Document AI & Extractionfree

Domain Specific Web Content Crawler with Depth Control & Text Extraction

by Le NguyenUpdated Aug 2026

1/5

STEPS · 17

Starts on an incoming request

On a webhook request, crawls a domain in batches with depth control, extracts page text from HTML, and returns it in the response.

Webhook Fitbit Log With PDF Parsing

On a webhook, logs data to Fitbit and extracts content from a PDF.

Scrapes web content over HTTP, splits it, then uses Google Gemini to extract fields and summarize the results.

On a webhook request, reads an incoming PDF, processes its contents with OpenAI, saves the result to Google Drive, and emails it via Gmail.