Question

假设我有以下html：

<html>
<head>
</head>
<body>
    <div id="wrapper" >
         <div class="s2">I am going <a title="some title" href="">by flying</a>
           <p>mr tt</p>
         </div> 
    </div>
</body>    
</html>

文本节点中任何等于或大于4个字符的单词，例如单词“going”将替换为原始html中的html内容（非文本）<span>going<span>，而不会更改任何其他内容。

如果我尝试执行element.html（替换）之类的操作，问题是如果让当前元素为<div class="s2">它还会擦除<a title="some title"

Answer 1

在这种情况下，您必须按照this answer的建议遍历您的文档。以下是使用Jsoup API执行此操作的方法：

NodeTraversor和NodeVisitor允许您遍历DOM
Node.replaceWith(...)允许替换DOM中的节点

以下是代码：

public class JsoupReplacer {

  public static void main(String[] args) {
    so6527876();
  }

  public static void so6527876() {
    String html = 
    "<html>" +
    "<head>" +
    "</head>" +
    "<body>" +
    "    <div id=\"wrapper\" >" +
    "         <div class=\"s2\">I am going <a title=\"some title\" href=\"\">by flying</a>" +
    "           <p>mr tt</p>" +
    "         </div> " +
    "    </div>" +
    "</body>    " +
    "</html>";
    Document doc = Jsoup.parse(html);

    final List<TextNode> nodesToChange = new ArrayList<TextNode>();

    NodeTraversor nd  = new NodeTraversor(new NodeVisitor() {

      @Override
      public void tail(Node node, int depth) {
        if (node instanceof TextNode) {
          TextNode textNode = (TextNode) node;
          String text = textNode.getWholeText();
          String[] words = text.trim().split(" ");
          for (String word : words) {
            if (word.length() > 4) {
              nodesToChange.add(textNode);
              break;
            }
          }
        }
      }

      @Override
      public void head(Node node, int depth) {        
      }
    });

    nd.traverse(doc.body());

    for (TextNode textNode : nodesToChange) {
      Node newNode = buildElementForText(textNode);
      textNode.replaceWith(newNode);
    }

    System.out.println("result: ");
    System.out.println();
    System.out.println(doc);
  }

  private static Node buildElementForText(TextNode textNode) {
    String text = textNode.getWholeText();
    String[] words = text.trim().split(" ");
    Set<String> longWords = new HashSet<String>();
    for (String word : words) {
      if (word.length() > 4) {
        longWords.add(word);
      } 
    }
    String newText = text;
    for (String longWord : longWords) {
      newText = newText.replaceAll(longWord, 
          "<span>" + longWord + "</span>");
    }
    return new DataNode(newText, textNode.baseUri());
  }

}

Answer 2

我认为你需要穿越树。元素上 text（）的结果将是Element的所有文本，包括子元素中的文本。希望以下代码对您有所帮助：

import java.io.File;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.commons.io.FileUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;

public class ScreenScrape {

    public static void main(String[] args) throws IOException {
        String content = FileUtils.readFileToString(new File("test.html"));
        Document doc = Jsoup.parse(content);
        Element body = doc.body();
        //System.out.println(body.toString());

        StringBuilder sb = new StringBuilder();
        traverse(body, sb);

        System.out.println(sb.toString());
    }

    private static void traverse(Node n, StringBuilder sb) {
        if (n instanceof Element) {
            sb.append('<');
            sb.append(n.nodeName());            
            if (n.attributes().size() > 0) {
                sb.append(n.attributes().toString());
            }
            sb.append('>');
        }
        if (n instanceof TextNode) {
            TextNode tn = (TextNode) n;
            if (!tn.isBlank()) {
                sb.append(spanifyText(tn.text()));
            }
        }
        for (Node c : n.childNodes()) {
            traverse(c, sb);
        }
        if (n instanceof Element) {
            sb.append("</");
            sb.append(n.nodeName());
            sb.append('>');
        }        
    }

    private static String spanifyText(String text){
        StringBuilder sb = new StringBuilder();
        StringTokenizer st = new StringTokenizer(text);
        String token;
        while (st.hasMoreTokens()) {
             token = st.nextToken();
             if(token.length() > 3){
                 sb.append("<span>");
                 sb.append(token);
                 sb.append("</span>");
             } else {
                 sb.append(token);
             }             
             sb.append(' ');
        }
        return sb.substring(0, sb.length() - 1).toString();
    }

}

<强>更新

使用Jonathan的新Jsoup List element.textNode（）方法并将其与MarcoS建议的NodeTraversor / NodeVisitor技术相结合，我提出了（虽然我在修改树时穿过它 - 可能是一个坏主意）：

Document doc = Jsoup.parse(content);
Element body = doc.body();
NodeTraversor nd = new NodeTraversor(new NodeVisitor() {

    @Override
    public void tail(Node node, int depth) {
        if (node instanceof Element) {
            boolean foundLongWord;
            Element elem = (Element) node;
            Element span;
            String token;
            StringTokenizer st;
            ArrayList<Node> changedNodes;
            Node currentNode;
            for (TextNode tn : elem.textNodes()) {
                foundLongWord = Boolean.FALSE;
                changedNodes = new ArrayList<Node>();
                st = new StringTokenizer(tn.text());
                while (st.hasMoreTokens()) {
                    token = st.nextToken();
                    if (token.length() > 3) {
                        foundLongWord = Boolean.TRUE;
                        span = new Element(Tag.valueOf("span"), elem.baseUri());
                        span.appendText(token);
                        changedNodes.add(span);
                    } else {
                        changedNodes.add(new TextNode(token + " ", elem.baseUri()));
                    }
                }
                if (foundLongWord) {
                    currentNode = changedNodes.remove(0);
                    tn.replaceWith(currentNode);
                    for (Node n : changedNodes) {
                        currentNode.after(n);
                        currentNode = n;
                    }
                }
            }
        }
    }

    @Override
    public void head(Node node, int depth) {
    }
});    
nd.traverse(body);
System.out.println(body.toString());

Answer 3

我用hello（span标签）替换word hello

Document doc = Jsoup.parse(content);
    Element test =  doc.body();
    Elements elemenets = test.getAllElements();
    for(int i =0 ;i <elemenets .size();i++){
        String elementText = elemenets .get(i).text();
        if(elementText.contains("hello"))
            elemenets .get(i).html(l.get(i).text().replaceAll("hello","<span style=\"color:blue\">hello</span>"));
    }

如何使用jsoup替换带span标签的单词？

3 个答案: