import java.awt.BorderLayout;
import java.awt.Cursor;
import java.awt.Font;
import java.awt.GridBagConstraints;
import java.awt.GridBagLayout;
import java.awt.Insets;
import java.awt.event.ActionEvent;
import java.awt.event.ActionListener;
import java.awt.event.KeyEvent;
import java.awt.event.WindowAdapter;
import java.awt.event.WindowEvent;
import java.io.BufferedReader;
import java.io.FileWriter;
import java.io.InputStreamReader;
import java.io.PrintWriter;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.LinkedHashSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import javax.swing.BorderFactory;
import javax.swing.JButton;
import javax.swing.JCheckBox;
import javax.swing.JComboBox;
import javax.swing.JFrame;
import javax.swing.JLabel;
import javax.swing.JMenu;
import javax.swing.JMenuBar;
import javax.swing.JMenuItem;
import javax.swing.JOptionPane;
import javax.swing.JPanel;
import javax.swing.JProgressBar;
import javax.swing.JScrollPane;
import javax.swing.JSeparator;
import javax.swing.JTable;
import javax.swing.JTextField;
import javax.swing.table.DefaultTableModel;
// The Search Web Crawler
public class SearchCrawler extends JFrame {
// Max URLs drop-down values.
private static final String[] MAX_URLS = { "50", "100", "500", "1000" };
// Cache of robot disallow lists.
private HashMap disallowListCache = new HashMap();
// Search GUI controls.
private JTextField startTextField;
private JComboBox maxComboBox;
private JCheckBox limitCheckBox;
private JTextField logTextField;
private JTextField searchTextField;
private JCheckBox caseCheckBox;
private JButton searchButton;
// Search stats GUI controls.
private JLabel crawlingLabel2;
private JLabel crawledLabel2;
private JLabel toCrawlLabel2;
private JProgressBar progressBar;
private JLabel matchesLabel2;
// Table listing search matches.
private JTable table;
// Flag for whether or not crawling is underway.
private boolean crawling;
// Matches log file print writer.
private PrintWriter logFileWriter;
// Constructor for Search Web Crawler.
public SearchCrawler() {
// Set application title.
setTitle("Search Crawler");
// Set window size.
setSize(600, 600);
// Handle window closing events.
addWindowListener(new WindowAdapter() {
public void windowClosing(WindowEvent e) {
actionExit();
}
});
// Set up File menu.
JMenuBar menuBar = new JMenuBar();
JMenu fileMenu = new JMenu("File");
fileMenu.setMnemonic(KeyEvent.VK_F);
JMenuItem fileExitMenuItem = new JMenuItem("Exit", KeyEvent.VK_X);
fileExitMenuItem.addActionListener(new ActionListener() {
public void actionPerformed(ActionEvent e) {
actionExit();
}
});
fileMenu.add(fileExitMenuItem);
menuBar.add(fileMenu);
setJMenuBar(menuBar);
// Set up search panel.
JPanel searchPanel = new JPanel();
GridBagConstraints constraints;
GridBagLayout layout = new GridBagLayout();
searchPanel.setLayout(layout);
JLabel startLabel = new JLabel("Start URL:");
constraints = new GridBagConstraints();
constraints.anchor = GridBagConstraints.EAST;
constraints.insets = new Insets(5, 5, 0, 0);
layout.setConstraints(startLabel, constraints);
searchPanel.add(startLabel);
startTextField = new JTextField();
constraints = new GridBagConstraints();
constraints.fill = GridBagConstraints.HORIZONTAL;
constraints.gridwidth = GridBagConstraints.REMAINDER;
constraints.insets = new Insets(5, 5, 0, 5);
layout.setConstraints(startTextField, constraints);
searchPanel.add(startTextField);
JLabel maxLabel = new JLabel("Max URLs to Crawl:");
constraints = new GridBagConstraints();
constraints.anchor = GridBagConstraints.EAST;
constraints.insets = new Insets(5, 5, 0, 0);
layout.setConstraints(maxLabel, constraints);
searchPanel.add(maxLabel);
maxComboBox = new JComboBox(MAX_URLS);
maxComboBox.setEditable(true);
constraints = new GridBagConstraints();
constraints.insets = new Insets(5, 5, 0, 0);
layout.setConstraints(maxComboBox, constraints);
searchPanel.add(maxComboBox);
limitCheckBox = new JCheckBox("Limit crawling to Start URL site");
constraints = new GridBagConstraints();
constraints.anchor = GridBagConstraints.WEST;
constraints.insets = new Insets(0, 10, 0, 0);
layout.setConstraints(limitCheckBox, constraints);
searchPanel.add(limitCheckBox);
JLabel blankLabel = new JLabel();
constraints = new GridBagConstraints();
constraints.gridwidth = GridBagConstraints.REMAINDER;
layout.setConstraints(blankLabel, constraints);
searchPanel.add(blankLabel);
JLabel logLabel = new JLabel("Matches Log File:");
constraints = new GridBagConstraints();
constraints.anchor = GridBagConstraints.EAST;
constraints.insets = new Insets(5, 5, 0, 0);
layout.setConstraints(logLabel, constraints);
searchPanel.add(logLabel);
String file = System.getProperty("user.dir")
+ System.getProperty("file.separator") + "crawler.log";
logTextField = new JTextField(file);
constraints = new GridBagConstraints();
constraints.fill = GridBagConstraints.HORIZONTAL;
constraints.gridwidth = GridBagConstraints.REMAINDER;
constraints.insets = new Insets(5, 5, 0, 5);
layout.setConstraints(logTextField, constraints);
searchPanel.add(logTextField);
JLabel searchLabel = new JLabel("Search String:");
constraints = new GridBagConstraints();
constraints.anchor = GridBagConstraints.EAST;
constraints.insets = new Insets(5, 5, 0, 0);
layout.setConstraints(searchLabel, constraints);
searchPanel.add(searchLabel);
searchTextField = new JTextField();
constraints = new GridBagConstraints();
constraints.fill = GridBagConstraints.HORIZONTAL;
constraints.insets = new Insets(5, 5, 0, 0);
constraints.gridwidth = 2;
constraints.weightx = 1.0d;
layout.setConstraints(searchTextField, constraints);
searchPanel.add(searchTextField);
caseCheckBox = new JCheckBox("Case Sensitive");
constraints = new GridBagConstraints();
constraints.insets = new Insets(5, 5, 0, 5);
constraints.gridwidth = GridBagConstraints.REMAINDER;
layout.setConstraints(caseCheckBox, constraints);
searchPanel.add(caseCheckBox);
searchButton = new JButton("Search");
searchButton.addActionListener(new ActionListener() {
public void actionPerformed(ActionEvent e) {
actionSearch();
}
});
constraints = new GridBagConstraints();
constraints.gridwidth = GridBagConstraints.REMAINDER;
constraints.insets = new Insets(5, 5, 5, 5);
layout.setConstraints(searchButton, constraints);
searchPanel.add(searchButton);
JSeparator separator = new JSeparator();
constraints = new GridBagConstraints();
constraints.fill = GridBagConstraints.HORIZONTAL;
constraints.gridwidth = GridBagConstraints.REMAINDER;
constraints.insets = new Insets(5, 5, 5, 5);
layout.setConstraints(separator, constraints);
searchPanel.add(separator);
JLabel crawlingLabel1 = new JLabel("Crawling:");
constraints = new GridBagConstraints();
constraints.anchor = GridBagConstraints.EAST;
constraints.insets = new Insets(5, 5, 0, 0);
layout.setConstraints(crawlingLabel1, constraints);
searchPanel.add(crawlingLabel1);
crawlingLabel2 = new JLabel();
crawlingLabel2.setFont(crawlingLabel2.getFont().deriveFont(Font.PLAIN));
constraints = new GridBagConstraints();
constraints.fill = GridBagConstraints.HORIZONTAL;
constraints.gridwidth
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
SearchCrawler.zip (1个子文件)
SearchCrawler.java 27KB
共 1 条
- 1
资源评论
- sinat_317552492015-10-15就是没有说明
- mingchun20022012-12-13带说明就更好了
- duduli20012013-05-12代码。很不错
飞奔的兔子鸡
- 粉丝: 15
- 资源: 4
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 论文(最终)_20240430235101.pdf
- 基于python编写的Keras深度学习框架开发,利用卷积神经网络CNN,快速识别图片并进行分类
- 最全空间计量实证方法(空间杜宾模型和检验以及结果解释文档).txt
- 5uonly.apk
- 蓝桥杯Python组的历年真题
- 2023-04-06-项目笔记 - 第一百十九阶段 - 4.4.2.117全局变量的作用域-117 -2024.04.30
- 2023-04-06-项目笔记 - 第一百十九阶段 - 4.4.2.117全局变量的作用域-117 -2024.04.30
- 前端开发技术实验报告:内含4四实验&实验报告
- Highlight Plus v20.0.1
- 林周瑜-论文.docx
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功