Capacidades

# pip install firecrawl-py
from firecrawl import Firecrawl

firecrawl = Firecrawl(api_key="fc-YOUR-API-KEY")

scrape_result = firecrawl.scrape("firecrawl.dev", formats=["markdown", "html"])
print(scrape_result)

// npm install firecrawl
import { Firecrawl } from "firecrawl";

const firecrawl = new Firecrawl({ apiKey: "fc-YOUR-API-KEY" });

const scrapeResult = await firecrawl.scrape("firecrawl.dev", { formats: ["markdown", "html"] });
console.log(scrapeResult);

result = firecrawl.scrape("https://example.com/contact", formats=["markdown"])
scrape_id = result.metadata.scrape_id

response = firecrawl.interact(
  scrape_id,
  prompt="Type test@example.com into the email field",
  timeout=60,
)
print(response.output)
firecrawl.stop_interaction(scrape_id)

session = firecrawl.browser()

result = firecrawl.browser_execute(
  session.id,
  code='await page.goto("https://news.ycombinator.com")\ntitle = await page.title()\nprint(title)',
  language="python",
)
print(result.result)

firecrawl.delete_browser(session.id)

# Sesión 1: iniciar sesión y guardar el estado
result = firecrawl.scrape(
  "https://app.example.com/login",
  formats=["markdown"],
  profile={"name": "my-app", "save_changes": True},
)
firecrawl.interact(result.metadata.scrape_id, prompt="Fill in user@example.com and password, then click Login")
firecrawl.stop_interaction(result.metadata.scrape_id)

# Sesión 2: reutilizar el mismo perfil, con la sesión ya iniciada
result = firecrawl.scrape(
  "https://app.example.com/dashboard",
  formats=["markdown"],
  profile={"name": "my-app", "save_changes": False},
)

result = firecrawl.scrape("https://example.com/spa", formats=["markdown"])
print(result.markdown)

doc = firecrawl.parse("./report.pdf")
print(doc.markdown)

results = firecrawl.search(
  "firecrawl web scraping",
  limit=3,
  scrape_options={"formats": ["markdown", "links"]},
)

result = firecrawl.scrape(
  "https://firecrawl.dev",
  formats=[{"type": "json", "prompt": "Extract the company mission from the page."}],
  only_main_content=False,
  timeout=120000,
)
print(result)

git clone https://github.com/firecrawl/firecrawl.git
cd firecrawl
git checkout v2.11.162