public static WebDocument getDocument(Page page) {
InputStream stream = new ByteArrayInputStream(page.getContentBytes());
try {
Metadata metadata = new Metadata();
metadata.set(Metadata.CONTENT_TYPE, page.getContentType());
metadata.set(Metadata.CONTENT_LOCATION, page.getURL().toString());
metadata.set(Metadata.LOCATION, page.getURL().toString());
metadata.set(Metadata.MIME_TYPE_MAGIC, page.getContentType());
metadata.set(Metadata.CONTENT_ENCODING, page.getContentEncoding());
metadata.set(Metadata.TIKA_MIME_FILE, page.getContentType());
String text = getTika().parseToString(stream, metadata);
WebDocument wd =
new WebDocument(0, metadata.get(Metadata.TITLE), text, page.getURL().toString());
stream.close();
return wd;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (TikaException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} finally {
try {
stream.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} // close the stream
}
return null;
}
public void crawled(LinkEvent le) {
switch (le.getID()) {
case LinkEvent.ERROR:
logger.error(
"Crawling error occured during download of URL: "
+ le.getLink().getURL()
+ " Root cause: "
+ le.getException());
break;
case LinkEvent.TOO_DEEP:
case LinkEvent.SKIPPED:
logger.warn("Crawling event: " + le.getName() + ", URL: " + le.getLink().getURL());
break;
default:
break;
}
if (le.getID() != LinkEvent.DOWNLOADED) return;
logger.info("Crawling event: " + le.getName() + ", URL: " + le.getLink().getURL());
Link l = le.getLink();
Page p = l.getPage();
BookPage page = new BookPage();
page.setBookName(book.getName());
page.setName(book.getName() + counter);
page.setParentName(book.getName());
page.setTitle(p.getTitle());
page.setLocation(p.getURL().toString());
page.setChildCount(counter);
page.setContentType(book.getContentType());
page.setPath(p.getURL().getPath());
System.out.println(p.getContentBytes());
try {
ByteArrayInputStream is = new ByteArrayInputStream(p.getContentBytes());
FileContentParser parser = new FileContentParser();
parser.processContentType(p.getContentType(), is, page);
// } catch (UnsupportedEncodingException e1) {
} catch (ParserException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
try {
im.addPage(page);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
counter++;
}
