Java Implements crawler functionality

/**
* Crawl News information, encapsulated as entity Bean
*/
public class Getnews {
Public list<news> getnews () {
Storing News objects
list<news> list = new arraylist<news> ();
try {
Request DOM Document
Document document = Jsoup.connect ("http://baijia.baidu.com/"). get ();
Analytical
String selector = "H3>a";
Elements titlels = document.select (selector);

for (Element title:titlels) {
System.out.println ("Title---" + title.text ());
Request a tag again to get the content
String url = title.absurl ("href");
Document Document1 = jsoup.connect (URL). get ();
String selecttime = Document1.select ("Span[class=time]"). Text ();
SYSTEM.OUT.PRINTLN ("Time---" + selecttime);
String selectbody = Document1.select (
"Div[class=article-detail]"). Text ();
SYSTEM.OUT.PRINTLN ("Body---" + selectbody);
Make a News object join the list collection
News news = new News ();
News.settitle (Title.text ());
News.setbody (Selectbody);
News.setdate (Selecttime);
List.add (news);
}

} catch (IOException e) {
TODO auto-generated Catch block
E.printstacktrace ();
}

return list;
}

}

/*
* Save the received news object to the database
*/
public int Save (list<news> List) {

  //SQL prefix
  string sql = "INSERT INTO News (title,body,date) values";
  /*
   * This is the fastest way to insert a database
   */
  for (News news:list) {
 & Nbsp; sql = sql + "('" + news.gettitle () + "', '" + news.getbody () + "', '"
     + news.get Date () + "'),";
  }
  sql = sql.substring (0, Sql.length ()-1);
  system.out.println (SQL);
  int rows = basedao.executeupdate (SQL);
  return rows;
 }

/**
* Common tool classes for database connection
*
*/
public class Basedao {
Create need to get JDBC API
protected static Connection Connection = null;
protected static PreparedStatement PS = null;
protected static ResultSet rs = null;

01. Get a database connection
public static Boolean getconnection () {
/**
* Prerequisites for obtaining a 4-factor connection database for a database connection
*/
String Driver = Configmanager.getinstance (). GetValue ("Jdbc.driver");
String URL = configmanager.getinstance (). GetValue ("Jdbc.url");
String userName = Configmanager.getinstance (). GetValue ("Jdbc.username");
String password = configmanager.getinstance (). GetValue ("Jdbc.password");

  try {
   class.forname (driver);//Load driver
   connection = Drivermanager.getconnection (URL, userName, password);
  } catch (ClassNotFoundException e) {
   e.printstacktrace ();
   return false;
  } catch (SQLException e) {
   e.printstacktrace ();
   return false;
  }
  return true;
 }

/**
* 03. Change Executeupdate () returns an int represents the number of rows in the database that are affected by delete from user; Delete from
* User where id=? and name=?;
*/
public static int executeupdate (String sql, Object ... params) {
int rowNum = 0;
if (getconnection ()) {//Operation database affirms existing connection
try {
PS = connection.preparestatement (SQL);
Loop to the SQL statement? Placeholder Assignment
for (int i = 0; i < params.length; i++) {
Ps.setobject (i + 1, params[i]);
}
Execute SQL statement
RowNum = Ps.executeupdate ();
} catch (SQLException e) {
E.printstacktrace ();
} finally {
CloseConnection (); Close connection
}

}

return rowNum;
}

/**
* 04. Query ExecuteQuery () returns resultset select * from user; SELECT * FROM user
* Where id=? and name=?;
*/
public static ResultSet executeQuery (String sql, Object ... params) {
if (getconnection ()) {//Operation database affirms existing connection
try {
PS = connection.preparestatement (SQL);
Loop to the SQL statement? Placeholder Assignment
for (int i = 0; i < params.length; i++) {
Ps.setobject (i + 1, params[i]);
}
Execute SQL statement
rs = Ps.executequery ();
} catch (SQLException e) {
E.printstacktrace ();
}
}
Return RS;
}

02. Releasing Resources
public static Boolean CloseConnection () {
If none of the objects have been created? Can you close it? Non-null judgments must be made
if (rs! = null) {
try {
Rs.close ();
} catch (SQLException e) {
E.printstacktrace ();
return false;
}
}
if (PS! = null) {
try {
Ps.close ();
} catch (SQLException e) {
E.printstacktrace ();
return false;
}
}
if (connection! = null) {
try {
Connection.close ();
} catch (SQLException e) {
E.printstacktrace ();
return false;
}
}
return true;
}

}

/*
* input keyword query fuzzy query
  */
Public list<news> selectnews (String name) {
list<news> list = new arraylist<news> ();
String sql = "SELECT * from the news where title like?";
Object[] params = {"%" + name + "%"};
ResultSet rs = basedao.executequery (sql, params);
try {
Traversing result Sets
while (Rs.next ()) {
Create a News object
News news = new News ();
Get each column of each row
News.setid (Rs.getint ("id"));
News.settitle (rs.getstring ("title"));
News.setbody (rs.getstring ("body"));
News.setdate (rs.getstring ("date"));
List.add (news);
}
} catch (Exception e) {
Todo:handle exception
}
return list;
}

/*
* Single-instance read configuration file tool class
* */

public class ConfigManager {

01. Create your own static objects
private static ConfigManager manager = new ConfigManager ();
private static properties properties;

02. Privatization Structure
Private ConfigManager () {
Get the path to the configuration file
String Path = "Jdbc.properties";
Properties = new properties ();
Create an input stream
InputStream stream = ConfigManager.class.getClassLoader ()
. getResourceAsStream (path);
try {
Properties.load (stream);
} catch (IOException e) {
E.printstacktrace ();
} finally {
try {
Stream.Close ();
} catch (IOException e) {
E.printstacktrace ();
}
}

}

03. Provide an interface for external access
public static synchronized ConfigManager getinstance () {
Return manager;
}

Provides a way to obtain value from key
public static string GetValue (String key) {
return Properties.getproperty (key);
}

}

/*

*properties file

*/

Jdbc.url=jdbc\:mysql\://localhost\:3306/test
Jdbc.username=hhr
Jdbc.password=hhr
Jdbc.driver=com.mysql.jdbc.driver

Java Implements crawler functionality