surfaceextractioncrawl_batch
Extractionscalar · returns table

CRAWL_BATCH

Crawl a website and extract structured data from each page (via Firecrawl)

Per-row — runs once for each row.

extractionexternal-apiurl

Arguments

nametypedescription
urlVARCHARStarting URL or domain
schema_jsonVARCHARJSON Schema for per-page extraction
limit(optional)INTEGERMax pages to crawl
prompt(optional)VARCHAROptional extraction guidance prompt

About

Batch web crawl with optional structured extraction. Backend cascade for LARS CRAWL INTO syntax. Discovers URLs via /map, then either: - Extracts structured data per page (if schema provided) - Returns markdown content per page (if no schema)

Nearby rabbit holes

same domain
Climb back to The Looking Glass