One Click Page Extractor - source text package This attachment contains source code as plain text. It is not an executable Chrome extension package. To restore, create the listed files under one-click-page-extractor/ with UTF-8 encoding, then add icons separately from the existing local folder if needed. ===== FILE: manifest.json ===== { "manifest_version": 3, "name": "One Click Page Extractor", "description": "Extract readable text, headings, and links from the current page and download them as Markdown, plain text, or a URL list.", "version": "1.0.0", "permissions": [ "activeTab", "scripting", "downloads" ], "action": { "default_popup": "popup.html" }, "icons": { "16": "icons/icon16.png", "48": "icons/icon48.png", "128": "icons/icon128.png" } } ===== END FILE: manifest.json ===== ===== FILE: popup.html ===== One Click Page Extractor

One Click Page Extractor

現在ページを確認中...

準備完了

===== END FILE: popup.html ===== ===== FILE: popup.css ===== :root { color-scheme: light; --bg: #f4f8ff; --card: #ffffff; --text: #152238; --muted: #5d6b80; --line: #d8e4f5; --primary: #1769e0; --primary-dark: #0f55b8; --primary-soft: #eaf2ff; --danger: #b42318; } * { box-sizing: border-box; } body { width: 340px; margin: 0; padding: 14px; background: var(--bg); color: var(--text); font-family: system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; font-size: 14px; } .popup-card { border: 1px solid var(--line); border-radius: 8px; background: var(--card); box-shadow: 0 10px 30px rgba(23, 105, 224, 0.10); padding: 14px; } .popup-header { display: grid; grid-template-columns: 38px minmax(0, 1fr); gap: 10px; align-items: center; margin-bottom: 14px; } .app-mark { display: grid; width: 38px; height: 38px; place-items: center; border-radius: 8px; background: var(--primary-soft); color: var(--primary); font-weight: 800; letter-spacing: 0; } h1 { margin: 0 0 4px; font-size: 16px; line-height: 1.25; } .page-title { min-height: 18px; margin: 0; overflow: hidden; color: var(--muted); font-size: 12px; line-height: 1.45; text-overflow: ellipsis; white-space: nowrap; } .button-grid { display: grid; grid-template-columns: 1fr; gap: 8px; } button { width: 100%; min-height: 38px; border: 1px solid var(--primary); border-radius: 6px; background: var(--primary); color: #ffffff; cursor: pointer; font: inherit; font-weight: 700; } button:hover { border-color: var(--primary-dark); background: var(--primary-dark); } button:disabled { border-color: #b9c6d8; background: #d7e0ed; color: #66758a; cursor: wait; } .status { min-height: 18px; margin: 12px 0 0; color: var(--muted); font-size: 12px; line-height: 1.5; } .status.is-error { color: var(--danger); font-weight: 700; } ===== END FILE: popup.css ===== ===== FILE: popup.js ===== const STATUS = { ready: "準備完了", extracting: "抽出中...", downloaded: "ダウンロードしました", extractFailed: "抽出に失敗しました", unsupportedPage: "このページでは抽出できません" }; const buttons = { downloadMarkdown: document.getElementById("downloadMarkdown"), downloadText: document.getElementById("downloadText"), downloadUrls: document.getElementById("downloadUrls") }; const pageTitle = document.getElementById("pageTitle"); const statusMessage = document.getElementById("statusMessage"); document.addEventListener("DOMContentLoaded", async () => { await updateCurrentTabTitle(); setStatus(STATUS.ready); buttons.downloadMarkdown.addEventListener("click", () => handleAction("markdown")); buttons.downloadText.addEventListener("click", () => handleAction("text")); buttons.downloadUrls.addEventListener("click", () => handleAction("urls")); }); async function updateCurrentTabTitle() { try { const tab = await getCurrentTab(); pageTitle.textContent = tab.title || "タイトルなし"; } catch (error) { pageTitle.textContent = "現在ページを取得できません"; } } async function handleAction(format) { setBusy(true); setStatus(STATUS.extracting); try { const data = await extractCurrentPage(); const extractedAt = formatDateTime(new Date()); const output = buildOutput(format, data, extractedAt); await downloadOutput(output, data.title, format); setStatus(STATUS.downloaded); } catch (error) { const isExpectedError = error && error.isExpected; setStatus(isExpectedError ? error.message : STATUS.extractFailed, true); } finally { setBusy(false); } } function buildOutput(format, data, extractedAt) { if (format === "markdown") { return buildMarkdown(data, extractedAt); } if (format === "urls") { return buildUrlList(data, extractedAt); } return buildPlainText(data, extractedAt); } async function getCurrentTab() { const tabs = await chrome.tabs.query({ active: true, currentWindow: true }); if (!tabs.length || !tabs[0].id) { throw new Error("No active tab found."); } return tabs[0]; } async function extractCurrentPage() { const tab = await getCurrentTab(); if (!canAccessTabUrl(tab.url)) { throw createExpectedError(STATUS.unsupportedPage); } const results = await chrome.scripting.executeScript({ target: { tabId: tab.id }, files: ["content.js"] }); const result = results && results[0] ? results[0].result : null; if (!result) { throw new Error("No extraction result returned."); } return result; } function canAccessTabUrl(url) { if (!url) { return false; } if (/^https:\/\/(chromewebstore\.google\.com|chrome\.google\.com\/webstore)\//i.test(url)) { return false; } return /^(https?:|file:)/i.test(url); } function createExpectedError(message) { const error = new Error(message); error.isExpected = true; return error; } function buildMarkdown(data, extractedAt) { const headings = data.headings && data.headings.length ? data.headings.map((heading) => { const indent = " ".repeat(Math.max(0, heading.level - 1)); return `${indent}- H${heading.level}: ${heading.text}`; }).join("\n") : "- 見出しなし"; const links = data.links && data.links.length ? data.links.map((link) => `- [${escapeMarkdownLinkText(link.text)}](${link.url})`).join("\n") : "- リンクなし"; return [ `# ${data.title}`, "", `Source: ${data.url}`, "", `Extracted at: ${extractedAt}`, "", "---", "", "## Headings", "", headings, "", "---", "", "## Content", "", data.content || "", "", "---", "", "## Links", "", links, "" ].join("\n"); } function buildPlainText(data, extractedAt) { const links = data.links && data.links.length ? data.links.map((link) => `${link.text} - ${link.url}`).join("\n") : "リンクなし"; return [ "Title:", data.title, "", "URL:", data.url, "", "Extracted at:", extractedAt, "", "Content:", data.content || "", "", "Links:", links, "" ].join("\n"); } function buildUrlList(data, extractedAt) { const seen = new Set(); const uniqueLinks = (data.allLinks || []).filter((link) => { if (!link.url || seen.has(link.url)) { return false; } seen.add(link.url); return true; }); const links = uniqueLinks.length ? uniqueLinks.map((link) => `${link.text} - ${link.url}`).join("\n") : "URLなし"; return [ "Title:", data.title, "", "URL:", data.url, "", "Extracted at:", extractedAt, "", "Page URLs:", links, "" ].join("\n"); } async function downloadOutput(content, title, format) { const extension = format === "markdown" ? "md" : "txt"; const mimeType = format === "markdown" ? "text/markdown" : "text/plain"; const blob = new Blob([content], { type: `${mimeType};charset=utf-8` }); const objectUrl = URL.createObjectURL(blob); try { await chrome.downloads.download({ url: objectUrl, filename: `${buildDownloadBaseName(title, format)}_${formatDateForFileName(new Date())}.${extension}`, saveAs: false }); } finally { setTimeout(() => URL.revokeObjectURL(objectUrl), 1000); } } function buildDownloadBaseName(title, format) { const suffix = format === "urls" ? "-urls" : ""; return `${buildSafeFileName(title)}${suffix}`; } function buildSafeFileName(title) { const safe = String(title || "") .normalize("NFKC") .toLowerCase() .replace(/[\\/:*?"<>|#%&{}$!`'@+=]/g, "-") .replace(/[\s._]+/g, "-") .replace(/-+/g, "-") .replace(/^-|-$/g, "") .slice(0, 80) .replace(/^-|-$/g, ""); return safe || "page"; } function formatDateTime(date) { const year = date.getFullYear(); const month = pad(date.getMonth() + 1); const day = pad(date.getDate()); const hours = pad(date.getHours()); const minutes = pad(date.getMinutes()); const seconds = pad(date.getSeconds()); return `${year}-${month}-${day} ${hours}:${minutes}:${seconds}`; } function formatDateForFileName(date) { const year = date.getFullYear(); const month = pad(date.getMonth() + 1); const day = pad(date.getDate()); return `${year}-${month}-${day}`; } function pad(value) { return String(value).padStart(2, "0"); } function escapeMarkdownLinkText(text) { return String(text || "").replace(/[[\]\\]/g, "\\$&"); } function setBusy(isBusy) { Object.values(buttons).forEach((button) => { button.disabled = isBusy; }); } function setStatus(message, isError = false) { statusMessage.textContent = message; statusMessage.classList.toggle("is-error", isError); } ===== END FILE: popup.js ===== ===== FILE: content.js ===== (() => { const CONTENT_SELECTORS = [ "article", "main", "[role=\"main\"]", ".article", ".post", ".entry-content", ".content" ]; const REMOVE_SELECTORS = [ "script", "style", "noscript", "iframe", "svg", "canvas", "nav", "footer", "header", "aside" ]; const AD_WORDS = [ "ad", "ads", "advertisement", "sponsor", "sponsored", "banner", "promo", "promotion" ]; function getCanonicalUrl() { const canonical = document.querySelector("link[rel~=\"canonical\"]"); const href = canonical && canonical.href ? canonical.href.trim() : ""; return href || window.location.href; } function normalizeText(value) { return String(value || "") .replace(/\u00a0/g, " ") .replace(/[ \t]+/g, " ") .replace(/\s*\n\s*/g, "\n") .replace(/\n{3,}/g, "\n\n") .trim(); } function isHidden(element) { const style = window.getComputedStyle(element); return style.display === "none" || style.visibility === "hidden" || style.opacity === "0" || element.hidden || element.getAttribute("aria-hidden") === "true"; } function isLikelyAdElement(element) { const marker = `${element.id || ""} ${element.className || ""}`.toLowerCase(); return AD_WORDS.some((word) => marker.includes(word)); } function findContentRoot() { for (const selector of CONTENT_SELECTORS) { const element = document.querySelector(selector); if (element) { return element; } } return document.body; } function cleanClone(source) { const clone = source.cloneNode(true); const sourceElements = source.querySelectorAll("*"); const cloneElements = clone.querySelectorAll("*"); cloneElements.forEach((element, index) => { const original = sourceElements[index]; if (original && (isHidden(original) || isLikelyAdElement(original))) { element.remove(); } }); clone.querySelectorAll(REMOVE_SELECTORS.join(",")).forEach((element) => element.remove()); return clone; } function getHeadings() { return Array.from(document.querySelectorAll("h1, h2, h3")) .map((heading) => ({ level: Number(heading.tagName.slice(1)), text: normalizeText(heading.textContent) })) .filter((heading) => heading.text); } function getLinks(root) { const seen = new Set(); return Array.from(root.querySelectorAll("a[href]")) .map((link) => ({ text: normalizeText(link.getAttribute("title")) || normalizeText(link.getAttribute("aria-label")) || normalizeText(link.textContent) || link.href, url: link.href })) .filter((link) => { if (!link.url || seen.has(`${link.text}\n${link.url}`)) { return false; } seen.add(`${link.text}\n${link.url}`); return true; }); } function getAllPageLinks() { return getLinks(document); } const sourceRoot = findContentRoot(); const cleanedRoot = cleanClone(sourceRoot); return { title: normalizeText(document.title) || "Untitled Page", url: getCanonicalUrl(), headings: getHeadings(), content: normalizeText(cleanedRoot.innerText || cleanedRoot.textContent), links: getLinks(cleanedRoot), allLinks: getAllPageLinks() }; })(); ===== END FILE: content.js ===== ===== FILE: README.md ===== # One Click Page Extractor One Click Page Extractor は、現在表示中のWebページから本文、H1〜H3見出し、リンクを抽出し、Markdown、プレーンテキスト、URL一覧としてローカル保存できるChrome拡張です。 ## 主な機能 - 現在タブのページタイトル、URL、本文、見出し、本文内リンクを抽出 - ページ全体のリンクタイトルとURL一覧を抽出 - 本文Markdown形式でダウンロード - 本文プレーンテキスト形式でダウンロード - URL一覧テキストをダウンロード ## 使い方 1. Chromeの拡張機能管理画面で、このフォルダを「パッケージ化されていない拡張機能」として読み込みます。 2. 抽出したいWebページを開きます。 3. ツールバーの拡張機能アイコンをクリックします。 4. 本文が必要な場合は「本文Markdown」「本文テキスト」を選びます。 5. ページ内のURLだけが必要な場合は「URL一覧」を選びます。 ## プライバシー方針 - 外部APIを使いません。 - 外部サーバーへ送信しません。 - CDNを使いません。 - リモートJavaScriptを読み込みません。 - アナリティクスを入れません。 - ユーザーデータを収集しません。 - 閲覧履歴を保存しません。 - 抽出内容はユーザーのブラウザ内だけで処理します。 ## 権限説明 - `activeTab`：ユーザー操作時のみ現在ページを抽出するため。 - `scripting`：現在タブ上で抽出処理を実行するため。 - `downloads`：抽出ファイルを端末に保存するため。 ## 初期版でしないこと - 画像ファイル本体の一括ダウンロード - HTML完全保存 - PDF化 - Notion連携 - ChatGPT/API連携 - 自動要約 - クラウド保存 - 履歴保存 - 複数ページ一括処理 ===== END FILE: README.md =====