1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48
|
public class WebPagePdfExtractor {
public Map<String, Object> processRecord(String url) {
DefaultHttpClient httpclient = new DefaultHttpClient();
Map<String, Object> map = new HashMap<String, Object>();
try {
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){
try {
input.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
}catch (Exception exception) {
exception.printStackTrace();
}
return map;
}
public static void main(String arg[]){
WebPagePdfExtractor webPagePdfExtractor = new WebPagePdfExtractor();
Map<String, Object> extractedMap = webPagePdfExtractor.processRecord("http://math.about.com/library/q20.pdf");
System.out.println(extractedMap.get("text"));
}
} |
Partager