langchain-firecrawl

This package contains the LangChain integration with Firecrawl, an API that turns websites into clean, LLM-ready data. It lets you scrape, crawl, map, extract structured data from, and search the web — as a document loader or as agent tools.

Quick Install

pip install langchain-firecrawl

Get an API key from firecrawl.dev and set it as the FIRECRAWL_API_KEY environment variable (or pass api_key=...).

export FIRECRAWL_API_KEY="fc-your-api-key"

Document loader

FirecrawlLoader loads web content as LangChain Documents. Pick a mode: scrape (one page), crawl (a whole site), map (discover URLs), extract (structured data), or search (web search).

from langchain_firecrawl import FirecrawlLoader

loader = FirecrawlLoader(url="https://www.firecrawl.dev", mode="scrape")
docs = loader.load()
print(docs[0].page_content[:200])
print(docs[0].metadata)

Tools

Each Firecrawl capability is also available as a BaseTool you can bind to an agent:

from langchain_firecrawl import (
    FirecrawlScrape,
    FirecrawlCrawl,
    FirecrawlMap,
    FirecrawlExtract,
    FirecrawlSearch,
)

scrape = FirecrawlScrape()
result = scrape.invoke({"url": "https://www.firecrawl.dev"})
print(result["markdown"])

search = FirecrawlSearch()
print(search.invoke({"query": "best web scraping libraries", "limit": 5}))

Documentation

• LangChain provider docs: docs.langchain.com
• Firecrawl docs: docs.firecrawl.dev
• Firecrawl homepage: firecrawl.dev