|
|
Re: listing file locations from web page
|
Posted: Apr 1, 2004 5:53 AM
|
|
I believe there are many ways to achieve what you want (many libraries that will parse a html doc for you)
Maybe you can use this as a starting point (although it seems strange to use swing, it works): http://java.sun.com/developer/TechTips/1999/tt0923.html
I have changed the example to list img-tags' src attribute:
import java.io.*;
import java.net.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
class GetLinks {
public static void main(String[] args) {
EditorKit kit = new HTMLEditorKit();
Document doc = kit.createDefaultDocument();
// The Document class does not yet
// handle charset's properly.
doc.putProperty("IgnoreCharsetDirective",
Boolean.TRUE);
try {
// Create a reader on the HTML content.
//Reader rd = getReader(args[0]);
Reader rd = getReader("http://www.domain.tld/test.html");
// Parse the HTML.
kit.read(rd, doc, 0);
// Iterate through the elements
// of the HTML document.
ElementIterator it = new ElementIterator(doc);
javax.swing.text.Element elem;
while ((elem = it.next()) != null) {
SimpleAttributeSet s1 = (SimpleAttributeSet)elem.getAttributes().getAttribute(HTML.Tag.IMG);
Object o = elem.getAttributes().getAttribute(HTML.Attribute.SRC);
if (o != null) {
System.out.println(o);
}
}
} catch (Exception e) {
e.printStackTrace();
}
System.exit(1);
}
// Returns a reader on the HTML data. If 'uri' begins
// with "http:", it's treated as a URL; otherwise,
// it's assumed to be a local filename.
static Reader getReader(String uri)
throws IOException {
if (uri.startsWith("http:")) {
// Retrieve from Internet.
URLConnection conn =
new URL(uri).openConnection();
return new
InputStreamReader(conn.getInputStream());
} else {
// Retrieve from file.
return new FileReader(uri);
}
}
}
|
|
Previous Topic
