http://www.sufeinet.com/plugin.php?id=keke_group

苏飞论坛

 找回密码
 马上注册

QQ登录

只需一步,快速开始

分布式系统框架(V2.0) 轻松承载百亿数据,千万流量!讨论专区 - 源码下载 - 官方教程

HttpHelper爬虫框架(V2.7-含.netcore) HttpHelper官方出品,爬虫框架讨论区 - 源码下载 - 在线测试和代码生成

HttpHelper爬虫类(V2.0) 开源的爬虫类,支持多种模式和属性 源码 - 代码生成器 - 讨论区 - 教程- 例子

查看: 18429|回复: 14

[页面辅助] C# HTMLHelper类对Html源码处理教程与源码下载

[复制链接]
发表于 2014-1-22 08:33:50 | 显示全部楼层 |阅读模式
C# HTMLHelper类对Html源码处理教程与源码下载
导读部分
-------------------------------------------------------------------------------------------------------------
C#基类|C#自定义类|C#帮助类--系列导航文章
http://www.sufeinet.com/thread-655-1-1.html

源码下载,请到基库中直接查找http://www.sufeinet.com/thread-655-1-1.html
主要功能有
[C#] 纯文本查看 复制代码
1.获取HTML源代码
2.获取Html源代码的字符流
3.清理所有的Html标记,标签
4.匹配页面的链接,获取Html中所有的A链接
5.匹配页面的图片地址 ,获取Html中所有的图片地址
6.抓取远程页面内容
7.压缩HTML输出
8.过滤指定HTML标签
9.加载文件块
10.加载CSS样式文件
11.加载JavaScript脚本文件

如下图片
QQ截图20140122082754.jpg
[size=0.83em]QQ截图20140121085054.jpg (101.69 KB, 下载次数: 0)
下载附件
[color=rgb(153, 153, 153) !important]昨天 08:50 上传




预览源码
代码如下
[C#] 纯文本查看 复制代码
/// <summary>
/// 类说明:HTMLHelper
/// 编 码 人:苏飞
/// 联系方式:361983679  
/// 更新网站:[url=http://www.sufeinet.com/thread-655-1-1.html]http://www.sufeinet.com/thread-655-1-1.html[/url]
/// </summary>
using System;
using System.Text; 
using System.Net; 
using System.IO; 
using System.Threading;
using System.Text.RegularExpressions;

namespace DotNet.Utilities
{
    public class HTMLHelper
    {
        #region 私有字段
        private static CookieContainer cc = new CookieContainer();
        private static string contentType = "application/x-www-form-urlencoded";
        private static string accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/x-silverlight, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, application/x-ms-application, application/x-ms-xbap, application/vnd.ms-xpsdocument, application/xaml+xml, application/x-silverlight-2-b1, */*";
        private static string userAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022)";
        private static Encoding encoding = Encoding.GetEncoding("utf-8");
        private static int delay = 1000;
        private static int maxTry = 300;
        private static int currentTry = 0;
        #endregion

        #region 公有属性
        /// <summary> 
        /// Cookie
        /// </summary> 
        public static CookieContainer CookieContainer
        {
            get
            {
                return cc;
            }
        }

        /// <summary> 
        /// 语言
        /// </summary> 
        public static Encoding Encoding
        {
            get
            {
                return encoding;
            }
            set
            {
                encoding = value;
            }
        }

        public static int NetworkDelay
        {
            get
            {
                Random r = new Random();
                return (r.Next(delay, delay * 2));
            }
            set
            {
                delay = value;
            }
        }

        public static int MaxTry
        {
            get
            {
                return maxTry;
            }
            set
            {
                maxTry = value;
            }
        }
        #endregion

        #region 获取HTML
        /// <summary>
        /// 获取HTML
        /// </summary>
        /// <param name="url">地址</param>
        /// <param name="postData">post 提交的字符串</param>
        /// <param name="isPost">是否是post</param>
        /// <param name="cookieContainer">CookieContainer</param>
        public static string GetHtml(string url, string postData, bool isPost, CookieContainer cookieContainer)
        {
            if (string.IsNullOrEmpty(postData)) return GetHtml(url, cookieContainer);
            Thread.Sleep(NetworkDelay);
            currentTry++;
            HttpWebRequest httpWebRequest = null;
            HttpWebResponse httpWebResponse = null;
            try
            {
                byte[] byteRequest = Encoding.Default.GetBytes(postData);
                httpWebRequest = (HttpWebRequest)HttpWebRequest.Create(url);
                httpWebRequest.CookieContainer = cookieContainer;
                httpWebRequest.ContentType = contentType;
                httpWebRequest.ServicePoint.ConnectionLimit = maxTry;
                httpWebRequest.Referer = url;
                httpWebRequest.Accept = accept;
                httpWebRequest.UserAgent = userAgent;
                httpWebRequest.Method = isPost ? "POST" : "GET";
                httpWebRequest.ContentLength = byteRequest.Length;
                Stream stream = httpWebRequest.GetRequestStream();
                stream.Write(byteRequest, 0, byteRequest.Length);
                stream.Close();
                httpWebResponse = (HttpWebResponse)httpWebRequest.GetResponse();
                Stream responseStream = httpWebResponse.GetResponseStream();
                StreamReader streamReader = new StreamReader(responseStream, encoding);
                string html = streamReader.ReadToEnd();
                streamReader.Close();
                responseStream.Close();
                currentTry = 0;
                httpWebRequest.Abort();
                httpWebResponse.Close();
                return html;
            }
            catch (Exception e)
            {
                if (currentTry <= maxTry) GetHtml(url, postData, isPost, cookieContainer);
                currentTry--;
                if (httpWebRequest != null) httpWebRequest.Abort();
                if (httpWebResponse != null) httpWebResponse.Close();
                return string.Empty;
            }
        }

        /// <summary>
        /// 获取HTML
        /// </summary>
        /// <param name="url">地址</param>
        /// <param name="cookieContainer">CookieContainer</param>
        public static string GetHtml(string url, CookieContainer cookieContainer)
        {
            Thread.Sleep(NetworkDelay);
            currentTry++;
            HttpWebRequest httpWebRequest = null;
            HttpWebResponse httpWebResponse = null;
            try
            {
                httpWebRequest = (HttpWebRequest)HttpWebRequest.Create(url);
                httpWebRequest.CookieContainer = cookieContainer;
                httpWebRequest.ContentType = contentType;
                httpWebRequest.ServicePoint.ConnectionLimit = maxTry;
                httpWebRequest.Referer = url;
                httpWebRequest.Accept = accept;
                httpWebRequest.UserAgent = userAgent;
                httpWebRequest.Method = "GET";
                httpWebResponse = (HttpWebResponse)httpWebRequest.GetResponse();
                Stream responseStream = httpWebResponse.GetResponseStream();
                StreamReader streamReader = new StreamReader(responseStream, encoding);
                string html = streamReader.ReadToEnd();
                streamReader.Close();
                responseStream.Close();
                currentTry--;
                httpWebRequest.Abort();
                httpWebResponse.Close();
                return html;
            }
            catch (Exception e)
            {
                if (currentTry <= maxTry) GetHtml(url, cookieContainer);
                currentTry--;
                if (httpWebRequest != null) httpWebRequest.Abort();
                if (httpWebResponse != null) httpWebResponse.Close();
                return string.Empty;
            }
        }
        #endregion

        #region 获取字符流
        /// <summary>
        /// 获取字符流
        /// </summary>
        //---------------------------------------------------------------------------------------------------------------
        // 示例:
        // System.Net.CookieContainer cookie = new System.Net.CookieContainer(); 
        // Stream s = HttpHelper.GetStream("http://ptlogin2.qq.com/getimage?aid=15000102&0.43878429697395826", cookie);
        // picVerify.Image = Image.FromStream(s);
        //---------------------------------------------------------------------------------------------------------------
        /// <param name="url">地址</param>
        /// <param name="cookieContainer">cookieContainer</param>
        public static Stream GetStream(string url, CookieContainer cookieContainer)
        {
            currentTry++;

            HttpWebRequest httpWebRequest = null;
            HttpWebResponse httpWebResponse = null;

            try
            {
                httpWebRequest = (HttpWebRequest)HttpWebRequest.Create(url);
                httpWebRequest.CookieContainer = cookieContainer;
                httpWebRequest.ContentType = contentType;
                httpWebRequest.ServicePoint.ConnectionLimit = maxTry;
                httpWebRequest.Referer = url;
                httpWebRequest.Accept = accept;
                httpWebRequest.UserAgent = userAgent;
                httpWebRequest.Method = "GET";

                httpWebResponse = (HttpWebResponse)httpWebRequest.GetResponse();
                Stream responseStream = httpWebResponse.GetResponseStream();
                currentTry--;
                return responseStream;
            }
            catch (Exception e)
            {
                if (currentTry <= maxTry)
                {
                    GetHtml(url, cookieContainer);
                }

                currentTry--;

                if (httpWebRequest != null)
                {
                    httpWebRequest.Abort();
                } if (httpWebResponse != null)
                {
                    httpWebResponse.Close();
                }
                return null;
            }
        }
        #endregion

        #region 清除HTML标记
        ///<summary>   
        ///清除HTML标记   
        ///</summary>   
        ///<param name="NoHTML">包括HTML的源码</param>   
        ///<returns>已经去除后的文字</returns>   
        public static string NoHTML(string Htmlstring)
        {
            //删除脚本   
            Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);

            //删除HTML   
            Regex regex = new Regex("<.+?>", RegexOptions.IgnoreCase);
            Htmlstring = regex.Replace(Htmlstring, "");
            Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);

            Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", "   ", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);
            Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "", RegexOptions.IgnoreCase);

            Htmlstring.Replace("<", "");
            Htmlstring.Replace(">", "");
            Htmlstring.Replace("\r\n", "");

            return Htmlstring;
        }
        #endregion

        #region 匹配页面的链接
        /// <summary>
        /// 获取页面的链接正则
        /// </summary>
        public string GetHref(string HtmlCode)
        {
            string MatchVale = "";
            string Reg = @"(h|H)(r|R)(e|E)(f|F) *= *('|"")?((\w|\\|\/|\.|:|-|_)+)[\S]*";
            foreach (Match m in Regex.Matches(HtmlCode, Reg))
            {
                MatchVale += (m.Value).ToLower().Replace("href=", "").Trim() + "|";
            }
            return MatchVale;
        }
        #endregion

        #region 匹配页面的图片地址
        /// <summary>
        /// 匹配页面的图片地址
        /// </summary>
        /// <param name="imgHttp">要补充的http://路径信息</param>
        public string GetImgSrc(string HtmlCode, string imgHttp)
        {
            string MatchVale = "";
            string Reg = @"<img.+?>";
            foreach (Match m in Regex.Matches(HtmlCode.ToLower(), Reg))
            {
                MatchVale += GetImg((m.Value).ToLower().Trim(), imgHttp) + "|";
            }

            return MatchVale;
        }

        /// <summary>
        /// 匹配<img src="" />中的图片路径实际链接
        /// </summary>
        /// <param name="ImgString"><img src="" />字符串</param>
        public string GetImg(string ImgString, string imgHttp)
        {
            string MatchVale = "";
            string Reg = @"src=.+\.(bmp|jpg|gif|png|)";
            foreach (Match m in Regex.Matches(ImgString.ToLower(), Reg))
            {
                MatchVale += (m.Value).ToLower().Trim().Replace("src=", "");
            }
            if (MatchVale.IndexOf(".net") != -1 || MatchVale.IndexOf(".com") != -1 || MatchVale.IndexOf(".org") != -1 || MatchVale.IndexOf(".cn") != -1 || MatchVale.IndexOf(".cc") != -1 || MatchVale.IndexOf(".info") != -1 || MatchVale.IndexOf(".biz") != -1 || MatchVale.IndexOf(".tv") != -1)
                return (MatchVale);
            else
                return (imgHttp + MatchVale);
        }
        #endregion

        #region 抓取远程页面内容
        /// <summary>
        /// 以GET方式抓取远程页面内容
        /// </summary>
        public static string Get_Http(string tUrl)
        {
            string strResult;
            try
            {
                HttpWebRequest hwr = (HttpWebRequest)HttpWebRequest.Create(tUrl);
                hwr.Timeout = 19600;
                HttpWebResponse hwrs = (HttpWebResponse)hwr.GetResponse();
                Stream myStream = hwrs.GetResponseStream();
                StreamReader sr = new StreamReader(myStream, Encoding.Default);
                StringBuilder sb = new StringBuilder();
                while (-1 != sr.Peek())
                {
                    sb.Append(sr.ReadLine() + "\r\n");
                }
                strResult = sb.ToString();
                hwrs.Close();
            }
            catch (Exception ee)
            {
                strResult = ee.Message;
            }
            return strResult;
        }

        /// <summary>
        /// 以POST方式抓取远程页面内容
        /// </summary>
        /// <param name="postData">参数列表</param>
        public static string Post_Http(string url, string postData, string encodeType)
        {
            string strResult = null;
            try
            {
                Encoding encoding = Encoding.GetEncoding(encodeType);
                byte[] POST = encoding.GetBytes(postData);
                HttpWebRequest myRequest = (HttpWebRequest)WebRequest.Create(url);
                myRequest.Method = "POST";
                myRequest.ContentType = "application/x-www-form-urlencoded";
                myRequest.ContentLength = POST.Length;
                Stream newStream = myRequest.GetRequestStream();
                newStream.Write(POST, 0, POST.Length); //设置POST
                newStream.Close();
                HttpWebResponse myResponse = (HttpWebResponse)myRequest.GetResponse();
                StreamReader reader = new StreamReader(myResponse.GetResponseStream(), Encoding.Default);
                strResult = reader.ReadToEnd();
            }
            catch (Exception ex)
            {
                strResult = ex.Message;
            }
            return strResult;
        }
        #endregion

        #region 压缩HTML输出
        /// <summary>
        /// 压缩HTML输出
        /// </summary>
        public static string ZipHtml(string Html)
        {
            Html = Regex.Replace(Html, @">\s+?<", "><");//去除HTML中的空白字符
            Html = Regex.Replace(Html, @"\r\n\s*", "");
            Html = Regex.Replace(Html, @"<body([\s|\S]*?)>([\s|\S]*?)</body>", @"<body$1>$2</body>", RegexOptions.IgnoreCase);
            return Html;
        }
        #endregion

        #region 过滤指定HTML标签
        /// <summary>
        /// 过滤指定HTML标签
        /// </summary>
        /// <param name="s_TextStr">要过滤的字符</param>
        /// <param name="html_Str">a img p div</param>
        public static string DelHtml(string s_TextStr, string html_Str)
        {
            string rStr = "";
            if (!string.IsNullOrEmpty(s_TextStr))
            {
                rStr = Regex.Replace(s_TextStr, "<" + html_Str + "[^>]*>", "", RegexOptions.IgnoreCase);
                rStr = Regex.Replace(rStr, "</" + html_Str + ">", "", RegexOptions.IgnoreCase);
            }
            return rStr;
        }
        #endregion

        #region 加载文件块
        /// <summary>
        /// 加载文件块
        /// </summary>
        public static string File(string Path, System.Web.UI.Page p)
        {
            return @p.ResolveUrl(Path);
        }
        #endregion

        #region 加载CSS样式文件
        /// <summary>
        /// 加载CSS样式文件
        /// </summary>
        public static string CSS(string cssPath, System.Web.UI.Page p)
        {
            return @"<link href=""" + p.ResolveUrl(cssPath) + @""" rel=""stylesheet"" type=""text/css"" />" + "\r\n";
        }
        #endregion

        #region 加载JavaScript脚本文件
        /// <summary>
        /// 加载javascript脚本文件
        /// </summary>
        public static string JS(string jsPath, System.Web.UI.Page p)
        {
            return @"<script type=""text/javascript"" src=""" + p.ResolveUrl(jsPath) + @"""></script>" + "\r\n";
        }
        #endregion
    }
}

例子
比如我们要获取一个网页的源代码
[C#] 纯文本查看 复制代码
   HttpHelper http = new HttpHelper();

            HttpItem item = new HttpItem()
            {
                URL = "http://www.sufeinet.com",//URL     必需项    
            };
            HttpResult result = http.GetHtml(item);

            //这里就是获取到的压缩后的Html了
            string html = HTMLHelper.ZipHtml(result.Html);

其他的方法调用和这个都一样,大家只要传不同的参数就是了。
Ok就到这里有问题跟帖吧



1. 开通SVIP会员,免费下载本站所有源码,不限次数据,不限时间
2. 加官方QQ群,加官方微信群获取更多资源和帮助
3. 找站长苏飞做网站、商城、CRM、小程序、App、爬虫相关、项目外包等点这里
发表于 2014-1-22 08:37:42 | 显示全部楼层
这个不错..
回复

使用道具 举报

发表于 2014-1-22 08:37:48 | 显示全部楼层
真是难得给力的帖子啊,强烈支持楼主。
 楼主| 发表于 2014-1-22 08:40:35 | 显示全部楼层
@Monn @(··)-Dark- 多谢
发表于 2014-1-22 08:41:18 | 显示全部楼层
非常不错的资源,谢谢,辛苦了
发表于 2014-1-22 09:21:50 | 显示全部楼层
哈哈,这个不错,省去了好多工作。。
发表于 2014-1-22 10:29:02 | 显示全部楼层
强烈支持…………
回复

使用道具 举报

发表于 2014-1-22 21:09:25 | 显示全部楼层
膜拜中……

这个类真的不错。飞哥太棒了
发表于 2014-6-24 11:58:55 | 显示全部楼层
我想要获取  指定标签中  的内容 怎么写
 楼主| 发表于 2014-6-24 12:23:18 | 显示全部楼层
ufowiner 发表于 2014-6-24 11:58
我想要获取  指定标签中  的内容 怎么写

你这个去求助里发个帖子吧,说清楚要什么标签里的内容
您需要登录后才可以回帖 登录 | 马上注册

本版积分规则

QQ|手机版|小黑屋|手机版|联系我们|关于我们|广告合作|苏飞论坛 ( 豫ICP备18043678号-2)

GMT+8, 2024-11-8 15:32

© 2014-2021

快速回复 返回顶部 返回列表