利用正則表達(dá)式抓取博客園列表數(shù)據(jù)

public class BlogRegexController : Controller
   {
     public void ExecuteRegex()
     {
       string strBaseUrl = "http://www.cnblogs.com/p"; //定義博客園可以訪問的列表數(shù)據(jù)的基地址
       for (int i = ; i = ; i++)//因?yàn)椴┛蛨@首頁列表最大只有頁，所以我們這個循環(huán)就執(zhí)行次
       {
         string strUrl = strBaseUrl + i.ToString();
         BlogRege blogRegex = new BlogRege(); //定義的具體的Regex類 抓取博客園地址
         string result = blogRegex.SendUrl(strUrl);
         blogRegex.AnalysisHtml(result);
 
         Response.Write("獲取成功");
       }
     }
 
     //
     // GET: /BlogRegex/
 
     public ActionResult Index()
     {
       ExecuteRegex();
       return View();
     }
 
   }

public class BlogRege
   {   //負(fù)責(zé)把數(shù)據(jù)插入到數(shù)據(jù)庫中 使用到的是sqlhelper類
     public void Insert(string title, string content,string linkurl, int categoryID = )
     {
       SqlHelper helper = new SqlHelper();
       helper.Insert(title, content, categoryID,linkurl);
     }
     /// summary>
     /// 通過Url地址獲取具體網(wǎng)頁內(nèi)容 發(fā)起一個請求獲得html內(nèi)容
     /// /summary>
     /// param name="strUrl">/param>
     /// returns>/returns>
     public string SendUrl(string strUrl)
     {
       try
       {
         WebRequest webRequest = WebRequest.Create(strUrl);
         WebResponse webResponse = webRequest.GetResponse();
         StreamReader reader = new StreamReader(webResponse.GetResponseStream());
         string result = reader.ReadToEnd();
         return result;
       }
       catch (Exception ex)
       {
         throw ex;
       }
     }
     /// summary>
     /// 分析Html 解析出里面具體的數(shù)據(jù)
     /// /summary>
     /// param name="htmlContent">/param>
     public void AnalysisHtml(string htmlContent)
     {//這個就是我在regulator正則表達(dá)式工具中拼接獲取到的正則表達(dá)式 還有一點(diǎn)請注意就是轉(zhuǎn)義字符的問題
       string strPattern = "div\\s*class=\"post_item\">\\s*.*\\s*.*\\s*.*\\s*.*\\s*.*\\s*.*\\s*.*\\s*div\\s*class=\"post_item_body\">\\s*h>a\\s*class=\"titlelnk\"\\s*href=\"(?href>.*)\"\\s*target=\"_blank\">(?title>.*)/a>.*\\s*p\\s*class=\"post_item_summary\">\\s*(?content>.*)\\s*/p>";
       Regex regex = new Regex(strPattern, RegexOptions.IgnoreCase | RegexOptions.Multiline | RegexOptions.CultureInvariant);
       if (regex.IsMatch(htmlContent))
       {
         MatchCollection matchCollection = regex.Matches(htmlContent);
         foreach (Match match in matchCollection)
         {
           string title = match.Groups[].Value;//獲取到的是列表數(shù)據(jù)的標(biāo)題
           string content = match.Groups[].Value;//獲取到的是內(nèi)容
           string linkurl=match.Groups[].Value;//獲取到的是鏈接到的地址
          Insert(title, content,linkurl);//執(zhí)行插入到數(shù)據(jù)庫的操作
         }
       }
     }
   }