Create markdownUrls.html

huggingface-cn · Mar 10, 2024 · 4af5501 · 4af5501
1 parent beb0183
commit 4af5501
Showing 1 changed file with 60 additions and 0 deletions.
diff --git a/markdownUrls.html b/markdownUrls.html
@@ -0,0 +1,60 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Markdown Link Extractor with WeChat Link Exclusion</title>
+    <style>
+        #inputMarkdown, #outputMarkdown {
+            width: 90%;
+            height: 150px;
+            margin: 10px;
+        }
+    </style>
+</head>
+<body>
+
+<h2>Markdown Link Extractor with WeChat Link Exclusion</h2>
+<textarea id="inputMarkdown" placeholder="输入Markdown内容..."></textarea><br>
+<button onclick="extractAndAppendLinks()">提取并追加链接</button><br>
+<textarea id="outputMarkdown" readonly placeholder="处理后的结果..."></textarea>
+
+<script>
+    function extractAndAppendLinks() {
+        let inputText = document.getElementById('inputMarkdown').value;
+        let output = document.getElementById('outputMarkdown');
+
+        // 分段处理，以换行符分割文本
+        let paragraphs = inputText.split('\n\n');
+        let processedParagraphs = paragraphs.map(paragraph => {
+            // 正则表达式匹配Markdown链接格式
+            const linkRegex = /\[([^\]]+)\]\((https?:\/\/[^\s)]+)(?: "[^"]*")?\)/g;
+            let links = [];
+            let result;
+            let processedText = paragraph;
+
+            // 循环匹配并收集所有链接，跳过微信链接
+            while ((result = linkRegex.exec(paragraph)) !== null) {
+                if (!result[2].includes('mp.weixin.qq.com')) {
+                    links.push({
+                        title: result[1],
+                        url: result[2]
+                    });
+                }
+            }
+
+            // 构建并追加链接到当前段落
+            if (links.length > 0) {
+                let linksString = links.map(link => `- ${link.title}\n<url>${link.url}</url>`).join('\n');
+                processedText += '\n\n' + linksString; // 追加链接到当前段落下面
+            }
+
+            return processedText;
+        });
+
+        // 将处理后的段落重新拼接成一个字符串，并显示在输出框中
+        output.value = processedParagraphs.join('\n\n');
+    }
+</script>
+
+</body>
+</html>