import net.htmlparser.jericho.*;
public static void parseHtmlDocument() throws IOException {
String sourceUrlString = "index.html";
Source source = new Source(new URL(sourceUrlString));
String content = source.toString();
System.out.println(content);
}
public static void parseHtmlDocument() throws IOException {
String sourceUrlString = "index.html";
Source source = new Source(new URL(sourceUrlString));
List<Element> divElements = source.getAllElements("div");
for (Element divElement : divElements) {
System.out.println(divElement.getAttributeValue("id"));
}
}
public static void main(String[] args) {
try {
parseHtmlDocument();
} catch (IOException e) {
e.printStackTrace();
}
}
import net.htmlparser.jericho.*;
import java.io.IOException;
import java.net.URL;
import java.util.List;
public class HtmlParser {
public static void parseHtmlDocument() throws IOException {
String sourceUrlString = "index.html";
Source source = new Source(new URL(sourceUrlString));
List<Element> divElements = source.getAllElements("div");
for (Element divElement : divElements) {
System.out.println(divElement.getAttributeValue("id"));
}
}
public static void main(String[] args) {
try {
parseHtmlDocument();
} catch (IOException e) {
e.printStackTrace();
}
}
}
