!752

lib 1004690 // tika

import org.apache.http.HttpEntity;

import org.apache.http.HttpResponse;

import org.apache.http.client.methods.HttpGet;

import org.apache.http.impl.client.DefaultHttpClient;

import org.apache.tika.metadata.Metadata;

import org.apache.tika.metadata.TikaCoreProperties;

import org.apache.tika.parser.AutoDetectParser;

import org.apache.tika.parser.ParseContext;

import org.apache.tika.sax.BodyContentHandler;

static Map<S, O> tika(String url) {

  DefaultHttpClient httpclient = new DefaultHttpClient();

  Map<String, Object> map = new HashMap<String, Object>();

  pcall {

    HttpGet httpGet = new HttpGet(url);

    HttpResponse response = httpclient.execute(httpGet);

    HttpEntity entity = response.getEntity();

    InputStream input = null;

    if (entity != null) {

      try {

        input = entity.getContent();

        BodyContentHandler handler = new BodyContentHandler();

        Metadata metadata = new Metadata();

        AutoDetectParser parser = new AutoDetectParser();

        ParseContext parseContext = new ParseContext();

        parser.parse(input, handler, metadata, parseContext);

        map.put("text", handler.toString() /*.replaceAll("\n|\r|\t", " ") */);

        map.put("title", metadata.get(TikaCoreProperties.TITLE));

        map.put("pageCount", metadata.get("xmpTPg:NPages"));

        map.put("status_code", response.getStatusLine().getStatusCode() + "");

      } catch (Exception e) {                     

          e.printStackTrace();

      } finally {

        if (input != null)

          input.close();

      }

    }

  }

  return map;

}

p {

  S url = or(get(args, 0), "http://math.about.com/library/q20.pdf");

  print("Loading " + url);

  Map<S, O> extractedMap = tika(url);

  print(extractedMap.get("text"));

}