feat: Html转Markdown

pom.xml

@@ -375,6 +375,13 @@
             <version>0.10.328</version>
         </dependency>
 
+        <dependency>
+            <groupId>io.github.furstenheim</groupId>
+            <artifactId>copy_down</artifactId>
+            <version>1.0</version>
+        </dependency>
+
+
     </dependencies>
 
 

src/main/java/cn/com/poc/common/utils/DocumentLoad.java

@@ -2,6 +2,7 @@ package cn.com.poc.common.utils;
 
 import cn.com.yict.framemax.core.i18n.I18nMessageException;
 import cn.hutool.core.io.FileUtil;
+import io.github.furstenheim.*;
 import org.apache.pdfbox.io.RandomAccessBufferedFileInputStream;
 import org.apache.pdfbox.pdfparser.PDFParser;
 import org.apache.pdfbox.pdmodel.PDDocument;
@@ -12,10 +13,48 @@ import org.apache.poi.xwpf.usermodel.XWPFDocument;
 import org.springframework.util.Assert;
 
 import java.io.*;
+import java.net.URL;
+import java.net.URLConnection;
 import java.nio.file.Files;
 
 public class DocumentLoad {
 
+    final static OptionsBuilder optionsBuilder = OptionsBuilder.anOptions();
+    final static Options options = optionsBuilder.withBr("-")
+            .withLinkStyle(LinkStyle.REFERENCED)
+            .withLinkReferenceStyle(LinkReferenceStyle.SHORTCUT)
+            .build();
+    final static CopyDown converter = new CopyDown(options);
+
+    /**
+     * Html To Markdown
+     */
+    public static String htmlToMarkdown(String url) {
+        try {
+            // 创建 资源符对象 连接
+            URLConnection conn = new URL(url).openConnection();
+            // 获取输入流
+            InputStream inputStream = conn.getInputStream();
+            // 缓冲区，读取输入流内容，64KB
+            char[] buffer = new char[1024 * 64];
+            int len;
+            StringBuilder sb = new StringBuilder();
+            // 转换为字符流
+            InputStreamReader isr = new InputStreamReader(inputStream);
+            // 循环读取
+            while ((len = isr.read(buffer)) != -1) {
+                sb.append(buffer, 0, len);
+            }
+            // 关闭资源
+            inputStream.close();
+            isr.close();
+            String htmlStr = sb.toString();
+            return converter.convert(htmlStr);
+        } catch (IOException e) {
+            throw new I18nMessageException(e.getMessage());
+        }
+    }
+
     /**
      * 读取文档
      *