import net.htmlparser.jericho.*;
public class ParserThread implements Runnable {
private String html;
public ParserThread(String html) {
this.html = html;
}
public void run() {
Source source = new Source(html);
// ...
}
}
// ...
import net.htmlparser.jericho.*;
public class ParserManager {
private static ExecutorService threadPool = Executors.newFixedThreadPool(10);
private static ThreadLocal<Source> sourceThreadLocal = new ThreadLocal<Source>() {
@Override
protected Source initialValue() {
return new Source();
}
};
public static void parseHtml(String html) {
Runnable task = new Runnable() {
public void run() {
Source source = sourceThreadLocal.get();
source.setContent(html);
// ...
}
};
threadPool.submit(task);
}
}
ParserManager.parseHtml(html);
Source source = new Source(html);
source.setEncoding("UTF-8");
Source source = new Source(html);
source.setAutoDetectXmlAndHtmlTags(false);
Source source = new Source(html);
List<Element> divElements = source.getAllElements("div");