Java用正則表達式如何讀取網(wǎng)頁內(nèi)容

package com.xiaofeng.picup;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/** *//**
*
* @抓取頁面文章標題及內(nèi)容（測試） 手動輸入網(wǎng)址抓取，可進一步自動抓取整個頁面的全部內(nèi)容
*
*/
public class WebContent ...{
  /** *//**
   * 讀取一個網(wǎng)頁全部內(nèi)容
   */
  public String getOneHtml(String htmlurl) throws IOException...{
    URL url;
    String temp;
    StringBuffer sb = new StringBuffer();
    try ...{
      url = new URL(htmlurl);
      BufferedReader in = new BufferedReader(new InputStreamReader(url
          .openStream(), "utf-8"));// 讀取網(wǎng)頁全部內(nèi)容
      while ((temp = in.readLine()) != null) ...{
        sb.append(temp);
      }
      in.close();
    }catch(MalformedURLException me)...{
      System.out.println("你輸入的URL格式有問題！請仔細輸入");
      me.getMessage();
      throw me;
    }catch (IOException e) ...{
      e.printStackTrace();
      throw e;
    }
    return sb.toString();
  }
  /** *//**
   *
   * @param s
   * @return 獲得網(wǎng)頁標題
   */
  public String getTitle(String s) ...{
    String regex;
    String title = "";
    ListString> list = new ArrayListString>();
    regex = "title>.*?/title>";
    Pattern pa = Pattern.compile(regex, Pattern.CANON_EQ);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    for (int i = 0; i  list.size(); i++) ...{
      title = title + list.get(i);
    }
    return outTag(title);
  }
  /** *//**
   *
   * @param s
   * @return 獲得鏈接
   */
  public ListString> getLink(String s) ...{
    String regex;
    ListString> list = new ArrayListString>();
    regex = "a[^>]*href=("([^"]*)"|'([^']*)'|([^s>]*))[^>]*>(.*?)/a>";
    Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  /** *//**
   *
   * @param s
   * @return 獲得腳本代碼
   */
  public ListString> getScript(String s) ...{
    String regex;
    ListString> list = new ArrayListString>();
    regex = "script.*?/script>";
    Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  /** *//**
   *
   * @param s
   * @return 獲得CSS
   */
  public ListString> getCSS(String s) ...{
    String regex;
    ListString> list = new ArrayListString>();
    regex = "style.*?/style>";
    Pattern pa = Pattern.compile(regex, Pattern.DOTALL);
    Matcher ma = pa.matcher(s);
    while (ma.find()) ...{
      list.add(ma.group());
    }
    return list;
  }
  /** *//**
   *
   * @param s
   * @return 去掉標記
   */
  public String outTag(String s) ...{
    return s.replaceAll(".*?>", "");
  }