Skip to content
Recued
Menu
← Back to recipes

Firecrawl page extraction brief

by recued-core v1

Read-only Firecrawl page extraction workflow. It scrapes one explicit URL through recued-core.firecrawl.page.scrape, summarizes the returned markdown and metadata, and shows key extraction counters. It never starts crawl jobs, runs browser actions, sends custom headers/cookies, bypasses TLS verification, registers webhooks, or calls arbitrary Firecrawl API routes.

How it works 9 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (9 steps)
normalized_url trim
Trim whitespace from setting url
scrape ?
links default
Apply default
link_count count
Count items in links
summarize ?
link_rows map
Extract from each item
link_table_rows slice
Take a subset of
link_table to_table
Format results as a data table
card to_summary
Format results as a summary card
Settings 10 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

url setting =
focus setting = Summarize the scraped page for a knowledge/RAG user: topic, key facts, useful links, missing sections, and any warnings. Do not invent facts outside the Firecrawl response.
formats setting = markdown,links
firecrawl setting =
max age ms setting = 172800000
max length setting = 900
timeout ms setting = 60000
exclude tags setting =
include tags setting =
only main content setting = true

Trust & control

What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.

Where it runs

Device + server Runs on your device (browser) or your server.

Permissions it requires

Read your Firecrawl connection
Declared by the recipe — Recued grants these at install, where you review them before approving.

Data it touches

Warehousedata.linksdata.metadatadata.markdowndata.warning

About

Tags

firecrawl firecrawlscrapingmarkdownextractionai-summarypack:firecrawl

Details

9 steps 10 configurable settings recipe_id: firecrawl-page-extraction-brief