Source source = new Source(new URL("https://www.example.com/page.html"));
TableIterator iterator = source.findAllTables().iterator();
while (iterator.hasNext()) {
Table table = iterator.nextTable();
for (TableRow row : table.getRows()) {
for (TableColumn column : row.getColumns()) {
String cellData = column.getContent().getTextExtractor().toString();
System.out.println(cellData);
}
}
}
import net.htmlparser.jericho.*;
import java.io.IOException;
import java.net.URL;
public class HTMLTableParser {
public static void main(String[] args) throws IOException {
Source source = new Source(new URL("https://www.example.com/page.html"));
TableIterator iterator = source.findAllTables().iterator();
while (iterator.hasNext()) {
Table table = iterator.nextTable();
for (TableRow row : table.getRows()) {
for (TableColumn column : row.getColumns()) {
String cellData = column.getContent().getTextExtractor().toString();
System.out.println(cellData);
}
}
}
}
}
