Reading multiple html files into folder parse and store into csv file

Jsoup is a Java library for working with real-world HTML. It provides a very convenient API for extracting and manipulating data, using the best of DOM, CSS, and jquery-like methods.

http://jsoup.org/

Example :

import java.io.File;

import java.io.FileWriter;

import java.io.IOException;

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

public class HTMLParser {

public static void main(String[] args) {

Document doc = null;

{

FileWriter writer =null;

System.out.println("--------------------------Program started--------------------------");

try {

writer = new FileWriter("c:\\Temp\\abc_search_data.csv");

       File input = new File("C:\\My Web     Sites\\http___www.abcd.com_\\www.abcd.com\\library\\html\\");

File[] st = input.listFiles();

for (int i = 0; i < st.length; i++) {

if (st[i].isFile()) {// other condition like name ends in

// html

// parse(st[i]);

doc = Jsoup.parse(st[i], null);

// get page title

String title = doc.title();

System.out.println("title : " +"["+i+"]"+ title);

//

String ownText = doc.body().ownText();

String text = doc.body().text();

//

//System.out.println("ownText" + ownText + "\n");

//System.out.println("text" + text);

//

 

     writer.append("title : "+"["+i+"]");

     writer.append(',');

     writer.append(title);

     writer.append('\n');

    /* writer.append("ownText");

     writer.append(',');

     writer.append(ownText);

     writer.append('\n');*/

     

     writer.append("text : "+"["+i+"]");

     writer.append(',');

     writer.append(text);

       writer.append('\n');

}

}

} catch (Exception e) {

e.printStackTrace();

}finally {

try {

writer.flush();

writer.close();

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

}

System.out.println("--------------------------Program End--------------------------");

}

}