HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
lightfeed
extractor
TypeScript2026–2026
lightfeed / extractor

extractor

Use LLMs to robustly extract web data

AI & Machine LearningWeb DevelopmentLanguages & CompilersProductivityScience & EngineeringData & DatabasesFinance & CommerceAutomation & Workflows
Explore on GitHubRead Hacker News discussions
2Distinct people
4Mentions
0Explicit recommenders
321GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Use LLMs to robustly extract web data

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 12:54:37 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by 3-hour interval4 dated mentions

Observed mentions: 2026-03-26 03:55:52 UTC to 2026-03-28 16:15:38 UTC.

0122026-03-26 03:00:00 UTC to 2026-03-26 06:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsMar 26, 03:002026-03-26 06:00:00 UTC to 2026-03-26 09:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2026-03-26 09:00:00 UTC to 2026-03-26 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-26 12:00:00 UTC to 2026-03-26 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-26 15:00:00 UTC to 2026-03-26 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-26 18:00:00 UTC to 2026-03-26 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-26 21:00:00 UTC to 2026-03-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-27 00:00:00 UTC to 2026-03-27 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-27 03:00:00 UTC to 2026-03-27 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-27 06:00:00 UTC to 2026-03-27 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-27 09:00:00 UTC to 2026-03-27 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsMar 27, 09:002026-03-27 12:00:00 UTC to 2026-03-27 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-27 15:00:00 UTC to 2026-03-27 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-27 18:00:00 UTC to 2026-03-27 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-27 21:00:00 UTC to 2026-03-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-28 00:00:00 UTC to 2026-03-28 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-28 03:00:00 UTC to 2026-03-28 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-28 06:00:00 UTC to 2026-03-28 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-28 09:00:00 UTC to 2026-03-28 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-28 12:00:00 UTC to 2026-03-28 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-03-28 15:00:00 UTC to 2026-03-28 18:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsMar 28, 15:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Mar 26, 03:002026-03-26 03:00:00 UTC2026-03-26 06:00:00 UTC110
Mar 26, 06:002026-03-26 06:00:00 UTC2026-03-26 09:00:00 UTC202
Mar 26, 09:002026-03-26 09:00:00 UTC2026-03-26 12:00:00 UTC000
Mar 26, 12:002026-03-26 12:00:00 UTC2026-03-26 15:00:00 UTC000
Mar 26, 15:002026-03-26 15:00:00 UTC2026-03-26 18:00:00 UTC000
Mar 26, 18:002026-03-26 18:00:00 UTC2026-03-26 21:00:00 UTC000
Mar 26, 21:002026-03-26 21:00:00 UTC2026-03-27 00:00:00 UTC000
Mar 27, 00:002026-03-27 00:00:00 UTC2026-03-27 03:00:00 UTC000
Mar 27, 03:002026-03-27 03:00:00 UTC2026-03-27 06:00:00 UTC000
Mar 27, 06:002026-03-27 06:00:00 UTC2026-03-27 09:00:00 UTC000
Mar 27, 09:002026-03-27 09:00:00 UTC2026-03-27 12:00:00 UTC000
Mar 27, 12:002026-03-27 12:00:00 UTC2026-03-27 15:00:00 UTC000
Mar 27, 15:002026-03-27 15:00:00 UTC2026-03-27 18:00:00 UTC000
Mar 27, 18:002026-03-27 18:00:00 UTC2026-03-27 21:00:00 UTC000
Mar 27, 21:002026-03-27 21:00:00 UTC2026-03-28 00:00:00 UTC000
Mar 28, 00:002026-03-28 00:00:00 UTC2026-03-28 03:00:00 UTC000
Mar 28, 03:002026-03-28 03:00:00 UTC2026-03-28 06:00:00 UTC000
Mar 28, 06:002026-03-28 06:00:00 UTC2026-03-28 09:00:00 UTC000
Mar 28, 09:002026-03-28 09:00:00 UTC2026-03-28 12:00:00 UTC000
Mar 28, 12:002026-03-28 12:00:00 UTC2026-03-28 15:00:00 UTC000
Mar 28, 15:002026-03-28 15:00:00 UTC2026-03-28 18:00:00 UTC101

What Hacker News says

4 sources
andrew_zhong·Mar 26, 2026Submission

Show HN: Robust LLM extractor for websites in TypeScript

We've been building data pipelines that scrape websites and extract structured data for a while now. If you've done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers. LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it's more painful than that: - Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you'd expect, especially with nested arrays and complex schemas. One bad bracket and your pipeline crashes. - Relative URLs, markdown-escaped links, tracking parameters — the "small" URL issues compound fast when you're processing thousands of pages. - You end up writing the same bo
Read the rest
ilerplate: HTML cleanup → markdown conversion → LLM call → JSON parsing → error recovery → schema validation. Over and over. We got tired of rebuilding this stack for every project, so we extracted it into a library. Lightfeed Extractor is a TypeScript library that handles the full pipeline from raw HTML to validated, structured data: - Converts HTML to LLM-ready markdown with main content extraction (strips nav, headers, footers), optional image inclusion, and URL cleaning - Works with any LangChain-compatible LLM (OpenAI, Gemini, Claude, Ollama, etc.) - Uses Zod schemas for type-safe extraction with real validation - Recovers partial data from malformed LLM output instead of failing entirely — if 19 out of 20 products parsed correctly, you get those 19 - Built-in browser automation via Playwright (local, serverless, or remote) with anti-bot patches - Pairs with our browser agent (@lightfeed/browser-agent) for AI-driven page navigation before extraction We use this ourselves in production at Lightfeed, and it's been solid enough that we decided to open-source it. GitHub: https://github.com/lightfeed/extractor npm: npm install @lightfeed/extractor Apache 2.0 licensed. Happy to answer questions or hear feedback.
72 points · Open discussion

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.