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

?

01

02

03

04

05

06

07

08

09

10

11

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

[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

?

01

02

03

04

05

06

07

08

09

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

/// <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>

usingSystem;

usingSystem.Text;

usingSystem.Net;

usingSystem.IO;

usingSystem.Threading;

usingSystem.Text.RegularExpressions;

 

namespaceDotNet.Utilities

{

    publicclassHTMLHelper

    {

        #region 私有字段

        privatestaticCookieContainer cc = newCookieContainer();

        privatestaticstring contentType = "application/x-www-form-urlencoded";

        privatestaticstring 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, */*";

        privatestaticstring 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)";

        privatestaticEncoding encoding = Encoding.GetEncoding("utf-8");

        privatestaticint delay = 1000;

        privatestaticint maxTry = 300;

        privatestaticint currentTry = 0;

        #endregion

 

        #region 公有属性

        /// <summary>

        /// Cookie

        /// </summary>

        publicstaticCookieContainer CookieContainer

        {

            get

            {

                returncc;

            }

        }

 

        /// <summary>

        /// 语言

        /// </summary>

        publicstaticEncoding Encoding

        {

            get

            {

                returnencoding;

            }

            set

            {

                encoding = value;

            }

        }

 

        publicstaticint NetworkDelay

        {

            get

            {

                Random r = newRandom();

                return(r.Next(delay, delay * 2));

            }

            set

            {

                delay = value;

            }

        }

 

        publicstaticint MaxTry

        {

            get

            {

                returnmaxTry;

            }

            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>

        publicstaticstring GetHtml(stringurl,stringpostData,boolisPost, CookieContainer cookieContainer)

        {

            if(string.IsNullOrEmpty(postData))returnGetHtml(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 = newStreamReader(responseStream, encoding);

                stringhtml = streamReader.ReadToEnd();

                streamReader.Close();

                responseStream.Close();

                currentTry = 0;

                httpWebRequest.Abort();

                httpWebResponse.Close();

                returnhtml;

            }

            catch(Exception e)

            {

                if(currentTry <= maxTry) GetHtml(url, postData, isPost, cookieContainer);

                currentTry--;

                if(httpWebRequest != null) httpWebRequest.Abort();

                if(httpWebResponse != null) httpWebResponse.Close();

                returnstring.Empty;

            }

        }

 

        /// <summary>

        /// 获取HTML

        /// </summary>

        /// <param name="url">地址</param>

        /// <param name="cookieContainer">CookieContainer</param>

        publicstaticstring GetHtml(stringurl, 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 = newStreamReader(responseStream, encoding);

                stringhtml = streamReader.ReadToEnd();

                streamReader.Close();

                responseStream.Close();

                currentTry--;

                httpWebRequest.Abort();

                httpWebResponse.Close();

                returnhtml;

            }

            catch(Exception e)

            {

                if(currentTry <= maxTry) GetHtml(url, cookieContainer);

                currentTry--;

                if(httpWebRequest != null) httpWebRequest.Abort();

                if(httpWebResponse != null) httpWebResponse.Close();

                returnstring.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>

        publicstaticStream GetStream(stringurl, 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--;

                returnresponseStream;

            }

            catch(Exception e)

            {

                if(currentTry <= maxTry)

                {

                    GetHtml(url, cookieContainer);

                }

 

                currentTry--;

 

                if(httpWebRequest != null)

                {

                    httpWebRequest.Abort();

                }if(httpWebResponse != null)

                {

                    httpWebResponse.Close();

                }

                returnnull;

            }

        }

        #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>  

        publicstaticstring NoHTML(stringHtmlstring)

        {

            //删除脚本  

            Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>","", RegexOptions.IgnoreCase);

 

            //删除HTML  

            Regex regex = newRegex("<.+?>", 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","");

 

            returnHtmlstring;

        }

        #endregion

 

        #region 匹配页面的链接

        /// <summary>

        /// 获取页面的链接正则

        /// </summary>

        publicstringGetHref(stringHtmlCode)

        {

            stringMatchVale = "";

            stringReg = @"(h|H)(r|R)(e|E)(f|F) *= *('|"")?((\w|\\|\/|\.|:|-|_)+)[\S]*";

            foreach(Match m inRegex.Matches(HtmlCode, Reg))

            {

                MatchVale += (m.Value).ToLower().Replace("href=","").Trim() + "|";

            }

            returnMatchVale;

        }

        #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>

        publicstringGetImgSrc(stringHtmlCode,stringimgHttp)

        {

            stringMatchVale = "";

            stringReg = @"<img.+?>";

            foreach(Match m inRegex.Matches(HtmlCode.ToLower(), Reg))

            {

                MatchVale += GetImg((m.Value).ToLower().Trim(), imgHttp) + "|";

            }

 

            returnMatchVale;

        }

 

        /// <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>

        publicstringGetImg(stringImgString,stringimgHttp)

        {

            stringMatchVale = "";

            stringReg = @"src=.+\.(bmp|jpg|gif|png|)";

            foreach(Match m inRegex.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>

        publicstaticstring Get_Http(stringtUrl)

        {

            stringstrResult;

            try

            {

                HttpWebRequest hwr = (HttpWebRequest)HttpWebRequest.Create(tUrl);

                hwr.Timeout = 19600;

                HttpWebResponse hwrs = (HttpWebResponse)hwr.GetResponse();

                Stream myStream = hwrs.GetResponseStream();

                StreamReader sr = newStreamReader(myStream, Encoding.Default);

                StringBuilder sb = newStringBuilder();

                while(-1 != sr.Peek())

                {

                    sb.Append(sr.ReadLine() + "\r\n");

                }

                strResult = sb.ToString();

                hwrs.Close();

            }

            catch(Exception ee)

            {

                strResult = ee.Message;

            }

            returnstrResult;

        }

 

        /// <summary>

        /// 以POST方式抓取远程页面内容

        /// </summary>

        /// <param name="postData">参数列表</param>

        publicstaticstring Post_Http(stringurl,stringpostData,stringencodeType)

        {

            stringstrResult = 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 = newStreamReader(myResponse.GetResponseStream(), Encoding.Default);

                strResult = reader.ReadToEnd();

            }

            catch(Exception ex)

            {

                strResult = ex.Message;

            }

            returnstrResult;

        }

        #endregion

 

        #region 压缩HTML输出

        /// <summary>

        /// 压缩HTML输出

        /// </summary>

        publicstaticstring ZipHtml(stringHtml)

        {

            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);

            returnHtml;

        }

        #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>

        publicstaticstring DelHtml(strings_TextStr,stringhtml_Str)

        {

            stringrStr = "";

            if(!string.IsNullOrEmpty(s_TextStr))

            {

                rStr = Regex.Replace(s_TextStr, "<"+ html_Str + "[^>]*>","", RegexOptions.IgnoreCase);

                rStr = Regex.Replace(rStr, "</"+ html_Str + ">","", RegexOptions.IgnoreCase);

            }

            returnrStr;

        }

        #endregion

 

        #region 加载文件块

        /// <summary>

        /// 加载文件块

        /// </summary>

        publicstaticstring File(stringPath, System.Web.UI.Page p)

        {

            [e-mail](Path);

        }

        #endregion

 

        #region 加载CSS样式文件

        /// <summary>

        /// 加载CSS样式文件

        /// </summary>

        publicstaticstring CSS(stringcssPath, 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>

        publicstaticstring JS(stringjsPath, 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

?

01

02

03

04

05

06

07

08

09

10

HttpHelper http = newHttpHelper();

 

         HttpItem item = newHttpItem()

         {

             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

         stringhtml = 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