engineutil.java

来自「网页采集系统 ================= 安装配置 -------」· Java 代码 · 共 47 行

JAVA
47
字号
package com.laozizhu.search.util;

import java.net.URLEncoder;
import net.java2000.tools.StrTools;
import com.laozizhu.search.Engine;
import com.laozizhu.search.EngineFactory;
import com.laozizhu.search.Factory;
import com.laozizhu.search.Item;

public class EngineUtil {
  public static final EngineFactory engineFactory = (EngineFactory) Factory.getBean("EngineFactory");

  public static Item get(String url) {
    Engine engine = engineFactory.getInstance(url);
    if (engine == null) {
      System.out.println("Not Supported WebSite : " + url);
      return null;
    }
    try {
      Item item = engine.parseItem(url);
      return item;
    } catch (Exception ex) {
      System.out.println("发生解析错误" + ex.getMessage());
      return null;
    }
  }

  public static String postRemote(String website, String sign, String url) throws Exception {
    if (StrTools.isBlank(website)) {
      return "缺少服务站点";
    }
    if (StrTools.isBlank(url)) {
      return "缺少页面";
    }
    Engine engine = engineFactory.getInstance(url);
    Item item = engine.parseItem(url);
    if (item == null || !item.isValid()) {
      return "Invalid!";
    }
    String rtn = PageService.postPage(website, "sign=" + sign + "&url=" + URLEncoder.encode(item.getUrl(), "UTF-8")
        + "&author=" + URLEncoder.encode(item.getAuthor(), "UTF-8") + "&title=" + URLEncoder.encode(item.getTitle(), "UTF-8")
        + "&body=" + URLEncoder.encode(item.getBody(), "UTF-8") + "&date="
        + URLEncoder.encode(item.getDatetimeCreate(), "UTF-8"));
    return rtn;
  }
}

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?