surface↓extraction↓web_scrape
Extractionscalar · returns table

WEB_SCRAPE

Extract structured data from a URL as a table (LLM-powered)

Per-row — runs once for each row.

extractionexternal-apiurl

Arguments

nametypedescription
urlVARCHARURL to scrape
schema_jsonVARCHARJSON Schema for extraction, e.g. '{"name":"string","price":"number"}'
prompt(optional)VARCHAROptional prompt to guide extraction

About

Extract structured data from a single URL into a table. The schema defines what columns to extract. Firecrawl uses LLM-powered extraction to parse the page content into the requested structure. SQL Usage: SELECT * FROM web_scrape('https://example.com/pricing', '{"tier": "string", "price": "number", "features": "string"}' ) -- With extraction guidance prompt: SELECT * FROM web_scrape('https://example.com/team', '{"name": "string", "role": "string", "bio": "string"}', 'Extract the leadership team members' )

Nearby rabbit holes

same domain
scalar

CRAWL_BATCH

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

extractionexternal-apiurl
scalar

EXTRACT

Extract specific information from unstructured text (zero-shot NER)

extractionnlispecialist-zootext
scalar

EXTRACT_LLM

LLM-backed extraction (escape hatch for EXTRACTS)

extractionllmllm-escape-hatchtext
scalar

EXTRACT_STRUCTURED

Extract structured fields from text per a user-supplied schema

extractionllmtext
aggregate

MERGE_TIMELINES

Merge multiple timelines into unified chronological sequence

extractionllmjson
scalar

PARSE

Extract information from text using natural-language instructions

extractionllmtext
Climb back to The Looking Glass