import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.io.MapFile;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapred.MapFileOutputFormat;
import org.apache.nutch.protocol.Content;
import org.apache.nutch.util.NutchConfiguration;

public class ContentGetter extends Configured {

  private FileSystem fs;

  // public ContentGetter() { super(null); }

  public ContentGetter(Configuration conf) {
    super(conf);
    try {
      this.fs = FileSystem.get(getConf());
    } catch (IOException e) {
      e.printStackTrace();
    }
  }

  public byte[] getContent(final Path segment, final Text key) throws Exception {
    Path dir = new Path(segment, Content.DIR_NAME);
    MapFile.Reader[] readers = MapFileOutputFormat.getReaders(fs, dir, getConf());
    if (readers == null || readers.length != 1) {
      return null;
    }

    Content value = new Content();
    readers[0].get(key, value);
    readers[0].close();

    return value.getContent();
  }

  public static void main(String[] args) throws Exception {
    if (args.length < 2) {
      usage();
      return;
    }
    String input = args[0];
    String key = args[1];
    //
    Configuration conf = NutchConfiguration.create();
    ContentGetter contentGetter = new ContentGetter(conf);
    byte[] content = contentGetter.getContent(new Path(input), new Text(key));
    System.out.write(content);
    System.out.flush();
    return;
  }

  private static void usage() {
    System.err.println("Usage: ContentGetter segment url");
  }
}

$ javac -classpath nutch-0.9.jar:lib/hadoop-0.12.2-core.jar ContentGetter.java
$ java -classpath .:nutch-0.9.jar:lib/hadoop-0.12.2-core.jar:\
lib/commons-logging-1.0.4.jar:lib/log4j-1.2.13.jar:conf  \
ContentGetter crawl-3/segments/20070421201803 http://kazuomik.livejournal.com/495.html \
> 495.html
$