public void testCharsetWithTEXT() throws Exception {
String text =
"<html>"
+ "<head>"
+ "</head>"
+ "<body>"
+ "<h1>This is a HTML file for testing!</h1>"
+ "</body>"
+ "</html>";
HTMLDocument document = HTMLParser.createDocument(text);
assertNotNull(document);
NodePath path = NodePathParser.toPath("html.body.h1");
HTMLNode node = NodePathUtil.lookFor(document.getRoot(), path);
assertNotNull(node);
assertEquals(node.getName(), Name.H1);
assertEquals(node.getName().toString(), "H1");
System.out.println("NAME: " + node.getName());
System.out.println("VALUE: " + new String(node.getValue()));
System.out.println("TEXTVALUE: " + node.getTextValue());
// assertNull(node.getChildren());
assertNotNull(node.getChildren());
assertEquals(node.getChildren().size(), 1);
assertEquals(!node.getChildren().isEmpty(), true);
assertEquals(node.getChildren().get(0).getName(), Name.CONTENT);
assertEquals(node.getChildren().get(0).getName().toString(), "CONTENT");
HTMLNode child = node.getChildren().get(0);
assertNotNull(child);
assertNull(child.getChildren());
assertEquals(child.getTextValue(), "This is a HTML file for testing!");
// assertEquals(child.getValue(),"content");
System.out.println("CONTENT-VALUE: " + new String(child.getValue()));
assertEquals(child.getTextValue(), new String(child.getValue()));
}
public void testCharsetWithURL() throws Exception {
HTMLDocument document;
try {
URL url_ = new URL("http://www.24h.com.vn");
document = HTMLParser.createDocument(url_.openConnection().getInputStream(), null);
document = HTMLParser.createDocument(url_.openStream(), null);
} catch (java.net.UnknownHostException e) {
return;
} catch (java.net.ConnectException e) {
return;
}
assertNotNull(document);
assertNotNull(document.getRoot());
}
public void testCharsetWithFile() throws Exception {
HTMLDocument document = HTMLParser.createDocument(this.file_, null);
assertNotNull(document);
assertEquals("ASCII", HTMLParser.getCharset());
assertNotSame("UTF-8", HTMLParser.getCharset());
System.out.println("CHARSET: " + HTMLParser.getCharset());
System.out.println("DOCUMENT-TEXTVALUE: " + document.getTextValue());
System.out.println("DOCUMENT-ROOT: " + document.getRoot().getName().toString());
System.out.println("CLASS: " + document.getClass().getName() + "\n");
System.out.println("DOCUMENT-DOCTYPE-TEXTVALUE: " + document.getDoctype().getTextValue());
System.out.println("DOCUMENT-DOCTYPE-VALUE: " + new String(document.getDoctype().getValue()));
System.out.println("DOCUMENT-DOCTYPE-NAME: " + document.getDoctype().getName().toString());
}
public void testNode() throws Exception {
// assertNotNull(this.file_);
System.out.println("FILE PATH: " + this.file_.getAbsolutePath());
// HTMLDocument.
String text =
"<html>"
+ "<head>"
+ "<title>My own HTML file</title>"
+ "</head>"
+ "<body>"
+ "<h2>This is a test exercise for me!</h2>"
+ "</body>"
+ "</html>";
HTMLDocument document = HTMLParser.createDocument(text);
assertNotNull(document);
String pathStr = "html.head.title";
NodePath path = NodePathParser.toPath(pathStr);
assertNotNull(path);
assertEquals(path.toString(), "HTML[0].HEAD[0].TITLE[0]");
System.out.println("PATH: " + path.toString());
HTMLNode node = NodePathUtil.lookFor(document.getRoot(), path);
assertNotNull(node);
assertEquals(node.getName(), Name.TITLE);
// Add a Tag to HTMLDocument.
NodeImpl impl = new NodeImpl("h2 id = \"dds\"".toCharArray(), Name.H2);
node.addChild(impl);
assertNotNull(node.getChildrenNode().get(1));
assertEquals(node.getChildren().get(1).getName(), Name.H2);
System.out.println("THE NEW NODE-NAME: " + node.getChildrenNode().get(1).getName().toString());
System.out.println("THE NEW NODE-VALUE: " + new String(node.getChildren().get(1).getValue()));
// Add a Table to HTMLDocument.
HTMLDocument doc = HTMLParser.createDocument("<table border='1'><tr></tr></table>");
HTMLNode table = NodePathUtil.lookFor(doc.getRoot(), NodePathParser.toPath("html.body.table"));
node.addChild(table);
// Remove a Node which is text in format from HTMLDocument.
System.out.println("\n\nRemove:");
HTMLNode contentNode =
NodePathUtil.lookFor(document.getRoot(), NodePathParser.toPath("html.head.title.content"));
assertNotNull(contentNode);
assertEquals(Name.CONTENT, contentNode.getName());
assertEquals("CONTENT", contentNode.getName().toString());
assertEquals(new String(contentNode.getValue()), contentNode.getTextValue());
System.out.println("NODE-VALUE: " + new String(contentNode.getValue()));
System.out.println("NODE-TEXTVALUE: " + contentNode.getTextValue());
assertEquals(true, node.getChildren().remove(contentNode));
// Pass the Node which has removed from HTMLDocument into the <h2> TAG.
HTMLNode h2Node =
NodePathUtil.lookFor(document.getRoot(), NodePathParser.toPath("html.head.title.h2"));
assertNotNull(h2Node);
assertEquals(Name.H2, h2Node.getName());
assertEquals("H2", h2Node.getName().toString());
h2Node.addChild(contentNode);
// Show all.
System.out.println("\n\nShow all the content of HTML file:");
System.out.println(node.getTextValue());
}