网站的新闻。代码比较简单，可以考虑用个工厂模式。

写的比较乱，都不敢上代码了。求大神喷！

2013-6-28号更新

1、添加了皮肤

2013-6-29号更新

1、解决了ListView控件添加数据闪烁问题。

2、取消皮肤加快数据加载速度

3、优化了浏览文章体验

点击下载

 

 

 里面有几个类库非常不错，想要的可以拿去。

 

///
/// 类说明：HttpHelps类，用来实现Http访问，Post或者Get方式的，直接访问，带Cookie的，带证书的等方式，可以设置代理
/// 重要提示：请不要自行修改本类，如果因为你自己修改后将无法升级到新版本。如果确实有什么问题请到官方网站提建议，
/// 我们一定会及时修改
/// 编码日期：2011-09-20
/// 编 码 人：苏飞
/// 联系方式：361983679
/// 官方网址：http://www.sufeinet.com/thread-3-1-1.html
/// 修改日期：2013-04-14
///
using  System;
using  System.Collections.Generic;
using  System.Text;
using  System.Net;
using  System.IO;
using  System.Text.RegularExpressions;
using  System.IO.Compression;
using  System.Security.Cryptography.X509Certificates;
using  System.Net.Security;

namespace  Common.PageHelper
{
    ///
    /// Http连接操作帮助类
    ///
    public  class  HttpHelper
    {
        #region 预定义方法或者变更
        //默认的编码
        private  Encoding encoding = Encoding.Default;
        //HttpWebRequest对象用来发起请求
        private  HttpWebRequest request = null ;
        //获取影响流的数据对象
        private  HttpWebResponse response = null ;
        ///
        /// 根据相传入的数据，得到相应页面数据
        ///
        ///参数类对象
        ///返回HttpResult类型
        private  HttpResult GetHttpRequestData(HttpItem objhttpitem)
        {
            //返回参数
            HttpResult result = new  HttpResult();
            try
            {
                #region 得到请求的response
                using  (response = (HttpWebResponse)request.GetResponse())
                {
                    result.StatusCode = response.StatusCode;
                    result.StatusDescription = response.StatusDescription;
                    result.Header = response.Headers;
                    if  (response.Cookies != null )
                        result.CookieCollection = response.Cookies;
                    if  (response.Headers[ "set-cookie" ] != null )
                        result.Cookie = response.Headers[ "set-cookie" ];
                    MemoryStream _stream = new  MemoryStream();
                    //GZIIP处理
                    if  (response.ContentEncoding != null  && response.ContentEncoding.Equals( "gzip" , StringComparison.InvariantCultureIgnoreCase))
                    {
                        //开始读取流并设置编码方式
                        //new GZipStream(response.GetResponseStream(), CompressionMode.Decompress).CopyTo(_stream, 10240);
                        //.net4.0以下写法
                        _stream = GetMemoryStream( new  GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
                    }
                    else
                    {
                        //开始读取流并设置编码方式
                        //response.GetResponseStream().CopyTo(_stream, 10240);
                        //.net4.0以下写法
                        _stream = GetMemoryStream(response.GetResponseStream());
                    }
                    //获取Byte
                    byte [] RawResponse = _stream.ToArray();
                    _stream.Close();
                    //是否返回Byte类型数据
                    if  (objhttpitem.ResultType == ResultType.Byte)
                        result.ResultByte = RawResponse;
                    //从这里开始我们要无视编码了
                    if  (encoding == null )
                    {
                        Match meta = Regex.Match(Encoding.Default.GetString(RawResponse), "<meta([^<]*)charset=([^<]*)[\"']" , RegexOptions.IgnoreCase);
                        string  charter = (meta.Groups.Count > 2) ? meta.Groups[2].Value.ToLower() : string .Empty;
                        charter = charter.Replace( "\"" , "" ).Replace( "'" , "" ).Replace( ";" , "" ).Replace( "iso-8859-1" , "gbk" );
                        if  (charter.Length > 2)
                            encoding = Encoding.GetEncoding(charter);
                        else
                        {
                            if  ( string .IsNullOrEmpty(response.CharacterSet))
                                encoding = Encoding.UTF8;
                            else
                                encoding = Encoding.GetEncoding(response.CharacterSet);
                        }
                    }
                    //得到返回的HTML
                    result.Html = encoding.GetString(RawResponse);
                }
                #endregion
            }
            catch  (WebException ex)
            {
                //这里是在发生异常时返回的错误信息
                response = (HttpWebResponse)ex.Response;
                result.Html = ex.Message;
                result.StatusCode = response.StatusCode;
                result.StatusDescription = response.StatusDescription;
            }
            catch  (Exception ex)
            {
                result.Html = ex.Message;
            }
            if  (objhttpitem.IsToLower)
                result.Html = result.Html.ToLower();

            return  result;
        }
        ///
        /// 4.0以下.net版本取数据使用
        ///
        ///流
        private  static  MemoryStream GetMemoryStream(Stream streamResponse)
        {
            MemoryStream _stream = new  MemoryStream();
            int  Length = 256;
            Byte[] buffer = new  Byte[Length];
            int  bytesRead = streamResponse.Read(buffer, 0, Length);
            // write the required bytes
            while  (bytesRead > 0)
            {
                _stream.Write(buffer, 0, bytesRead);
                bytesRead = streamResponse.Read(buffer, 0, Length);
            }
            return  _stream;
        }
        ///
        /// 为请求准备参数
        ///
        ///参数列表
        ///读取数据时的编码方式
        private  void  SetRequest(HttpItem objhttpItem)
        {
            // 验证证书
            SetCer(objhttpItem);
            //设置Header参数
            if  (objhttpItem.Header != null  && objhttpItem.Header.Count > 0)
            {
                foreach  ( string  item in  objhttpItem.Header.AllKeys)
                {
                    request.Headers.Add(item, objhttpItem.Header[item]);
                }
            }
            // 设置代理
            SetProxy(objhttpItem);
            //请求方式Get或者Post
            request.Method = objhttpItem.Method;
            request.Timeout = objhttpItem.Timeout;
            request.ReadWriteTimeout = objhttpItem.ReadWriteTimeout;
            //Accept
            request.Accept = objhttpItem.Accept;
            //ContentType返回类型
            request.ContentType = objhttpItem.ContentType;
            //UserAgent客户端的访问类型，包括浏览器版本和操作系统信息
            request.UserAgent = objhttpItem.UserAgent;
            // 编码
            encoding = objhttpItem.Encoding;
            //设置Cookie
            SetCookie(objhttpItem);
            //来源地址
            request.Referer = objhttpItem.Referer;
            //是否执行跳转功能
            request.AllowAutoRedirect = objhttpItem.Allowautoredirect;
            //设置Post数据
            SetPostData(objhttpItem);
            //设置最大连接
            if  (objhttpItem.Connectionlimit > 0)
                request.ServicePoint.ConnectionLimit = objhttpItem.Connectionlimit;
        }
        ///
        /// 设置证书
        ///
        ///
        private  void  SetCer(HttpItem objhttpItem)
        {
            if  (! string .IsNullOrEmpty(objhttpItem.CerPath))
            {
                //这一句一定要写在创建连接的前面。使用回调的方法进行证书验证。
                ServicePointManager.ServerCertificateValidationCallback = new  System.Net.Security.RemoteCertificateValidationCallback(CheckValidationResult);
                //初始化对像，并设置请求的URL地址
                request = (HttpWebRequest)WebRequest.Create(objhttpItem.URL);
                //将证书添加到请求里
                request.ClientCertificates.Add( new  X509Certificate(objhttpItem.CerPath));
            }
            else
                //初始化对像，并设置请求的URL地址
                request = (HttpWebRequest)WebRequest.Create(objhttpItem.URL);
        }
        ///
        /// 设置Cookie
        ///
        ///Http参数
        private  void  SetCookie(HttpItem objhttpItem)
        {
            if  (! string .IsNullOrEmpty(objhttpItem.Cookie))
                //Cookie
                request.Headers[HttpRequestHeader.Cookie] = objhttpItem.Cookie;
            //设置Cookie
            if  (objhttpItem.CookieCollection != null )
            {
                request.CookieContainer = new  CookieContainer();
                request.CookieContainer.Add(objhttpItem.CookieCollection);
            }
        }
        ///
        /// 设置Post数据
        ///
        ///Http参数
        private  void  SetPostData(HttpItem objhttpItem)
        {
            //验证在得到结果时是否有传入数据
            if  (request.Method.Trim().ToLower().Contains( "post" ))
            {
                byte [] buffer = null ;
                //写入Byte类型
                if  (objhttpItem.PostDataType == PostDataType.Byte && objhttpItem.PostdataByte != null  && objhttpItem.PostdataByte.Length > 0)
                {
                    //验证在得到结果时是否有传入数据
                    buffer = objhttpItem.PostdataByte;
                } //写入文件
                else  if  (objhttpItem.PostDataType == PostDataType.FilePath && ! string .IsNullOrEmpty(objhttpItem.Postdata))
                {
                    StreamReader r = new  StreamReader(objhttpItem.Postdata, encoding);
                    buffer = Encoding.Default.GetBytes(r.ReadToEnd());
                    r.Close();
                } //写入字符串
                else  if  (! string .IsNullOrEmpty(objhttpItem.Postdata))
                {
                    buffer = Encoding.Default.GetBytes(objhttpItem.Postdata);
                }
                if  (buffer != null )
                {
                    request.ContentLength = buffer.Length;
                    request.GetRequestStream().Write(buffer, 0, buffer.Length);
                }
            }
        }
        ///
        /// 设置代理
        ///
        ///参数对象
        private  void  SetProxy(HttpItem objhttpItem)
        {
            if  (! string .IsNullOrEmpty(objhttpItem.ProxyIp))
            {
                //设置代理服务器
                WebProxy myProxy = new  WebProxy(objhttpItem.ProxyIp, false );
                //建议连接
                myProxy.Credentials = new  NetworkCredential(objhttpItem.ProxyUserName, objhttpItem.ProxyPwd);
                //给当前请求对象
                request.Proxy = myProxy;
                //设置安全凭证
                request.Credentials = CredentialCache.DefaultNetworkCredentials;
            }
        }
        ///
        /// 回调验证证书问题
        ///
        ///流对象
        ///证书
        ///X509Chain
        ///SslPolicyErrors
        ///bool
        public  bool  CheckValidationResult( object  sender, X509Certificate certificate, X509Chain chain, SslPolicyErrors errors)
        {
            // 总是接受
            return  true ;
        }
        #endregion
        #region 普通类型
        ///
        ///采用https协议访问网络,根据传入的URl地址，得到响应的数据字符串。
        ///
        ///参数列表
        ///String类型的数据
        public  HttpResult GetHtml(HttpItem objhttpItem)
        {
            try
            {
                //准备参数
                SetRequest(objhttpItem);
            }
            catch  (Exception ex)
            {
                return  new  HttpResult() { Cookie = "" , Header = null , Html = ex.Message, StatusDescription = "配置参考时报错" };
            }
            //调用专门读取数据的类
            return  GetHttpRequestData(objhttpItem);
        }
        #endregion
    }
    ///
    /// Http请求参考类
    ///
    public  class  HttpItem
    {
        string  _URL = string .Empty;
        ///
        /// 请求URL必须填写
        ///
        public  string  URL
        {
            get  { return  _URL; }
            set  { _URL = value; }
        }
        string  _Method = "GET" ;
        ///
        /// 请求方式默认为GET方式,当为POST方式时必须设置Postdata的值
        ///
        public  string  Method
        {
            get  { return  _Method; }
            set  { _Method = value; }
        }
        int  _Timeout = 100000;
        ///
        /// 默认请求超时时间
        ///
        public  int  Timeout
        {
            get  { return  _Timeout; }
            set  { _Timeout = value; }
        }
        int  _ReadWriteTimeout = 30000;
        ///
        /// 默认写入Post数据超时间
        ///
        public  int  ReadWriteTimeout
        {
            get  { return  _ReadWriteTimeout; }
            set  { _ReadWriteTimeout = value; }
        }
        string  _Accept = "text/html, application/xhtml+xml, */*" ;
        ///
        /// 请求标头值 默认为text/html, application/xhtml+xml, */*
        ///
        public  string  Accept
        {
            get  { return  _Accept; }
            set  { _Accept = value; }
        }
        string  _ContentType = "text/html" ;
        ///
        /// 请求返回类型默认 text/html
        ///
        public  string  ContentType
        {
            get  { return  _ContentType; }
            set  { _ContentType = value; }
        }
        string  _UserAgent = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)" ;
        ///
        /// 客户端访问信息默认Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)
        ///
        public  string  UserAgent
        {
            get  { return  _UserAgent; }
            set  { _UserAgent = value; }
        }
        Encoding _Encoding = null ;
        ///
        /// 返回数据编码默认为NUll,可以自动识别,一般为utf-8,gbk,gb2312
        ///
        public  Encoding Encoding
        {
            get  { return  _Encoding; }
            set  { _Encoding = value; }
        }
        private  PostDataType _PostDataType = PostDataType.String;
        ///
        /// Post的数据类型
        ///
        public  PostDataType PostDataType
        {
            get  { return  _PostDataType; }
            set  { _PostDataType = value; }
        }
        string  _Postdata = string .Empty;
        ///
        /// Post请求时要发送的字符串Post数据
        ///
        public  string  Postdata
        {
            get  { return  _Postdata; }
            set  { _Postdata = value; }
        }
        private  byte [] _PostdataByte = null ;
        ///
        /// Post请求时要发送的Byte类型的Post数据
        ///
        public  byte [] PostdataByte
        {
            get  { return  _PostdataByte; }
            set  { _PostdataByte = value; }
        }
        CookieCollection cookiecollection = null ;
        ///
        /// Cookie对象集合
        ///
        public  CookieCollection CookieCollection
        {
            get  { return  cookiecollection; }
            set  { cookiecollection = value; }
        }
        string  _Cookie = string .Empty;
        ///
        /// 请求时的Cookie
        ///
        public  string  Cookie
        {
            get  { return  _Cookie; }
            set  { _Cookie = value; }
        }
        string  _Referer = string .Empty;
        ///
        /// 来源地址，上次访问地址
        ///
        public  string  Referer
        {
            get  { return  _Referer; }
            set  { _Referer = value; }
        }
        string  _CerPath = string .Empty;
        ///
        /// 证书绝对路径
        ///
        public  string  CerPath
        {
            get  { return  _CerPath; }
            set  { _CerPath = value; }
        }
        private  Boolean isToLower = false ;
        ///
        /// 是否设置为全文小写，默认为不转化
        ///
        public  Boolean IsToLower
        {
            get  { return  isToLower; }
            set  { isToLower = value; }
        }
        private  Boolean allowautoredirect = false ;
        ///
        /// 支持跳转页面，查询结果将是跳转后的页面，默认是不跳转
        ///
        public  Boolean Allowautoredirect
        {
            get  { return  allowautoredirect; }
            set  { allowautoredirect = value; }
        }
        private  int  connectionlimit = 1024;
        ///
        /// 最大连接数
        ///
        public  int  Connectionlimit
        {
            get  { return  connectionlimit; }
            set  { connectionlimit = value; }
        }
        private  string  proxyusername = string .Empty;
        ///
        /// 代理Proxy 服务器用户名
        ///
        public  string  ProxyUserName
        {
            get  { return  proxyusername; }
            set  { proxyusername = value; }
        }
        private  string  proxypwd = string .Empty;
        ///
        /// 代理 服务器密码
        ///
        public  string  ProxyPwd
        {
            get  { return  proxypwd; }
            set  { proxypwd = value; }
        }
        private  string  proxyip = string .Empty;
        ///
        /// 代理 服务IP
        ///
        public  string  ProxyIp
        {
            get  { return  proxyip; }
            set  { proxyip = value; }
        }
        private  ResultType resulttype = ResultType.String;
        ///
        /// 设置返回类型String和Byte
        ///
        public  ResultType ResultType
        {
            get  { return  resulttype; }
            set  { resulttype = value; }
        }
        private  WebHeaderCollection header = new  WebHeaderCollection();
        //header对象
        public  WebHeaderCollection Header
        {
            get  { return  header; }
            set  { header = value; }
        }
    }
    ///
    /// Http返回参数类
    ///
    public  class  HttpResult
    {
        string  _Cookie = string .Empty;
        ///
        /// Http请求返回的Cookie
        ///
        public  string  Cookie
        {
            get  { return  _Cookie; }
            set  { _Cookie = value; }
        }
        CookieCollection cookiecollection = new  CookieCollection();
        ///
        /// Cookie对象集合
        ///
        public  CookieCollection CookieCollection
        {
            get  { return  cookiecollection; }
            set  { cookiecollection = value; }
        }
        private  string  html = string .Empty;
        ///
        /// 返回的String类型数据 只有ResultType.String时才返回数据，其它情况为空
        ///
        public  string  Html
        {
            get  { return  html; }
            set  { html = value; }
        }
        private  byte [] resultbyte = null ;
        ///
        /// 返回的Byte数组 只有ResultType.Byte时才返回数据，其它情况为空
        ///
        public  byte [] ResultByte
        {
            get  { return  resultbyte; }
            set  { resultbyte = value; }
        }
        private  WebHeaderCollection header = new  WebHeaderCollection();
        //header对象
        public  WebHeaderCollection Header
        {
            get  { return  header; }
            set  { header = value; }
        }
        private  string  statusDescription = "" ;
        ///
        /// 返回状态说明
        ///
        public  string  StatusDescription
        {
            get  { return  statusDescription; }
            set  { statusDescription = value; }
        }
        private  HttpStatusCode statusCode = HttpStatusCode.OK;
        ///
        /// 返回状态码,默认为OK
        ///
        public  HttpStatusCode StatusCode
        {
            get  { return  statusCode; }
            set  { statusCode = value; }
        }
    }
    ///
    /// 返回类型
    ///
    public  enum  ResultType
    {
        ///
        /// 表示只返回字符串 只有Html有数据
        ///
        String,
        ///
        /// 表示返回字符串和字节流 ResultByte和Html都有数据返回
        ///
        Byte
    }
    ///
    /// Post的数据格式默认为string
    ///
    public  enum  PostDataType
    {
        ///
        /// 字符串类型，这时编码Encoding可不设置
        ///
        String,
        ///
        /// Byte类型，需要设置PostdataByte参数的值编码Encoding可设置为空
        ///
        Byte,
        ///
        /// 传文件，Postdata必须设置为文件的绝对路径，必须设置Encoding的值
        ///
        FilePath
    }
}

 

 

分类:  .net代码