kettle中与jsoup结合解析html页面

1. 生成记录
   
2. Http Rest
   
3. Java代码
   特别注意：Element在这里用不了，报错，必须用Elements
   

import org.jsoup.Connection;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;

public boolean processRow(StepMetaInterface smi, StepDataInterface sdi) throws KettleException {
  if (first) {
    first = false;
  }

  Object[] r = getRow();

  if (r == null) {
    setOutputDone();
    return false;
  }

  r = createOutputRow(r, data.outputRowMeta.size());

		String url = "https://policy.smejs.cn/frontend/policy-service/7eb3545b15ee474a96af7b34d24ab807";


      	try {
            // Jsoup解析处理
            Connection conn = Jsoup.connect(url);

            Document doc = conn.timeout(10000).get();

			Elements ul = doc.select("div.policy-info-detail-page__main__top__line__value");

			get(Fields.Out, "doc").setValue(r, ul.get(2));

        } catch (IOException e) {
            e.printStackTrace();
        }
		
		
	
  // Send the row on to the next step.
  putRow(data.outputRowMeta, r);
	
  return true;
}

4. 写日志
   

5. 结果
   成功~