HtmlCleanerでOPG情報を取得

HtmlCleanerで、OPG情報を取得する例。 (以下では title と image を出力しているだけです)

import java.io.*;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URI;

import org.htmlcleaner.CleanerProperties;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.PrettyXmlSerializer;
import org.htmlcleaner.TagNode;

public class Test {

    public static void main(String[] args) throws MalformedURLException {

      CleanerProperties props = new CleanerProperties();

      final SimpleHtmlSerializer htmlSerializer =
            new SimpleHtmlSerializer(props);
    TagNode node = null;

    try {

     node = new HtmlCleaner(props).clean( new URL("https://hacknote.jp/") );

     TagNode[] metaElements = node.getElementsByName("meta", true);

     for(int i = 0; i < metaElements.length; i++){
       TagNode metaElement = metaElements[i];
       String property = metaElement.getAttributeByName("property");
       if("og:title".equals(property)){
         System.out.println(metaElement.getAttributeByName("content"));
       }else if("og:image".equals(property)){
         System.out.println(metaElement.getAttributeByName("content"));
       }
     }
    } catch(IOException e){
      System.out.println(e.getMessage());
    } catch (Exception ex){
      System.out.println(ex.getMessage());
    }
  }
}

• HTTP 403 エラーが帰ってきてしまうのはUser Agent を追加すれば回避できるそうです。
  • Resolve HtmlCleaner issue of getting HTTP respond code 403