Skip to content

Instantly share code, notes, and snippets.

@tommedema
Created December 24, 2011 21:21
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save tommedema/1518382 to your computer and use it in GitHub Desktop.
Save tommedema/1518382 to your computer and use it in GitHub Desktop.
import java.net.URL;
import java.util.Scanner;
import de.l3s.boilerpipe.extractors.ArticleExtractor;
public class BoilerpipeCLI {
public static void main(String[] args) throws Exception {
String inputText = "";
Scanner scanner = new Scanner(System.in);
while (scanner.hasNextLine()) {
inputText += scanner.nextLine()+"\n";
}
String output = ArticleExtractor.INSTANCE.getText(inputText);
System.out.println(output);
}
}
var request = require('request'),
spawn = require('child_process').spawn;
request('http://yahoo.com', function (error, response, body) {
if (error) throw error;
if (response.statusCode !== 200) throw new Error('invalid statuscode: ' + response.statusCode);
if (!body) throw new Error('no body');
var child = spawn('java', ['-classpath', './;./boilerpipe-1.2.0.jar;./lib/nekohtml-1.9.13.jar;./lib/xderces-2.9.1.jar', 'BoilerpipeCLI'], {
cwd: __dirname + '/lib/boilerpipe'
}),
output = '';
child.stdout.on('data', function(data) {
console.log('writing output: ' + data);
output += data;
});
child.on('exit', function() {
console.log('child exit');
console.log(output);
});
child.stdin.write(body, 'utf8');
child.stdin.once('drain', function() {
child.stdin.end();
});
});
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment