{"id":259551,"date":"2024-05-15T13:09:28","date_gmt":"2024-05-15T05:09:28","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/259551.html"},"modified":"2024-05-15T13:09:36","modified_gmt":"2024-05-15T05:09:36","slug":"java-%e7%bc%96%e7%a8%8b%e4%bb%a3%e7%a0%81%e5%a6%82%e4%bd%95%e5%8e%bb%e9%99%a4-html-%e4%b8%ad%e7%9a%84%e7%a9%ba%e6%a0%87%e7%ad%be%e5%af%b9","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/259551.html","title":{"rendered":"java \u7f16\u7a0b\u4ee3\u7801\u5982\u4f55\u53bb\u9664 HTML \u4e2d\u7684\u7a7a\u6807\u7b7e\u5bf9"},"content":{"rendered":"

\"java<\/p>\n

\u53bb\u9664HTML\u4e2d\u7684\u7a7a\u6807\u7b7e\u5bf9\u4e3b\u8981\u6d89\u53ca\u5230\u5b57\u7b26\u4e32\u5904\u7406\u548cDOM\u89e3\u6790\u4e24\u79cd\u65b9\u6cd5\u3002\u5b57\u7b26\u4e32\u5904\u7406\u65b9\u6cd5\u9002\u7528\u4e8e\u5feb\u901f\u5904\u7406\u7b80\u5355\u7684HTML\u4ee3\u7801<\/strong>\uff0c\u800cDOM\u89e3\u6790\u5219\u9002\u7528\u4e8e\u66f4\u590d\u6742\u7684HTML\u6587\u6863\u5904\u7406\uff0c\u63d0\u4f9b\u66f4\u52a0\u7cbe\u786e\u7684\u64cd\u4f5c\u3002<\/strong> \u5176\u4e2d\uff0cDOM\u89e3\u6790\u65b9\u6cd5\u66f4\u503c\u5f97\u6df1\u5165\u8ba8\u8bba\u3002<\/p>\n<\/p>\n

\u91c7\u7528DOM\u89e3\u6790\u7684\u65b9\u5f0f\uff0c\u53ef\u4ee5\u66f4\u51c6\u786e\u5730\u8bc6\u522b\u548c\u5904\u7406HTML\u4e2d\u7684\u6807\u7b7e\u3002\u8fd9\u79cd\u65b9\u6cd5\u901a\u5e38\u6d89\u53ca\u5230\u52a0\u8f7dHTML\u5185\u5bb9\u5230\u4e00\u4e2a\u53ef\u64cd\u4f5c\u7684DOM\u6811\u4e2d\uff0c\u7136\u540e\u904d\u5386DOM\u6811\uff0c\u8bc6\u522b\u51fa\u7a7a\u7684\u6807\u7b7e\u5143\u7d20\u5e76\u79fb\u9664\u3002\u8fd9\u79cd\u65b9\u6cd5\u7684\u4f18\u70b9\u5728\u4e8e\u53ef\u4ee5\u66f4\u52a0\u7cbe\u7ec6\u5730\u64cd\u4f5cHTML\u6587\u6863\u7684\u7ed3\u6784\uff0c\u9002\u7528\u4e8e\u9700\u8981\u7cbe\u786e\u5904\u7406\u7684\u573a\u666f\u3002\u6bd4\u5982\uff0c\u53ef\u4ee5\u5f88\u5bb9\u6613\u5730\u8bc6\u522b\u51fa\u54ea\u4e9b\u7a7a\u6807\u7b7e\u5bf9\u662f\u56e0\u4e3a\u7528\u6237\u8f93\u5165\u5bfc\u81f4\u7684\uff0c\u54ea\u4e9b\u662f\u6b63\u5e38\u7684\u9875\u9762\u7ed3\u6784\uff0c\u4ece\u800c\u505a\u51fa\u66f4\u52a0\u5408\u7406\u7684\u5904\u7406\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u5b57\u7b26\u4e32\u5904\u7406\u65b9\u6cd5<\/h3>\n<\/p>\n

\u5728\u5904\u7406\u7b80\u5355\u7684HTML\u6587\u6863\u6216\u8005\u6bb5\u843d\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528\u5b57\u7b26\u4e32\u5904\u7406\u7684\u65b9\u6cd5\u6765\u53bb\u9664\u7a7a\u7684\u6807\u7b7e\u5bf9\u3002\u6b64\u65b9\u6cd5\u8f83\u4e3a\u76f4\u63a5\uff0c\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u7a7a\u6807\u7b7e\u5e76\u5c06\u5176\u79fb\u9664\u3002<\/p>\n<\/p>\n

\u539f\u7406\u4ecb\u7ecd\uff1a<\/strong><\/p>\n<\/p>\n

\u8fd9\u79cd\u65b9\u6cd5\u6838\u5fc3\u5728\u4e8e\u6784\u5efa\u4e00\u79cd\u80fd\u591f\u5339\u914d\u5404\u7c7b\u7a7a\u6807\u7b7e\u5bf9\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u5339\u914d\u7c7b\u4f3c<tag><\/tag><\/code>\u6216<tag> <\/tag><\/code>\u8fd9\u6837\u7684\u6a21\u5f0f\uff0c\u5176\u4e2dtag<\/code>\u4ee3\u8868HTML\u4e2d\u7684\u4efb\u4f55\u6807\u7b7e\u3002<\/p>\n<\/p>\n

\u5b9e\u8df5\u5e94\u7528\uff1a<\/strong><\/p>\n<\/p>\n

public String removeEmptyTags(String htmlContent) {<\/p>\n
    \/\/ \u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u5177\u6709\u7a7a\u767d\u5185\u5bb9\u7684\u6807\u7b7e\uff0c\u5982<TAG> <\/TAG><\/p>\n
    String regex = "<(\\\\w+)\\\\s*>(\\\\s*)<\/\\\\1>";<\/p>\n
    return htmlContent.replaceAll(regex, "");<\/p>\n
}<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528\u4e86replaceAll<\/code>\u65b9\u6cd5\u914d\u5408\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u79fb\u9664\u7a7a\u7684\u6807\u7b7e\u5bf9\uff0c\u8fd9\u79cd\u65b9\u6cd5\u7b80\u5355\u5feb\u901f\uff0c\u9002\u7528\u4e8e\u4e0d\u590d\u6742\u7684HTML\u5904\u7406\u3002<\/p>\n<\/p>\n
\u4e8c\u3001DOM\u89e3\u6790\u65b9\u6cd5<\/h3>\n<\/p>\n
\u4f7f\u7528DOM\u89e3\u6790\u65b9\u6cd5\u5904\u7406HTML\u4e2d\u7684\u7a7a\u6807\u7b7e\u5bf9\uff0c\u76f8\u8f83\u4e8e\u5b57\u7b26\u4e32\u5904\u7406\u65b9\u6cd5\uff0c\u66f4\u4e3a\u7cbe\u51c6\u548c\u7075\u6d3b\u3002<\/p>\n<\/p>\n
\u539f\u7406\u4ecb\u7ecd\uff1a<\/strong><\/p>\n<\/p>\n
DOM\u89e3\u6790\u6d89\u53ca\u5230\u5c06HTML\u5b57\u7b26\u4e32\u52a0\u8f7d\u5230\u4e00\u4e2aDOM\u6811\u7ed3\u6784\u4e2d\uff0c\u8fd9\u4f7f\u5f97\u6211\u4eec\u53ef\u4ee5\u904d\u5386\u6574\u4e2aHTML\u6587\u6863\u7684\u7ed3\u6784\uff0c\u5e76\u5bf9\u7279\u5b9a\u7684\u8282\u70b9\u8fdb\u884c\u64cd\u4f5c\u3002\u8fd9\u79cd\u65b9\u6cd5\u7684\u4f18\u70b9\u662f\u80fd\u591f\u7cbe\u786e\u5730\u8bc6\u522b\u6807\u7b7e\u7684\u5c42\u6b21\u5173\u7cfb\u548c\u4e0a\u4e0b\u6587\u73af\u5883\uff0c\u4ece\u800c\u505a\u51fa\u66f4\u52a0\u5408\u7406\u7684\u5904\u7406\u51b3\u7b56\u3002<\/p>\n<\/p>\n
\u5b9e\u8df5\u5e94\u7528\uff1a<\/strong><\/p>\n<\/p>\n
import org.jsoup.Jsoup;<\/p>\n
import org.jsoup.nodes.Document;<\/p>\n
import org.jsoup.nodes.Element;<\/p>\n
import org.jsoup.select.Elements;<\/p>\n
public String removeEmptyTagsUsingDOM(String htmlContent) {<\/p>\n
    Document doc = Jsoup.parse(htmlContent);<\/p>\n
    Elements emptyElements = doc.select(":empty");<\/p>\n
    for (Element empty : emptyElements) {<\/p>\n
        empty.remove();<\/p>\n
    }<\/p>\n
    return doc.html();<\/p>\n
}<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u6bb5\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528\u4e86Jsoup\u5e93\u6765\u52a0\u8f7d\u548c\u64cd\u4f5cHTML\u6587\u6863\u3002Jsoup\u662f\u4e00\u4e2a\u5f3a\u5927\u7684Java\u5e93\uff0c\u53ef\u4ee5\u7528\u6765\u89e3\u6790\u548c\u5904\u7406HTML\u3002\u5b83\u63d0\u4f9b\u7684select<\/code>\u65b9\u6cd5\u548c:empty<\/code>\u4f2a\u7c7b\u9009\u62e9\u5668\u4f7f\u5f97\u8bc6\u522b\u548c\u79fb\u9664\u7a7a\u6807\u7b7e\u5bf9\u53d8\u5f97\u5f02\u5e38\u7b80\u5355\u3002\u901a\u8fc7\u8fd9\u79cd\u65b9\u6cd5\uff0c\u6211\u4eec\u4e0d\u4ec5\u80fd\u5904\u7406\u7b80\u5355\u7684\u7a7a\u6807\u7b7e\u5bf9\uff0c\u800c\u4e14\u8fd8\u80fd\u5e94\u5bf9\u590d\u6742\u7684HTML\u6587\u6863\u7ed3\u6784\uff0c\u975e\u5e38\u9002\u5408\u9700\u8981\u7cbe\u7ec6\u5904\u7406HTML\u6587\u6863\u7684\u573a\u666f\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u8fdb\u4e00\u6b65\u4f18\u5316<\/h3>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6211\u4eec\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u7279\u6b8a\u60c5\u51b5\uff0c\u6bd4\u5982\u5982\u4f55\u5904\u7406\u90a3\u4e9b\u4ec5\u5305\u542b\u7a7a\u767d\u5b57\u7b26\u7684\u6807\u7b7e\u5bf9\u3002<\/p>\n<\/p>\n
\u4f18\u5316\u5904\u7406\uff1a<\/strong><\/p>\n<\/p>\n
\u5bf9\u4e8e\u4ec5\u5305\u542b\u7a7a\u767d\u5b57\u7b26\u7684\u6807\u7b7e\u5bf9\uff0c\u6211\u4eec\u8fd8\u53ef\u4ee5\u8fdb\u4e00\u6b65\u4f18\u5316\u6211\u4eec\u7684\u5904\u7406\u65b9\u6cd5\u3002\u6bd4\u5982\uff0c\u5728\u4f7f\u7528DOM\u89e3\u6790\u65b9\u6cd5\u65f6\uff0c\u53ef\u4ee5\u7ed3\u5408\u4f7f\u7528Jsoup\u63d0\u4f9b\u7684\u6587\u672c\u64cd\u4f5c\u65b9\u6cd5\uff0c\u6765\u5224\u65ad\u6807\u7b7e\u5185\u662f\u5426\u771f\u6b63\u5730\u4e3a\u7a7a\u6216\u53ea\u5305\u542b\u7a7a\u767d\u5b57\u7b26\u3002\u7136\u540e\u518d\u51b3\u5b9a\u662f\u5426\u79fb\u9664\u8be5\u6807\u7b7e\u3002<\/p>\n<\/p>\n
for (Element element : doc.getAllElements()) {<\/p>\n
    if (element.ownText().trim().isEmpty() && element.children().isEmpty()) {<\/p>\n
        element.remove();<\/p>\n
    }<\/p>\n
}<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u8fd9\u6837\u7684\u7ec6\u8282\u5904\u7406\uff0c\u6211\u4eec\u53ef\u4ee5\u786e\u4fdd\u5373\u4f7f\u662f\u770b\u4f3c\u7a7a\u767d\u7684\u6807\u7b7e\uff08\u5b9e\u9645\u4e0a\u53ef\u80fd\u5305\u542b\u4e86\u6362\u884c\u7b26\u3001\u7a7a\u683c\u7b49\uff09\uff0c\u5982\u679c\u786e\u5b9e\u4e0d\u5305\u542b\u4efb\u4f55\u6709\u7528\u4fe1\u606f\uff0c\u4e5f\u80fd\u591f\u88ab\u51c6\u786e\u5730\u79fb\u9664\u3002\u8fd9\u6837\u7684\u5904\u7406\u80fd\u591f\u786e\u4fddHTML\u6587\u6863\u7684\u6574\u6d01\u6027\uff0c\u540c\u65f6\u907f\u514d\u79fb\u9664\u90a3\u4e9b\u53ef\u80fd\u5728\u9875\u9762\u5e03\u5c40\u4e2d\u8d77\u5230\u4f5c\u7528\u7684\u7a7a\u767d\u6807\u7b7e\u3002<\/p>\n<\/p>\n
\u56db\u3001\u603b\u7ed3\u4e0e\u5e94\u7528\u573a\u666f<\/h3>\n<\/p>\n
\u53bb\u9664HTML\u4e2d\u7684\u7a7a\u6807\u7b7e\u5bf9\uff0c\u662fWeb\u5f00\u53d1\u4e2d\u4f18\u5316\u9875\u9762\u52a0\u8f7d\u901f\u5ea6\u548c\u63d0\u5347\u7528\u6237\u4f53\u9a8c\u7684\u91cd\u8981\u63aa\u65bd\u4e4b\u4e00\u3002\u65e0\u8bba\u662f\u91c7\u7528\u5b57\u7b26\u4e32\u5904\u7406\u65b9\u6cd5\u8fd8\u662fDOM\u89e3\u6790\u65b9\u6cd5\uff0c\u6838\u5fc3\u76ee\u7684\u90fd\u5728\u4e8e\u786e\u4fddHTML\u6587\u6863\u7684\u6574\u6d01\u548c\u6709\u6548\u4fe1\u606f\u7684\u5b8c\u6574\u3002\u5728\u5b9e\u9645\u5f00\u53d1\u4e2d\uff0c\u5e94\u6839\u636e\u5904\u7406\u5bf9\u8c61\u7684\u590d\u6742\u5ea6\u548c\u7cbe\u786e\u5ea6\u9700\u6c42\uff0c\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
\u5e94\u7528\u573a\u666f\uff1a<\/strong><\/p>\n<\/p>\n