Your AI agent can't read a scanned PDF. This gives it the text, page by page

feveroliang — Fri, 30 Oct 2026 17:37:41 +0000

Hand an AI agent a PDF link and one of two things happens. The file is too big for its context, or the PDF is a scan and contains no text at all.

So I built a tool that returns the text of any PDF, one row per page. Pages that are scans get read by OCR in the same run.

What the rows look like

The default run reads three PDFs, so you can see both paths:

a 14-page research paper, where every page is read from the text layer
two scanned brochures with no text layer, read by OCR at 91% confidence

Each row says how its page was read (text-layer or ocr) and carries the OCR confidence. Long pages are split into rows under 3 KB at paragraph breaks, which is the size an agent's context and a RAG index want. Each page is still charged once.

Why it's cheap and doesn't break

There's no third-party OCR service and no API key. pdf.js, the engine inside Firefox, reads the text layer, and Tesseract reads the scans, both inside the Actor. There's also no website to scrape, so there's no markup that can change under it.

PDF Text Extractor: $3 per 1,000 pages with text.
Image to Text OCR: the same OCR for screenshots, receipts and photos, at $4 per 1,000 images.

Blank pages and dead links are rows that say what went wrong, and they're never charged.

Ready to run: PDF to page-tagged chunks for RAG · scanned PDF to text · screenshot to text

What's the worst PDF you've had to get text out of?

I built a Google Play lead finder — pick a category, get every app company and its contact

feveroliang — Wed, 28 Oct 2026 09:27:40 +0000

Selling to app companies? Your prospect list is already on Google Play. You just can't export it.

So I built a tool that does: pick a category, get the apps in it with installs, rating and the developer email each company publishes on its listing.

What you get

Every app on the category page — 30 to 90 per category, per country
Installs, rating, genre, last update for each one
The developer's published email and website
Filters that run before you pay: minimum installs, "has an email"

How to use it

Pick categories — FINANCE, Health & Fitness, GAME_PUZZLE… or TOP
Pick countries — every store lists different apps
Run it → JSON, CSV or Excel

Fintech companies in the US and UK with 100K+ installs and a contact email took one run: 33 companies.

Why it doesn't break

Most Google Play scrapers use search or Google's internal API. Both are disallowed by Google Play's robots.txt, and both change without warning. This one reads only the public category pages a shopper browses, plus each app's public page. Slower to build. Much harder to break.

You pay only for apps that pass your filters.

👉 Try Google Play Category Apps

Ready to run: fintech companies · game studios · EdTech companies

Which category would you pull first? Tell me and I'll add a ready-made example for it.