使用Dom4j解析RSS源（使用Dom4j解析XML）

直接代码不墨迹

maven依赖引入

<dependency>
    <groupId>dom4j</groupId>
    <artifactId>dom4j</artifactId>
    <version>1.6.1</version>
</dependency>

 定义对象

@Data
public class RssItem {
    
    private String title;

    private String link;

    private String describe;

    private String thumb;

    private String data;

    private String dataLength;

    private String pubDate;

    private String guid;

    private String author;
    
}

@Data
public class RssXml {

    private int id;

    private String type;

    private String title;

    private String author;

    private String url;

    private String image;

    private List<RssItem> items;
    
}

解析方法

  public RssXml parseXml(String url) {

        SAXReader reader = new SAXReader();
        RssXml rssXml = new RssXml();
        rssXml.setUrl(url);
        // 设置文件编码
        reader.setEncoding("UTF-8");

        Document document = null;
        try {
            document = reader.read(new URL(url));
        } catch (Exception e) {
            try {
                // 这里是为了做兼容， 有的rss源有权限问题， 不能用上面的方式访问
                // 这个方法是我的工具类， 代码贴到下面，是为了模拟浏览器，绕过验证
                InputStream inputStream = RSSUtil.getInputStream(url);
                document = reader.read(inputStream);
            } catch (Exception ex) {
                throw new YamiShopBindException("解析RSS失败");
            }

        }

        Element dataViewRoot = document.getRootElement();
        Iterator iteratorRoot = dataViewRoot.elementIterator();
        while (iteratorRoot.hasNext()) {

            Element dataElement = (Element) iteratorRoot.next();

            Element title = dataElement.element("title");

            rssXml.setTitle(title.getStringValue());

            // 判断 这是我自己的业务， 你可以 不这么写， 这里不重要，重要的是解析方式和方法
            if (StringUtils.equals(rssXml.getType(), "ximalaya")) {
                Element author = dataElement.element("author");
                if (author != null) {
                    rssXml.setAuthor(author.getStringValue());
                }
            }

            List<Element> item = dataElement.elements("item");

            List<RssItem> list = new ArrayList<>();
            for (int i = 0; i < item.size(); i++) {
                if (i >= 100) {
                    break;
                }
                RssItem e = new RssItem();
                Element o = item.get(i);

                Element t = o.element("title");
                if (t != null) {
                    e.setTitle(t.getStringValue());
                }
                Element link = o.element("link");
                Element image = o.element("image");
                Element pubDate = o.element("pubDate");
                Element guid = o.element("guid");

                Element creator = o.element("creator");
                if (creator != null) {
                    e.setAuthor(creator.getStringValue());
                }

                if(guid != null) {
                    e.setGuid(guid.getStringValue());

                }

                Element enclosure = o.element("enclosure");
                if (enclosure != null) {
                    Attribute attribute = enclosure.attribute("url");
                    Attribute length = enclosure.attribute("length");
                    if (attribute != null) {
                        String stringValue = attribute.getStringValue();
                        e.setData(stringValue);
                        if (length != null) {
                            e.setDataLength(length.getStringValue());
                        }
                    }
                }

                if(link != null) {
                    e.setLink(link.getStringValue());
                }

                if (image != null) {
                    Attribute attribute1 = image.attribute("href");
                    if (attribute1 != null) {
                        e.setThumb(attribute1.getStringValue());
                    }

                }
                e.setPubDate(pubDate.getStringValue());

                Element description = o.element("description");
                e.setDescribe(description.getStringValue());

                list.add(e);

            }
            rssXml.setItems(list);
        }
        return rssXml;
    }

package com.yami.shop.common.util;

import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.impl.conn.PoolingClientConnectionManager;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;

/**
 * @author JiYanLong
 * @date 2023/12/22 17:25
 */
public class RSSUtil {


    public static InputStream getInputStream(String url) throws IOException {

        DefaultHttpClient client = new DefaultHttpClient(new PoolingClientConnectionManager());

        HttpGet get = new HttpGet(url);
//        rsp.setCharacterEncoding("UTF-8");
//        get.setContentType();
        get.setHeader("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36");
        get.setHeader("Sec-Ch-Ua", "\"Not_A Brand\";v=\"8\", \"Chromium\";v=\"120\", \"Google Chrome\";v=\"120\"");
        get.setHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7");
        CloseableHttpResponse response = client.execute(get);
        return response.getEntity().getContent();

    }


    public static String parseXML(String url) throws IOException {

        InputStream inputStream = getInputStream(url);

        BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream));

        StringBuilder stringBuilder = new StringBuilder();
        String str = "";
        while ((str = reader.readLine()) != null) {
            stringBuilder.append(str);
        }
        inputStream.close();

        return stringBuilder.toString();

    }
}

代码就是上面的所有的内容，重点在 parseXml 这个方法。

下面是我用上面代码做的小程序，订阅RSS用的，希望对你有帮助。