Initial commit

Author: mon-jai

.github/workflows/archive.yml

@@ -0,0 +1,45 @@
+name: Archive Gemini Conversations
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  archive-gemini-conversations:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 23
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v3
+        with:
+          version: 10
+
+      - name: Install dependencies
+        run: |
+          pnpm install
+          pnpm exec playwright install --with-deps
+
+      - name: Archive Gemini conversations
+        id: archive
+        run: pnpm start
+
+      - name: Commit changes
+        run: |
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git add conversations/*.html || true
+          git add -u conversations/*.html || true
+          git diff --cached --quiet && exit 0
+          git commit -F .git/commitmsg
+          git push

.gitignore

@@ -0,0 +1,139 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.*
+!.env.example
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Sveltekit cache directory
+.svelte-kit/
+
+# vitepress build output
+**/.vitepress/dist
+
+# vitepress cache directory
+**/.vitepress/cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# Firebase cache directory
+.firebase/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v3
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/sdks
+!.yarn/versions
+
+# Vite logs files
+vite.config.js.timestamp-*
+vite.config.ts.timestamp-*

package.json

@@ -0,0 +1,19 @@
+{
+  "name": "gemini-archive",
+  "version": "1.0.0",
+  "type": "module",
+  "scripts": {
+    "start": "node --import @swc-node/register/esm-register src/archive.ts"
+  },
+  "dependencies": {
+    "@swc-node/register": "^1.10.10",
+    "async": "^3.2.6",
+    "playwright": "^1.54.2",
+    "single-file-cli": "^2.0.75"
+  },
+  "devDependencies": {
+    "@types/async": "^3.2.25",
+    "@types/node": "^24.2.1",
+    "typescript": "^5.9.2"
+  }
+}

src/archive.ts

@@ -0,0 +1,58 @@
+import { mkdir, writeFile } from "fs/promises"
+import { join } from "path"
+
+import { queue } from "async"
+import { type Browser, chromium } from "playwright"
+
+import { ARCHIVE_DIR } from "./constants.js"
+import {
+  archiveConversation,
+  buildCommitMessage,
+  deleteFile,
+  getArchivedConversations,
+  getGeminiIdsFromReadme
+} from "./util.js"
+
+await mkdir(ARCHIVE_DIR, { recursive: true })
+
+const listedIds = await getGeminiIdsFromReadme("README.md")
+const archivedMap = await getArchivedConversations(ARCHIVE_DIR)
+const archivedIds = new Set(archivedMap.keys())
+
+const newIds = [...listedIds].filter(id => !archivedIds.has(id))
+const staleIds = [...archivedIds].filter(id => !listedIds.has(id))
+
+// Delete stale
+const deleted: string[] = []
+for (const id of staleIds) {
+  const file = join(ARCHIVE_DIR, archivedMap.get(id)!)
+  if (await deleteFile(file)) deleted.push(id)
+}
+
+// Archive new conversations with async.queue
+const added: string[] = []
+const errored: string[] = []
+let browser: Browser | null = null
+
+try {
+  browser = await chromium.launch({ args: ["--disable-web-security"] })
+
+  const archiveQueue = queue<string>(async (id, callback) => {
+    try {
+      await archiveConversation(browser!, id)
+      added.push(id)
+    } catch (error) {
+      errored.push(id)
+    }
+    callback()
+  }, 10)
+
+  archiveQueue.push(newIds)
+  await archiveQueue.drain()
+} finally {
+  if (browser) await browser.close()
+}
+
+// Compose commit message and output it for workflow
+const commitMessage = buildCommitMessage(added, deleted)
+await writeFile(".git/commit-msg", commitMessage, "utf8")

src/constants.ts

@@ -0,0 +1,8 @@
+// @ts-expect-error
+import { getHookScriptSource, getScriptSource, getZipScriptSource } from "single-file-cli/lib/single-file-script.js"
+
+export const ARCHIVE_DIR = "./conversations"
+
+export const SCRIPT = (await getScriptSource({})) + "; window.singlefile = singlefile"
+export const HOOK_SCRIPT = await getHookScriptSource()
+export const ZIP_SCRIPT = await getZipScriptSource()

src/util.ts

@@ -0,0 +1,104 @@
+import { readFile, readdir, unlink, writeFile } from "fs/promises"
+import { join } from "path"
+
+import type { Browser } from "playwright"
+
+import { ARCHIVE_DIR, HOOK_SCRIPT, SCRIPT, ZIP_SCRIPT } from "./constants.js"
+
+export async function getGeminiIdsFromReadme(readmePath: string): Promise<Set<string>> {
+  const readme = await readFile(readmePath, "utf8")
+  const matches = readme.matchAll(/https:\/\/(?:gemini\.google\.com|g\.co\/gemini)\/share\/(?<id>[^\/\s]+)/g)
+
+  const ids = new Set<string>()
+  for (const match of matches) ids.add(match.groups!.id!)
+  return ids
+}
+
+export async function getArchivedConversations(archiveDir: string): Promise<Map<string, string>> {
+  const files = await readdir(archiveDir)
+  const map = new Map<string, string>()
+
+  for (const file of files) {
+    const match = file.match(/^(?<id>[^-]+) - .+\.html$/)
+    if (match) map.set(match.groups?.["id"] as string, file)
+  }
+  return map
+}
+
+export async function deleteFile(filePath: string) {
+  try {
+    await unlink(filePath)
+    return true
+  } catch {
+    return false
+  }
+}
+
+export async function archiveConversation(browser: Browser, id: string) {
+  const url = `https://gemini.google.com/share/${id}`
+  let page
+
+  try {
+    page = await browser.newPage({ bypassCSP: true })
+    // https://github.com/gildas-lormeau/single-file-cli/blob/v2.0.75/lib/cdp-client.js#L235-L243
+    await page.addInitScript({ content: HOOK_SCRIPT })
+    await page.addInitScript({ content: SCRIPT })
+
+    await page.goto(url)
+    await page.waitForSelector("message-content", { timeout: 20000 })
+    await page.waitForTimeout(3000)
+
+    // Click all visible elements with text starting with "Show"
+    const showButtons = await page.getByText("Show").all()
+    for (const btn of showButtons) {
+      if (await btn.isVisible()) await btn.click()
+    }
+
+    const title = // @ts-expect-error
+      (await page.evaluate(() => document.querySelector("h1 > strong").textContent, "")).substring(0, 100)
+
+    // https://github.com/gildas-lormeau/single-file-cli/blob/v2.0.75/single-file-cli-api.js#L258
+    // https://github.com/gildas-lormeau/single-file-cli/blob/v2.0.75/lib/cdp-client.js#L332
+    // https://github.com/gildas-lormeau/single-file-core/blob/212a657/single-file.js#L125
+    // @ts-expect-error
+    const pageData = await page.evaluate(async options => await singlefile.getPageData(options), {
+      zipScript: ZIP_SCRIPT
+    })
+
+    const fileContent = pageData.content
+      .replaceAll(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>\s*/gi, "")
+      .replaceAll(/@font-face\s*{\s*[^}]+font-family:\s*codicon[^}]+}/gi, "")
+      .replaceAll(/@font-face\s*\{[^}]*\}/g, (fontFaceRule: string) => {
+        const fontFamilyMatch = fontFaceRule.match(/font-family:\s*(?<quote>['"]?)(?<fontFamily>[^'"]+)\k<quote>;/)
+
+        if (fontFamilyMatch && fontFamilyMatch.groups?.fontFamily) {
+          const fontFamily = fontFamilyMatch.groups?.fontFamily.trim()
+          if (fontFamily === "Google Symbols") return fontFaceRule
+          if (pageData.content.includes(`class="katex"`) && fontFamily.startsWith("KaTeX")) return fontFaceRule
+        }
+
+        return ""
+      })
+
+    // Remove illegal filename chars
+    const sanitizedTitle = title.replace(/[\\/:*?"<>|\n]/g, "")
+    const filepath = join(ARCHIVE_DIR, `${id} - ${sanitizedTitle}.html`)
+    await writeFile(filepath, fileContent)
+
+    await page.close()
+  } catch (err) {
+    if (page) await page.close()
+
+    console.error(`Failed to archive ${id}: ${(err as Error).message}`)
+    throw err
+  }
+}
+
+export function buildCommitMessage(added: string[], deleted: string[]): string {
+  let msg = "chore: Automatic conversation archive\n"
+
+  if (added.length > 0) msg += `\nAdded conversations: ${added.join(", ")}`
+  if (deleted.length > 0) msg += `\nDeleted conversations: ${deleted.join(", ")}`
+
+  return msg
+}