Export Website to Markdown

Export all rendered text from any webpage to a Markdown file. Preserves headings, lists, links, bold/italic, code, tables, and blockquotes.
התקן את הסקריפט ?
שאל שאלה, פרסם ביקורת, או דווח על הסקריפט.
Wrap lines
// ==UserScript==
// @name         Export Website to Markdown
// @namespace    https://github.com/theelderemo/export-website-as-markdown
// @version      1.0.0
// @description  Export all rendered text from any webpage to a Markdown file. Preserves headings, lists, links, bold/italic, code, tables, and blockquotes.
// @author       theelderemo
// @license      MIT
// @match        *://*/*
// @grant        none
// @run-at       document-idle
// ==/UserScript==

(function () {
  "use strict";

  const SKIP_TAGS = new Set([
    "SCRIPT", "STYLE", "NOSCRIPT", "TEMPLATE", "SVG", "CANVAS",
    "AUDIO", "VIDEO", "IFRAME", "OBJECT", "EMBED", "HEAD", "META",
    "LINK", "INPUT", "TEXTAREA", "SELECT", "BUTTON",
  ]);

  const BLOCK_TAGS = new Set([
    "P", "DIV", "SECTION", "ARTICLE", "MAIN", "ASIDE", "FOOTER",
    "HEADER", "NAV", "FIGURE", "FIGCAPTION", "DETAILS", "SUMMARY",
    "DIALOG", "ADDRESS", "FIELDSET", "LEGEND", "FORM",
  ]);

  function isVisible(el) {
    if (el.nodeType !== Node.ELEMENT_NODE) return true;
    const style = window.getComputedStyle(el);
    return (
      style.display !== "none" &&
      style.visibility !== "hidden" &&
      style.visibility !== "collapse" &&
      parseFloat(style.opacity) > 0 &&
      el.getAttribute("aria-hidden") !== "true"
    );
  }

  function nodeToMarkdown(node, ctx) {
    if (node.nodeType === Node.TEXT_NODE) {
      const text = node.textContent;
      const clean = text.replace(/[\r\n]+/g, " ").replace(/\t/g, " ");
      if (!clean.trim()) return "";
      return applyInlineStyle(clean, ctx);
    }

    if (node.nodeType !== Node.ELEMENT_NODE) return "";
    if (SKIP_TAGS.has(node.tagName)) return "";
    if (!isVisible(node)) return "";

    const tag = node.tagName;

    if (/^H[1-6]$/.test(tag)) {
      const level = parseInt(tag[1]);
      const prefix = "#".repeat(level);
      const inner = childrenToMarkdown(node, ctx).trim();
      return inner ? `\n\n${prefix} ${inner}\n\n` : "";
    }

    if (tag === "HR") return "\n\n---\n\n";

    if (tag === "BLOCKQUOTE") {
      const inner = childrenToMarkdown(node, ctx).trim();
      if (!inner) return "";
      return (
        "\n\n" +
        inner
          .split("\n")
          .map((l) => `> ${l}`)
          .join("\n") +
        "\n\n"
      );
    }

    if (tag === "PRE") {
      const codeEl = node.querySelector("code");
      const lang = codeEl
        ? (codeEl.className.match(/language-(\S+)/) || [])[1] || ""
        : "";
      const text = (codeEl || node).innerText || node.textContent;
      return `\n\n\`\`\`${lang}\n${text.trim()}\n\`\`\`\n\n`;
    }

    if (tag === "CODE" && node.closest("pre")) return "";

    if (tag === "CODE") {
      const text = node.textContent.trim();
      return text ? `\`${text}\`` : "";
    }

    if (["STRONG", "B"].includes(tag)) {
      const inner = childrenToMarkdown(node, { ...ctx, bold: true }).trim();
      return inner ? `**${inner}**` : "";
    }

    if (["EM", "I"].includes(tag)) {
      const inner = childrenToMarkdown(node, { ...ctx, italic: true }).trim();
      return inner ? `_${inner}_` : "";
    }

    if (tag === "MARK") {
      const inner = childrenToMarkdown(node, ctx).trim();
      return inner ? `==${inner}==` : "";
    }

    if (["S", "STRIKE", "DEL"].includes(tag)) {
      const inner = childrenToMarkdown(node, ctx).trim();
      return inner ? `~~${inner}~~` : "";
    }

    if (tag === "SUP") {
      const inner = childrenToMarkdown(node, ctx).trim();
      return inner ? `^${inner}^` : "";
    }

    if (tag === "SUB") {
      const inner = childrenToMarkdown(node, ctx).trim();
      return inner ? `~${inner}~` : "";
    }

    if (tag === "A") {
      const href = node.getAttribute("href") || "";
      const inner = childrenToMarkdown(node, ctx).trim();
      if (!inner) return "";
      const absHref = href
        ? new URL(href, window.location.href).href
        : "";
      return absHref && absHref !== inner ? `[${inner}](${absHref})` : inner;
    }

    if (tag === "IMG") {
      const alt = node.getAttribute("alt") || "";
      const src = node.getAttribute("src") || "";
      const absSrc = src ? new URL(src, window.location.href).href : "";
      return alt ? `![${alt}](${absSrc})` : "";
    }

    if (tag === "BR") return "  \n";

    if (tag === "UL") {
      const items = listItems(node, ctx, false);
      return items ? `\n\n${items}\n\n` : "";
    }

    if (tag === "OL") {
      const items = listItems(node, ctx, true);
      return items ? `\n\n${items}\n\n` : "";
    }

    if (tag === "LI") {
      return childrenToMarkdown(node, ctx).trim();
    }

    if (tag === "DL") {
      return "\n\n" + childrenToMarkdown(node, ctx).trim() + "\n\n";
    }
    if (tag === "DT") {
      return `\n**${childrenToMarkdown(node, ctx).trim()}**\n`;
    }
    if (tag === "DD") {
      return `: ${childrenToMarkdown(node, ctx).trim()}\n`;
    }

    if (tag === "TABLE") {
      return tableToMarkdown(node, ctx);
    }
    if (["THEAD", "TBODY", "TFOOT", "TR", "TH", "TD"].includes(tag)) {
      return childrenToMarkdown(node, ctx);
    }

    if (tag === "P" || BLOCK_TAGS.has(tag)) {
      const inner = childrenToMarkdown(node, ctx).trim();
      return inner ? `\n\n${inner}\n\n` : "";
    }

    return childrenToMarkdown(node, ctx);
  }

  function childrenToMarkdown(node, ctx) {
    let out = "";
    for (const child of node.childNodes) {
      out += nodeToMarkdown(child, ctx);
    }
    return out;
  }

  function applyInlineStyle(text, ctx) {
    return text;
  }

  function listItems(ulEl, ctx, ordered) {
    const items = [];
    let idx = 1;
    for (const child of ulEl.children) {
      if (child.tagName !== "LI") continue;
      if (!isVisible(child)) continue;
      const bullet = ordered ? `${idx}.` : "-";
      idx++;
      const inner = childrenToMarkdown(child, ctx)
        .trim()
        .replace(/\n{2,}/g, "\n")
        .replace(/\n/g, "\n    ");
      items.push(`${bullet} ${inner}`);
    }
    return items.join("\n");
  }

  function tableToMarkdown(tableEl, ctx) {
    const rows = [];
    for (const section of ["THEAD", "TBODY", "TFOOT"]) {
      const sectionEl = tableEl.querySelector(section);
      if (sectionEl) {
        for (const row of sectionEl.querySelectorAll("tr")) {
          if (isVisible(row)) rows.push(row);
        }
      }
    }
    if (rows.length === 0) {
      for (const row of tableEl.querySelectorAll("tr")) {
        if (isVisible(row)) rows.push(row);
      }
    }
    if (rows.length === 0) return "";

    const matrix = rows.map((row) =>
      [...row.querySelectorAll("th, td")]
        .filter(isVisible)
        .map((cell) => childrenToMarkdown(cell, ctx).trim().replace(/\|/g, "\\|"))
    );

    const colCount = Math.max(...matrix.map((r) => r.length));
    const pad = (arr) => {
      while (arr.length < colCount) arr.push("");
      return arr;
    };

    const lines = [];
    matrix.forEach((cells, i) => {
      lines.push(`| ${pad(cells).join(" | ")} |`);
      if (i === 0) {
        lines.push(`|${" --- |".repeat(colCount)}`);
      }
    });

    return `\n\n${lines.join("\n")}\n\n`;
  }

  function postProcess(md) {
    return md
      .replace(/\n{4,}/g, "\n\n\n")
      .replace(/[ \t]+\n/g, "\n")
      .replace(/^\n+/, "")
      .replace(/\n+$/, "\n");
  }

  function exportToMarkdown() {
    const title = document.title || window.location.hostname;
    const url = window.location.href;
    const date = new Date().toISOString().replace("T", " ").slice(0, 19) + " UTC";

    let md = `# ${title}\n\n`;
    md += `> **Source:** [${url}](${url})  \n`;
    md += `> **Exported:** ${date}\n\n`;
    md += "---\n\n";

    const body = document.body;
    if (!body) {
      alert("No document body found.");
      return;
    }

    const rawMd = childrenToMarkdown(body, {});
    md += postProcess(rawMd);

    const slug = title
      .toLowerCase()
      .replace(/[^a-z0-9]+/g, "-")
      .replace(/^-+|-+$/g, "")
      .slice(0, 60);
    const filename = `${slug || "export"}.md`;

    const blob = new Blob([md], { type: "text/markdown;charset=utf-8" });
    const a = document.createElement("a");
    a.href = URL.createObjectURL(blob);
    a.download = filename;
    document.body.appendChild(a);
    a.click();
    setTimeout(() => {
      URL.revokeObjectURL(a.href);
      a.remove();
    }, 1000);

    showToast(`✓ Exported as ${filename}`);
  }

  function showToast(message) {
    const toast = document.createElement("div");
    Object.assign(toast.style, {
      position: "fixed",
      bottom: "80px",
      right: "20px",
      background: "#1a1a2e",
      color: "#e2f0ff",
      padding: "10px 18px",
      borderRadius: "8px",
      fontFamily: "system-ui, sans-serif",
      fontSize: "13px",
      fontWeight: "500",
      zIndex: "2147483647",
      boxShadow: "0 4px 20px rgba(0,0,0,0.35)",
      transition: "opacity 0.4s ease",
      opacity: "1",
      pointerEvents: "none",
    });
    toast.textContent = message;
    document.body.appendChild(toast);
    setTimeout(() => (toast.style.opacity = "0"), 2400);
    setTimeout(() => toast.remove(), 2800);
  }

  function createButton() {
    const btn = document.createElement("button");
    btn.textContent = "⬇ MD";
    btn.title = "Export page to Markdown";

    const baseStyle = {
      position: "fixed",
      bottom: "20px",
      right: "20px",
      zIndex: "2147483647",
      background: "#1a1a2e",
      color: "#7dd3fc",
      border: "1.5px solid #334155",
      borderRadius: "10px",
      padding: "8px 14px",
      fontFamily: "system-ui, monospace",
      fontSize: "12px",
      fontWeight: "700",
      letterSpacing: "0.05em",
      cursor: "pointer",
      boxShadow: "0 4px 18px rgba(0,0,0,0.4)",
      transition: "transform 0.15s ease, background 0.15s ease, box-shadow 0.15s ease",
      userSelect: "none",
    };

    Object.assign(btn.style, baseStyle);

    btn.addEventListener("mouseenter", () => {
      btn.style.background = "#0f172a";
      btn.style.boxShadow = "0 6px 24px rgba(0,0,0,0.5)";
      btn.style.transform = "translateY(-2px)";
    });
    btn.addEventListener("mouseleave", () => {
      btn.style.background = "#1a1a2e";
      btn.style.boxShadow = "0 4px 18px rgba(0,0,0,0.4)";
      btn.style.transform = "translateY(0)";
    });
    btn.addEventListener("mousedown", () => {
      btn.style.transform = "translateY(0) scale(0.96)";
    });
    btn.addEventListener("mouseup", () => {
      btn.style.transform = "translateY(-2px)";
    });

    let isDragging = false, startX, startY, startRight, startBottom;

    btn.addEventListener("pointerdown", (e) => {
      if (e.button !== 0) return;
      isDragging = false;
      startX = e.clientX;
      startY = e.clientY;
      startRight = parseInt(btn.style.right) || 20;
      startBottom = parseInt(btn.style.bottom) || 20;

      const onMove = (ev) => {
        const dx = ev.clientX - startX;
        const dy = ev.clientY - startY;
        if (Math.abs(dx) > 4 || Math.abs(dy) > 4) isDragging = true;
        if (isDragging) {
          btn.style.right = `${startRight - dx}px`;
          btn.style.bottom = `${startBottom - dy}px`;
        }
      };
      const onUp = () => {
        document.removeEventListener("pointermove", onMove);
        document.removeEventListener("pointerup", onUp);
      };

      document.addEventListener("pointermove", onMove);
      document.addEventListener("pointerup", onUp);
    });

    btn.addEventListener("click", (e) => {
      if (isDragging) {
        e.stopImmediatePropagation();
        isDragging = false;
        return;
      }
      exportToMarkdown();
    });

    document.body.appendChild(btn);
  }

  document.addEventListener("keydown", (e) => {
    if (e.altKey && e.shiftKey && e.key === "M") {
      e.preventDefault();
      exportToMarkdown();
    }
  });

  if (document.readyState === "loading") {
    document.addEventListener("DOMContentLoaded", createButton);
  } else {
    createButton();
  }
})();