js 正则表达式 提取链接

// 假设htmlContent是包含多个链接的HTML字符串
const htmlContent = `
  <div>
    <a href="https://example.com/page1">Page 1</a>
    <a href="https://example.com/page2">Page 2</a>
    <a href="https://example.com/page3">Page 3</a>
  </div>
`;

// 正则表达式匹配href属性中的链接
const regex = /href="([^"]+)"/g;

let match;
const links = [];

while ((match = regex.exec(htmlContent)) !== null) {
  links.push(match[1]); // match[1]表示第一个捕获组，即链接地址
}

console.log(links);
// 输出: ["https://example.com/page1", "https://example.com/page2", "https://example.com/page3"]

const regex = /href=["']?([^"'>]+)["']?/g;

const regex = /href=["']?(https?:\/\/[^"'>]+)["']?/g;