1
|
package eu.dnetlib.iis.metadataextraction;
|
2
|
|
3
|
import java.io.File;
|
4
|
import java.io.FileInputStream;
|
5
|
import java.io.InputStream;
|
6
|
import java.security.InvalidParameterException;
|
7
|
import org.jdom.Element;
|
8
|
import org.jdom.output.Format;
|
9
|
import org.jdom.output.XMLOutputter;
|
10
|
import pl.edu.icm.cermine.ContentExtractor;
|
11
|
|
12
|
/**
|
13
|
* Metadata extractor main class executing extraction
|
14
|
* for all files provided as arguments.
|
15
|
* @author mhorst
|
16
|
*
|
17
|
*/
|
18
|
public class MetadataExtractorMain {
|
19
|
|
20
|
public static void main(String[] args) throws Exception {
|
21
|
if (args.length>0) {
|
22
|
for (String fileLoc : args) {
|
23
|
ContentExtractor extractor = new ContentExtractor();
|
24
|
InputStream inputStream = new FileInputStream(new File(fileLoc));
|
25
|
try {
|
26
|
extractor.uploadPDF(inputStream);
|
27
|
Element resultElem = extractor.getNLMContent();
|
28
|
XMLOutputter outputter = new XMLOutputter(Format.getPrettyFormat());
|
29
|
System.out.println(outputter.outputString(resultElem));
|
30
|
System.out.println();
|
31
|
} finally {
|
32
|
inputStream.close();
|
33
|
}
|
34
|
}
|
35
|
} else {
|
36
|
throw new InvalidParameterException("no pdf file path provided");
|
37
|
}
|
38
|
}
|
39
|
|
40
|
}
|