隔壁宿舍菜鸟学JAVA遇到了一个问题，在网上下载了一个JAVA帮助文档（也就和MSDN差不多的东西），十几万条信息，愣是按照首字母的顺序，排列成了27个静态网页，没有查询功能，该菜鸟每次写程序时都为查询烧透了脑筋。于是找到了我，求我给做个搜索功能。要回家了，没多少时间，所以只建了个索引表。 using System;using System.Text.RegularExpressions;using System.Net;using System.IO;using System.Text;using System.Xml;using System.Xml.Schema;using System.Xml.XPath;using System.Collections;using System.Data.SqlClient; public class search{    public static string ClientPage;   public static string infor;   public static string keys;   public static HttpWebRequest HttpWReq;   public static HttpWebResponse HttpWRes;   public static MatchCollection m;   public static MatchCollection m2;    public static Encoding GetEncoding(HttpWebResponse response)    {        string name = response.ContentEncoding;        Encoding code = Encoding.Default;        if (name == "")        {            string contentType = response.ContentType;            if (contentType.ToLower().IndexOf("charset") != -1)            {                name = contentType.Substring(contentType.ToLower().IndexOf("charset=") + "charset=".Length);            }        }         if (name != "")        {            try            {                code = Encoding.GetEncoding(name);            }            catch { }        }        return code;    }     public static string TextContent(HttpWebResponse response)    {        string buffer = "", line;         Stream stream = response.GetResponseStream();        StreamReader reader = new StreamReader(stream, GetEncoding(response));         //buffer = "<base href=http://localhost:1080 />";        while ((line = reader.ReadLine()) != null)        {             buffer += line + "\r\n";        }        stream.Close();         return buffer;    }     public static void insert_xml(string k, string t)    {         XmlDocument xmlDoc = new XmlDocument();        xmlDoc.Load("G://webroot/dotnet/api/index-files/java.xml");        XmlNode node = xmlDoc.SelectSingleNode("elements");         XmlElement xe = xmlDoc.CreateElement("element");        XmlElement xe1 = xmlDoc.CreateElement("key");        XmlElement xe2 = xmlDoc.CreateElement("detail");           xe1.InnerText = k;        xe.AppendChild(xe1);        xe2.InnerText = t;        xe.AppendChild(xe2);        node.AppendChild(xe);         xmlDoc.Save("G://webroot/dotnet/api/index-files/java.xml");    }    /// <summary>    /// /////    /// </summary>     public static void seek(string url)    {        /*         HttpWReq = (HttpWebRequest)WebRequest.Create(url);         HttpWReq.Timeout = 20000;         HttpWRes = (HttpWebResponse)HttpWReq.GetResponse();          */        ClientPage = new StreamReader((System.IO.Stream)File.OpenRead(url), System.Text.Encoding.GetEncoding("gb2312")).ReadToEnd();        string dl = @"\<DT\>.*DD[^。;]*(;|。)";        //show.Text="";        m = Regex.Matches(ClientPage, dl, RegexOptions.IgnoreCase | RegexOptions.IgnorePatternWhitespace | RegexOptions.ExplicitCapture);        //show.Text += m.Count.ToString()+"<br>";         for (int i = 0; i < m.Count; i++)        {            m2 = Regex.Matches(m[i].Value, @"\<B\>[^\<]*\</B\>", RegexOptions.IgnoreCase | RegexOptions.IgnorePatternWhitespace | RegexOptions.ExplicitCapture);            if (m2.Count > 0) keys = Regex.Replace(m2[0].Value, "<[^>]*>", "");            else keys = "No Keys!";            //show.Text += "<font color=red>"+(i+1).ToString()+"</font> ."+"<font color=green>"+keys+"</font>" + m[i].Value + "</DD></DT><br>";            insert_xml(keys, m[i].Value + "</DD></DT>");        }     }    public static void Main()    {        for (int i = 1; i <= 27; i++)        {            Console.WriteLine("seeking page: " + i.ToString() + ".......");             seek("G://webroot/dotnet/api/index-files/index-" + i.ToString() + ".html");        }    }} 索引表：

评论