本文实例讲述了C#实现抓取和分析网页类。分享给大家供大家参考。具体分析如下：
这里介绍了抓取和分析网页的类。
其主要功能有：
1、提取网页的纯文本，去所有html标签和javascript代码
2、提取网页的链接，包括href和frame及iframe
3、提取网页的title等(其它的标签可依此类推，正则是一样的)
4、可以实现简单的表单提交及cookie保存
?
1 2 3 4 5 6 7 8 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 using System; using System.Data; using System.Configuration; using System.Net; using System.IO; using System.Text; using System.Collections.Generic; using System.Text.Regularexpressions; using System.Threading; using System.Web; /// <summary> /// 网页类 /// </summary> public class WebPage { #region 私有成员 private Uri m_uri; //网址 private List<link> m_links; //此网页上的链接 private string m_title; //此网页的标题 private string m_html; //此网页的HTML代码 private string m_outstr; //此网页可输出的纯文本 private bool m_good; //此网页是否可用 private int m_pagesize; //此网页的大小 private static Dictionary<string, cookieContainer> webcookies = new Dictionary<string, cookieContainer>();//存放所有网页的cookie private string m_post; //此网页的登陆页需要的POST数据 private string m_loginurl; //此网页的登陆页 #endregion #region 私有方法 /// <summary> /// 这私有方法从网页的HTML代码中分析出链接信息 /// </summary> /// <returns>List<link></returns> private List<link> getlinks() { if (m_links.Count == 0) { Regex[] regex = new Regex[2]; regex[0] = new Regex("(?m)<a[^><]+href=http://www.shancun.net/skin/default/image/nopic.gif')?(?<url>([^>"'s)])+)http://www.shancun.net/skin/default/image/nopic.gif')?[^>]*>(?<text>(w|W)*?)</", RegexOptions.Multiline | RegexOptions.IgnoreCase); regex[1] = new Regex("<[i]*frame[^><]+src=http://www.shancun.net/skin/default/image/nopic.gif')?(?<url>([^>"'s)])+)http://www.shancun.net/skin/default/image/nopic.gif')?[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase); for (int i = 0; i < 2; i++) { Match match = regex[i].Match(m_html); while (match.Success) { try { string url = new Uri(m_uri, match.Groups["url"].Value).AbsoluteUri; string text = ""; if (i == 0) text = new Regex("(<[^>]+>)|(s)|( )|&|"", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(match.Groups["text"].Value, ""); link link = new link(url, text); m_links.Add(link); } catch(Exception ex){Console.WriteLine(ex.Message); }; match = match.NextMatch(); } } } return m_links; } /// <summary> /// 此私有方法从一段HTML文本中提取出一定字数的纯文本 /// </summary> /// <param name="instr">HTML代码</param> /// <param name="firstN">提取从头数多少个字</param> /// <param name="withlink">是否要链接里面的字</param> /// <returns>纯文本</returns> private string getFirstNchar(string instr, int firstN, bool withlink) { if (m_outstr == "") { m_outstr = instr.Clone() as string; m_outstr = new Regex(@"(?m)<script[^>]*>(w|W)*?</script[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase ).Replace(m_outstr, ""); m_outstr = new Regex(@"(?m)<style[^>]*>(w|W)*?</style[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase ).Replace(m_outstr, ""); m_outstr = new Regex(@"(?m)<select[^>]*>(w|W)*?</select[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase ).Replace(m_outstr, ""); if (!withlink) m_outstr = new Regex(@"(?m)<a[^>]*>(w|W)*?</a[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, ""); Regex objReg = new System.Text.Regularexpressions.Regex("(<[^>]+?>)| ", RegexOptions.Multiline | RegexOptions.IgnoreCase); m_outstr = objReg.Replace(m_outstr, ""); Regex objReg2 = new System.Text.Regularexpressions.Regex("(s)+", RegexOptions.Multiline | RegexOptions.IgnoreCase); m_outstr = objReg2.Replace(m_outstr, " "); } return m_outstr.Length > firstN ? m_outstr.Substring(0, firstN) : m_outstr; } /// <summary> /// 此私有方法返回一个IP地址对应的无符号整数 /// </summary> /// <param name="x">IP地址</param> /// <returns></returns> private uint getuintFromIP(IPAddress x) { Byte[] bt = x.GetAddressBytes(); uint i = (uint)(bt[0] * 256 * 256 * 256); i += (uint)(bt[1] * 256 * 256); i += (uint)(bt[2] * 256); i += (uint)(bt[3]); return i; } #endregion #region 公有文法 /// <summary> /// 此公有方法提取网页中一定字数的纯文本，包括链接文字 /// </summary> /// <param name="firstN">字数</param> /// <returns></returns> public string getContext(int firstN) { return getFirstNchar(m_html, firstN, true); } /// <summary> /// 此公有方法提取网页中一定字数的纯文本，不包括链接文字 /// </summary> /// <param name="firstN"></param> /// <returns></returns> public string getContextWithOutlink(int firstN) { return getFirstNchar(m_html, firstN, false); } /// <summary> /// 此公有方法从本网页的链接中提取一定数量的链接，该链接的URL满足某正则式 /// </summary> /// <param name="pattern">正则式</param> /// <param name="count">返回的链接的个数</param> /// <returns>List<link></returns> public List<link> getSpeciallinksByUrl(string pattern,int count) { if(m_links.Count==0)getlinks(); List<link> Speciallinks = new List<link>(); List<link>.Enumerator i; i = m_links.GetEnumerator(); int cnt = 0; while (i.MoveNext() && cnt<count) { if (new Regex(pattern, RegexOptions.Multiline | RegexOptions.IgnoreCase ).Match(i.Current.url).Success) { Speciallinks.Add(i.Current); cnt++; } } return Speciallinks; } /// <summary> /// 此公有方法从本网页的链接中提取一定数量的链接，该链接的文字满足某正则式 /// </summary> /// <param name="pattern">正则式</param> /// <param name="count">返回的链接的个数</param> /// <returns>List<link></returns> public List<link> getSpeciallinksByText(string pattern,int count) { if (m_links.Count == 0) getlinks(); List<link> Speciallinks = new List<link>(); List<link>.Enumerator i; i = m_links.GetEnumerator(); int cnt = 0; while (i.MoveNext() && cnt < count) { if (new Regex(pattern, RegexOptions.Multiline | RegexOptions.IgnoreCase ).Match(i.Current.text).Success) { Speciallinks.Add(i.Current); cnt++; } } return Speciallinks; } /// <summary> /// 此公有方法获得所有链接中在一定IP范围的链接 /// </summary> /// <param name="_ip_start">起始IP</param> /// <param name="_ip_end">终止IP</param> /// <returns></returns> public List<link> getSpeciallinksByIP(string _ip_start, string _ip_end) { IPAddress ip_start = IPAddress.Parse(_ip_start); IPAddress ip_end = IPAddress.Parse(_ip_end); if (m_links.Count == 0) getlinks(); List<link> Speciallinks = new List<link>(); List<link>.Enumerator i; i = m_links.GetEnumerator(); while (i.MoveNext()) { IPAddress ip; try { ip = Dns.GetHostEntry(new Uri(i.Current.url).Host).AddressList[0]; } catch { continue; } if(getuintFromIP(ip)>=getuintFromIP(ip_start) && getuintFromIP(ip)<=getuintFromIP(ip_end)) { Speciallinks.Add(i.Current); } } return Speciallinks; } /// <summary> /// 这公有方法提取本网页的纯文本中满足某正则式的文字 /// </summary> /// <param name="pattern">正则式</param> /// <returns>返回文字</returns> public string getSpecialWords(string pattern) { if (m_outstr == "") getContext(Int16.MaxValue); Regex regex = new Regex(pattern, RegexOptions.Multiline | RegexOptions.IgnoreCase ); Match mc=regex.Match(m_outstr); if (mc.Success) return mc.Groups[1].Value; return string.Empty; } #endregion #region 构造函数 private void Init(string _url) { try { m_uri = new Uri(_url); m_links = new List<link>(); m_html = ""; m_outstr = ""; m_title = ""; m_good = true; if (_url.EndsWith(".rar") || _url.EndsWith(".dat") || _url.EndsWith(".msi")) { m_good = false; return; } HttpWebRequest rqst = (HttpWebRequest)WebRequest.Create(m_uri); rqst.AllowAutoRedirect = true; rqst.MaximumAutomaticRedirections = 3; rqst.UserAgent = "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)"; rqst.KeepAlive = true; rqst.Timeout = 30000; lock (WebPage.webcookies) { if (WebPage.webcookies.ContainsKey(m_uri.Host)) rqst.cookieContainer = WebPage.webcookies[m_uri.Host]; else { cookieContainer cc = new cookieContainer(); WebPage.webcookies[m_uri.Host] = cc; rqst.cookieContainer = cc; } } HttpWebResponse rsps = (HttpWebResponse)rqst.GetResponse(); Stream sm = rsps.GetResponseStream(); if (!rsps.ContentType.ToLower().StartsWith("text/") || rsps.ContentLength > 1 << 22) { rsps.Close(); m_good = false; return; } Encoding cding = System.Text.Encoding.Default; string contenttype=rsps.ContentType.ToLower(); int ix = contenttype.IndexOf("charset="); if (ix != -1) { try { cding = System.Text.Encoding.GetEncoding(rsps.ContentType.Substring(ix + "charset".Length + 1)); } catch { cding = Encoding.Default; } m_html = new StreamReader(sm, cding).ReadToEnd(); } else { m_html = new StreamReader(sm, cding).ReadToEnd(); Regex regex = new Regex("charset=(?<cding>[^=]+)?"",RegexOptions.IgnoreCase); string strcding = regex.Match(m_html).Groups["cding"].Value; try { cding = Encoding.GetEncoding(strcding); } catch{ cding = Encoding.Default; } byte[] bytes=Encoding.Default.GetBytes(m_html.ToCharArray()); m_html = cding.GetString(bytes); if (m_html.Split('?').Length > 100) { m_html=Encoding.Default.GetString(bytes); } } m_pagesize = m_html.Length; m_uri = rsps.ResponseUri; rsps.Close(); } catch (Exception ex) { Console.WriteLine(ex.Message+m_uri.ToString()); m_good = false; } } public WebPage(string _url) { string uurl = ""; try { uurl = Uri.UnescapeDataString(_url); _url = uurl; } catch { }; Regex re = new Regex("(?<h>[^x00-xff]+)"); Match mc = re.Match(_url); if (mc.Success) { string han = mc.Groups["h"].Value; _url = _url.Replace(han, System.Web.HttpUtility.UrlEncode(han, Encoding.GetEncoding("GB2312"))); } Init(_url); } public WebPage(string _url, string _loginurl, string _post) { string uurl = ""; try { uurl = Uri.UnescapeDataString(_url); _url = uurl; } catch { }; Regex re = new Regex("(?<h>[^x00-xff]+)"); Match mc = re.Match(_url); if (mc.Success) { string han = mc.Groups["h"].Value; _url = _url.Replace(han, System.Web.HttpUtility.UrlEncode(han, Encoding.GetEncoding("GB2312"))); } if (_loginurl.Trim() == "" || _post.Trim() == "" || WebPage.webcookies.ContainsKey(new Uri(_url).Host)) { Init(_url); } else { #region 登陆 string indata = _post; m_post = _post; m_loginurl = _loginurl; byte[] bytes = Encoding.Default.GetBytes(_post); cookieContainer mycookieContainer = new cookieContainer(); try { //新建一个cookieContainer来存放cookie集合 HttpWebRequest myHttpWebRequest = (HttpWebRequest)WebRequest.Create(_loginurl); //新建一个HttpWebRequest myHttpWebRequest.ContentType = "application/x-www-form-urlencoded"; myHttpWebRequest.AllowAutoRedirect = false; myHttpWebRequest.UserAgent = "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)"; myHttpWebRequest.Timeout = 60000; myHttpWebRequest.KeepAlive = true; myHttpWebRequest.ContentLength = bytes.Length; myHttpWebRequest.Method = "POST"; myHttpWebRequest.cookieContainer = mycookieContainer; //设置HttpWebRequest的cookieContainer为刚才建立的那个mycookieContainer Stream myRequestStream = myHttpWebRequest.GetRequestStream(); myRequestStream.Write(bytes, 0, bytes.Length); myRequestStream.Close(); HttpWebResponse myHttpWebResponse = (HttpWebResponse)myHttpWebRequest.GetResponse(); foreach (cookie ck in myHttpWebResponse.cookies) { mycookieContainer.Add(ck); } myHttpWebResponse.Close(); } catch { Init(_url); return; } #endregion #region 登陆后再访问页面 try { m_uri = new Uri(_url); m_links = new List<link>(); m_html = ""; m_outstr = ""; m_title = ""; m_good = true; if (_url.EndsWith(".rar") || _url.EndsWith(".dat") || _url.EndsWith(".msi")) { m_good = false; return; } HttpWebRequest rqst = (HttpWebRequest)WebRequest.Create(m_uri); rqst.AllowAutoRedirect = true; rqst.MaximumAutomaticRedirections = 3; rqst.UserAgent = "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)"; rqst.KeepAlive = true; rqst.Timeout = 30000; rqst.cookieContainer = mycookieContainer; lock (WebPage.webcookies) { WebPage.webcookies[m_uri.Host] = mycookieContainer; } HttpWebResponse rsps = (HttpWebResponse)rqst.GetResponse(); Stream sm = rsps.GetResponseStream(); if (!rsps.ContentType.ToLower().StartsWith("text/") || rsps.ContentLength > 1 << 22) { rsps.Close(); m_good = false; return; } Encoding cding = System.Text.Encoding.Default; int ix = rsps.ContentType.ToLower().IndexOf("charset="); if (ix != -1) { try { cding = System.Text.Encoding.GetEncoding(rsps.ContentType.Substring(ix + "charset".Length + 1)); } catch { cding = Encoding.Default; } } m_html = new StreamReader(sm, cding).ReadToEnd(); m_pagesize = m_html.Length; m_uri = rsps.ResponseUri; rsps.Close(); } catch (Exception ex) { Console.WriteLine(ex.Message+m_uri.ToString()); m_good = false; } #endregion } } #endregion #region 属性 /// <summary> /// 通过此属性可获得本网页的网址，只读 /// </summary> public string URL { get { return m_uri.AbsoluteUri; } } /// <summary> /// 通过此属性可获得本网页的标题，只读 /// </summary> public string Title { get { if (m_title == "") { Regex reg = new Regex(@"(?m)<title[^>]*>(?<title>(?:w|W)*?)</title[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase ); Match mc = reg.Match(m_html); if (mc.Success) m_title= mc.Groups["title"].Value.Trim(); } return m_title; } } /// <summary> /// 此属性获得本网页的所有链接信息，只读 /// </summary> public List<link> links { get { if (m_links.Count == 0) getlinks(); return m_links; } } /// <summary> /// 此属性返回本网页的全部纯文本信息，只读 /// </summary> public string Context { get { if (m_outstr == "") getContext(Int16.MaxValue); return m_outstr; } } /// <summary> /// 此属性获得本网页的大小 /// </summary> public int PageSize { get { return m_pagesize; } } /// <summary> /// 此属性获得本网页的所有站内链接 /// </summary> public List<link> Insitelinks { get { return getSpeciallinksByUrl("^http://"+m_uri.Host,Int16.MaxValue); } } /// <summary> /// 此属性表示本网页是否可用 /// </summary> public bool IsGood { get { return m_good; } } /// <summary> /// 此属性表示网页的所在的网站 /// </summary> public string Host { get { return m_uri.Host; } } /// <summary> /// 此网页的登陆页所需的POST数据 /// </summary> public string PostStr { get { return m_post; } } /// <summary> /// 此网页的登陆页 /// </summary> public string LoginURL { get { return m_loginurl; } } #endregion } /// <summary> /// 链接类 /// </summary> public class link { public string url; //链接网址 public string text; //链接文字 public link(string _url, string _text) { url = _url; text = _text; } }希望本文所述对大家的C#程序设计有所帮助。
