java-bbcNews-scraper
---------
import java.io.*;
import java.util.Scanner;
import org.jsoup.*;
import org.jsoup.nodes.*;
import java.util.regex.Pattern;
import java.util.regex.Matcher;


public class Scraper{
	public static void main (String[] args){
		// initialize primitive objects
		int choice;
		String finalHOutput;
		String finalSOutput;
		String finalDOutput;
		String output;
		String selection = "http://www.bbc.co.uk/news/uk/"; // given default value

		// initialize complex objects
		HeadlineRegex headlineRegex = new HeadlineRegex();
		SummaryRegex summaryRegex = new SummaryRegex();
		DateRegex dateRegex = new DateRegex();
		RegexVisitor visitor = new RegexVisitor();

		// take user input
		System.out.println("What kind of news story would you like to scrape?\n"
							+ "Press: 1 for UK, 2 for Business,\n 3 for Politics, "
							+ "4 for Tech,\n 5 for Science, or 6 for Health... ");
		Scanner reader = new Scanner(System.in);
		choice = reader.nextInt();

		// alter selection to fit user choice
		switch (choice){
			case (1):
				selection = "http://www.bbc.co.uk/news/uk/";
				break;
			case (2):
				selection = "http://bbc.co.uk/news/business/";
				break;
			case (3):
				selection = "http://bbc.co.uk/news/politics/";
				break;
			case (4):
				selection = "http://bbc.co.uk/news/technology/";
				break;
			case (5):
				selection = "http://bbc.co.uk/news/science_and_environment/";
				break;
			case (6):
				selection = "http://bbc.co.uk/news/health/";
				break;
		}

		// create new object of Document class and scrape HTML to populate it
		Document doc = null;
		try {
   			doc = Jsoup.connect(selection).get();
		} catch (IOException ioe) {
   			ioe.printStackTrace();
		}

		// send the HTML input to the visitor
		String input = doc.toString();
		visitor.setInput(input);

		// visit the regular expression
		visitor.visit(headlineRegex);
		finalHOutput = visitor.getFinalHOutput();
		visitor.visit(summaryRegex);
		finalSOutput = visitor.getFinalSOutput();
		visitor.visit(dateRegex);
		finalDOutput = visitor.getFinalDOutput();
		visitor.createOutput(finalHOutput, finalSOutput, finalDOutput);

		// get the output from the visitor
		output = visitor.getOutput();

		System.out.println(output + "\n");
		reader.close();
	}
}

// Allow visit-able objects to accept visitor
public interface Visitable{
	public void accept(Visitor visitor);
}

// plan out the visitor's route
public interface Visitor{
	// parse headline
	public String visit(HeadlineRegex headlineRegex);
	// parse summary
	public String visit(SummaryRegex summaryRegex);
	// parse date
	public String visit(DateRegex dateRegex);
}


//concrete element
public class HeadlineRegex implements Visitable{

	// initialize variables
	private String finalHOutput;
	private Pattern headline = Pattern.compile("<span class=\"title-link__title-text\">[A-Za-z0-9 -;:.,!\"'/$]*</span>");

	// accept the visitor
	public void accept(Visitor visitor){
		visitor.visit(this);
	}

	// refine regular expression
	public String refineHOutput(String hOutput) {
		// requires StringBuilder object as Strings are immutable in Java
		StringBuilder sbHOutput = new StringBuilder(hOutput);
		sbHOutput.delete(0, 163);
		finalHOutput = sbHOutput.toString();
		finalHOutput = finalHOutput.replace("</span>]", "");
		return finalHOutput;
	}

	// getters
	public Pattern getHeadline() {
		return headline;
	}

	public String getFinalHOutput() {
		return finalHOutput;
	}


}

// concrete element
public class SummaryRegex implements Visitable {

	// initialize variables
	private String finalSOutput;
	private Pattern summary = Pattern.compile("<p class=\"buzzard__summary\">[A-Za-z0-9 -;:.,!\\\"'/$]*</p>");


	// accept the visitor
	public void accept(Visitor visitor){
		visitor.visit(this);
	}

	// refine regular expression
	public String refineSOutput(String sOutput) {
		// requires StringBuilder object as Strings are immutable in Java
		StringBuilder sbSOutput = new StringBuilder(sOutput);
		sbSOutput.delete(0, 143);
		finalSOutput = sbSOutput.toString();
		finalSOutput = finalSOutput.replace("</p>]", "");
		return finalSOutput;
	}

	// getters
	public Pattern getSummary() {
		return summary;
	}

	public String getFinalSOutput() {
		return finalSOutput;
	}

}

// concrete element
public class DateRegex implements Visitable {

	// initialize variables
	private String finalDOutput;
	private Pattern date = Pattern.compile("data-datetime=\"[A-Za-z0-9 -;:.,!\"'/$]*\">");


	// accept the visitor
	public void accept(Visitor visitor){
		visitor.visit(this);
	}

	// refine regular expression
	public String refineDOutput(String dOutput) {
		// requires StringBuilder object as Strings are immutable in Java
		StringBuilder sbDOutput = new StringBuilder(dOutput);
		sbDOutput.delete(0, 114);
		finalDOutput = sbDOutput.toString();
		finalDOutput = finalDOutput.replace("\">]", "");
		return finalDOutput;
	}

	// getters
	public Pattern getDate() {
		return date;
	}

	public String getFinalDOutput() {
		return finalDOutput;
	}

}

public class RegexVisitor implements Visitor {
	private String input;
	private String output;
	private String hOutput;
	private String finalHOutput;
	private String sOutput;
	private String finalSOutput;
	private String dOutput;
	private String finalDOutput;
	private boolean hFinds;
	private boolean sFinds;
	private boolean dFinds;

	// collect data about the regular expressions
	// use this data to return a matching String
	public String visit(HeadlineRegex headlineRegex) {
		Pattern headline = headlineRegex.getHeadline();
		Matcher hMatcher = headline.matcher(input);
		// find sub-string that contains pattern
		hFinds = hMatcher.find();
		if (hFinds == true ) {
			hOutput = hMatcher.toString();
		} else {
			hOutput = "Error";
		}
		// refine output to remove Object info and tags
		headlineRegex.refineHOutput(hOutput);
		finalHOutput = headlineRegex.getFinalHOutput();

		// return String
		return finalHOutput;
	}

	public String visit(SummaryRegex summaryRegex){
		Pattern summary = summaryRegex.getSummary();
		Matcher sMatcher = summary.matcher(input);
		// find sub-string that contains pattern
		sFinds = sMatcher.find();
		if (sFinds == true ) {
			sOutput = sMatcher.toString();
		} else {
			sOutput = "Error";
		}
		// refine output to remove Object info and tags
		summaryRegex.refineSOutput(sOutput);
		finalSOutput = summaryRegex.getFinalSOutput();
		return finalSOutput;
	}

	public String visit(DateRegex dateRegex){
		Pattern date = dateRegex.getDate();
		Matcher dMatcher = date.matcher(input);
		// find sub-string that contains pattern
		dFinds = dMatcher.find();
		if (dFinds == true ) {
			dOutput = dMatcher.toString();
		} else {
			dOutput = "Error";
		}
		// refine output to remove object info and tags
		dateRegex.refineDOutput(dOutput);
		finalDOutput = dateRegex.getFinalDOutput();
		return finalDOutput;
	}

	// concatenate the outputs
	public String createOutput(String finalHOutput, String finalSOutput, String finalDOutput){
		output = "\n" + finalHOutput + "\n" + finalSOutput + "\n" + finalDOutput;
		return output;
	}

	// getters and setters
	// collect input
	public String getInput() {
		return input;
	}

	public void setInput(String input) {
		this.input = input;
	}

	public String getFinalHOutput() {
		return finalHOutput;
	}

	public String getFinalSOutput() {
		return finalSOutput;
	}

	public String getFinalDOutput() {
		return finalDOutput;
	}

	public String getOutput() {
		return output;
	}

}