Ruby

require "firecrawl"

client = Firecrawl::Client.from_env

doc = client.scrape(
  "https://firecrawl.dev",
  Firecrawl::Models::ScrapeOptions.new(formats: ["markdown"])
)

job = client.crawl(
  "https://firecrawl.dev",
  Firecrawl::Models::CrawlOptions.new(limit: 5)
)

puts doc.markdown
puts "Crawled pages: #{job.data&.size || 0}"

doc = client.scrape(
  "https://firecrawl.dev",
  Firecrawl::Models::ScrapeOptions.new(
    formats: ["markdown", "html"],
    only_main_content: true,
    wait_for: 5000
  )
)

puts doc.markdown
puts doc.metadata["title"]

doc = client.scrape(
  "https://example.com/product",
  Firecrawl::Models::ScrapeOptions.new(
    formats: [
      {
        "type" => "json",
        "prompt" => "Extract the product name and price",
        "schema" => {
          "type" => "object",
          "properties" => {
            "name" => { "type" => "string" },
            "price" => { "type" => "number" }
          }
        }
      }
    ]
  )
)

puts doc.json

job = client.crawl(
  "https://firecrawl.dev",
  Firecrawl::Models::CrawlOptions.new(
    limit: 50,
    max_discovery_depth: 3,
    scrape_options: Firecrawl::Models::ScrapeOptions.new(
      formats: ["markdown"]
    )
  )
)

puts "Status: #{job.status}"
puts "Progress: #{job.completed}/#{job.total}"

job.data&.each do |page|
  puts page.metadata["sourceURL"]
end

response = client.start_crawl(
  "https://firecrawl.dev",
  Firecrawl::Models::CrawlOptions.new(limit: 100)
)

puts "Job ID: #{response.id}"

status = client.get_crawl_status(response.id)
puts "Status: #{status.status}"
puts "Progress: #{status.completed}/#{status.total}"

result = client.cancel_crawl(response.id)
puts result

data = client.map(
  "https://firecrawl.dev",
  Firecrawl::Models::MapOptions.new(
    limit: 100,
    search: "blog"
  )
)

data.links&.each do |link|
  puts "#{link["url"]} - #{link["title"]}"
end

results = client.search(
  "firecrawl web scraping",
  Firecrawl::Models::SearchOptions.new(limit: 10)
)

results.web&.each do |result|
  puts "#{result["title"]} - #{result["url"]}"
end

job = client.batch_scrape(
  ["https://firecrawl.dev", "https://firecrawl.dev/blog"],
  Firecrawl::Models::BatchScrapeOptions.new(
    options: Firecrawl::Models::ScrapeOptions.new(
      formats: ["markdown"]
    )
  )
)

job.data&.each do |doc|
  puts doc.markdown
end

result = client.agent(
  Firecrawl::Models::AgentOptions.new(
    prompt: "Find the pricing plans for Firecrawl and compare them"
  )
)

puts result.data

result = client.agent(
  Firecrawl::Models::AgentOptions.new(
    prompt: "Extract pricing plan details",
    urls: ["https://firecrawl.dev"],
    schema: {
      "type" => "object",
      "properties" => {
        "plans" => {
          "type" => "array",
          "items" => {
            "type" => "object",
            "properties" => {
              "name" => { "type" => "string" },
              "price" => { "type" => "string" }
            }
          }
        }
      }
    }
  )
)

puts result.data

concurrency = client.get_concurrency
puts "Concurrency: #{concurrency.concurrency}/#{concurrency.max_concurrency}"

credits = client.get_credit_usage
puts "Remaining credits: #{credits.remaining_credits}"

scrape_job_id = "550e8400-e29b-41d4-a716-446655440000"

run = client.interact(
  scrape_job_id,
  "console.log(page.url());",
  language: "node",
  timeout: 60
)

puts run["stdout"]

deleted = client.stop_interactive_browser(scrape_job_id)
puts "Deleted: #{deleted["success"]}"

client = Firecrawl::Client.new(
  api_key: "fc-your-api-key",
  api_url: "https://api.firecrawl.dev",
  timeout: 300,
  max_retries: 3,
  backoff_factor: 0.5
)

begin
  doc = client.scrape("https://example.com")
rescue Firecrawl::AuthenticationError => e
  puts "Auth failed: #{e.message}"
rescue Firecrawl::RateLimitError => e
  puts "Rate limited: #{e.message}"
rescue Firecrawl::JobTimeoutError => e
  puts "Job #{e.job_id} timed out after #{e.timeout_seconds}s"
rescue Firecrawl::FirecrawlError => e
  puts "Error (#{e.status_code}): #{e.message}"
end