Files
stash/extension/extract.js
Fredrik Johansson f2ebfe35d4 Initial build: stash server + browser extension
Server (Express + better-sqlite3 + FTS5, mirroring keep's stack):
/api/capture (upsert-on-url, per PROPOSAL.md's dedup decision),
/api/articles (list/search/mark-read/delete), plus a minimal
server-rendered reading list and reader view at / and /read/:id
(token passed as ?t= there since browser navigation can't set an
Authorization header). Bearer-token auth generated via `npm run
token` — no login flow, matching keep's one-time identity
registration pattern.

Extension (Manifest V3, sideloaded, no store distribution): toolbar
click or context menu "Send to stash" runs @mozilla/readability
(vendored into extension/lib/) against the current page, falling back
to raw rendered HTML when extraction comes back too thin. Options
page for one-time server URL + token entry.

Verified end-to-end with the real extension loaded in a live Chromium
instance (not just unit-tested extraction logic): capture against a
real page, dedup-on-recapture, mark-read, FTS5 search, 401 on missing
auth, and both server-rendered views all confirmed working.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-12 23:23:01 +02:00

32 lines
1.2 KiB
JavaScript

// Runs in the page as a content script, after lib/Readability.js has already
// been injected (see background.js's executeScript files array — order matters).
// Its return value becomes the result of chrome.scripting.executeScript.
(() => {
try {
const docClone = document.cloneNode(true);
const article = new Readability(docClone).parse();
if (article && article.textContent && article.textContent.trim().length > 200) {
return {
url: location.href,
title: article.title || document.title,
content_html: article.content,
content_text: article.textContent,
author: article.byline || undefined,
published_at: article.publishedTime || undefined,
};
}
} catch (e) {
// fall through to raw capture below
}
// Fallback: Readability either failed or returned too little to be useful
// (common on heavily JS-rendered pages) — capture what's actually rendered
// rather than failing outright. Worse capture beats no capture.
return {
url: location.href,
title: document.title,
content_html: document.body ? document.body.innerHTML : '',
content_text: document.body ? document.body.innerText : '',
};
})();