Spaces:
Sleeping
Sleeping
File size: 17,985 Bytes
097eaf0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 | # frozen_string_literal: true
require "json"
require "uri"
module Firecrawl
# Client for the Firecrawl v2 API.
#
# @example Quick start
# client = Firecrawl::Client.new(api_key: "fc-your-api-key")
#
# # Scrape a single page
# doc = client.scrape("https://example.com",
# Firecrawl::Models::ScrapeOptions.new(formats: ["markdown"]))
#
# # Crawl a website
# job = client.crawl("https://example.com",
# Firecrawl::Models::CrawlOptions.new(limit: 50))
class Client
DEFAULT_API_URL = "https://api.firecrawl.dev"
DEFAULT_TIMEOUT = 300 # seconds
DEFAULT_MAX_RETRIES = 3
DEFAULT_BACKOFF_FACTOR = 0.5
DEFAULT_POLL_INTERVAL = 2 # seconds
DEFAULT_JOB_TIMEOUT = 300 # seconds
# Creates a new Firecrawl client.
#
# @param api_key [String, nil] API key (falls back to FIRECRAWL_API_KEY env var)
# @param api_url [String] API base URL
# @param timeout [Integer] HTTP request timeout in seconds
# @param max_retries [Integer] maximum automatic retries for transient failures
# @param backoff_factor [Float] exponential backoff factor in seconds
def initialize(
api_key: nil,
api_url: nil,
timeout: DEFAULT_TIMEOUT,
max_retries: DEFAULT_MAX_RETRIES,
backoff_factor: DEFAULT_BACKOFF_FACTOR
)
resolved_key = api_key || ENV["FIRECRAWL_API_KEY"]
if resolved_key.nil? || resolved_key.strip.empty?
raise FirecrawlError, "API key is required. Provide api_key: or set FIRECRAWL_API_KEY environment variable."
end
resolved_url = api_url || ENV["FIRECRAWL_API_URL"] || DEFAULT_API_URL
unless resolved_url.match?(%r{\Ahttps?://}i)
raise FirecrawlError, "API URL must be a fully qualified HTTP or HTTPS URL (got: #{resolved_url})."
end
@http = HttpClient.new(
api_key: resolved_key,
base_url: resolved_url,
timeout: timeout,
max_retries: max_retries,
backoff_factor: backoff_factor
)
end
# Creates a client from the FIRECRAWL_API_KEY environment variable.
#
# @return [Client]
def self.from_env
new
end
# ================================================================
# SCRAPE
# ================================================================
# Scrapes a single URL and returns the document.
#
# @param url [String] the URL to scrape
# @param options [Models::ScrapeOptions, nil] scrape configuration
# @return [Models::Document]
def scrape(url, options = nil)
raise ArgumentError, "URL is required" if url.nil?
body = { "url" => url }
body.merge!(options.to_h) if options
raw = @http.post("/v2/scrape", body)
data = raw["data"] || raw
Models::Document.new(data)
end
# Interacts with the scrape-bound browser session for a scrape job.
#
# @param job_id [String] the scrape job ID
# @param code [String] the code to execute
# @param language [String] "python", "node", or "bash" (default: "node")
# @param timeout [Integer, nil] execution timeout in seconds (1-300)
# @return [Hash] execution result with stdout, stderr, exit_code
def interact(job_id, code, language: "node", timeout: nil)
raise ArgumentError, "Job ID is required" if job_id.nil?
raise ArgumentError, "Code is required" if code.nil?
body = { "code" => code, "language" => language }
body["timeout"] = timeout if timeout
@http.post("/v2/scrape/#{job_id}/interact", body)
end
# Stops the interactive browser session for a scrape job.
#
# @param job_id [String] the scrape job ID
# @return [Hash] stop response
def stop_interactive_browser(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
@http.delete("/v2/scrape/#{job_id}/interact")
end
# ================================================================
# PARSE
# ================================================================
# Parses an uploaded file and returns the extracted document.
#
# @param file [Models::ParseFile] file payload to upload
# @param options [Models::ParseOptions, nil] parse configuration
# @return [Models::Document]
def parse(file, options = nil)
raise ArgumentError, "File is required" if file.nil?
unless file.is_a?(Models::ParseFile)
raise ArgumentError, "File must be a Firecrawl::Models::ParseFile"
end
options_hash = options.nil? ? {} : options.to_h
raw = @http.post_multipart(
"/v2/parse",
fields: { "options" => JSON.generate(options_hash) },
file_field: "file",
filename: file.filename,
content: file.content,
content_type: file.content_type,
)
data = raw["data"] || raw
Models::Document.new(data)
end
# ================================================================
# CRAWL
# ================================================================
# Starts an async crawl job and returns immediately.
#
# @param url [String] the URL to start crawling from
# @param options [Models::CrawlOptions, nil] crawl configuration
# @return [Models::CrawlResponse]
def start_crawl(url, options = nil)
raise ArgumentError, "URL is required" if url.nil?
body = { "url" => url }
body.merge!(options.to_h) if options
raw = @http.post("/v2/crawl", body)
Models::CrawlResponse.new(raw)
end
# Gets the status and results of a crawl job.
#
# @param job_id [String] the crawl job ID
# @return [Models::CrawlJob]
def get_crawl_status(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
raw = @http.get("/v2/crawl/#{job_id}")
Models::CrawlJob.new(raw)
end
# Crawls a website and waits for completion (auto-polling).
#
# @param url [String] the URL to crawl
# @param options [Models::CrawlOptions, nil] crawl configuration
# @param poll_interval [Integer] seconds between status checks
# @param timeout [Integer] maximum seconds to wait
# @return [Models::CrawlJob]
def crawl(url, options = nil, poll_interval: DEFAULT_POLL_INTERVAL, timeout: DEFAULT_JOB_TIMEOUT)
start = start_crawl(url, options)
poll_crawl(start.id, poll_interval, timeout)
end
# Cancels a running crawl job.
#
# @param job_id [String] the crawl job ID
# @return [Hash]
def cancel_crawl(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
@http.delete("/v2/crawl/#{job_id}")
end
# Gets errors from a crawl job.
#
# @param job_id [String] the crawl job ID
# @return [Hash]
def get_crawl_errors(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
@http.get("/v2/crawl/#{job_id}/errors")
end
# ================================================================
# BATCH SCRAPE
# ================================================================
# Starts an async batch scrape job.
#
# @param urls [Array<String>] the URLs to scrape
# @param options [Models::BatchScrapeOptions, nil] batch scrape configuration
# @return [Models::BatchScrapeResponse]
def start_batch_scrape(urls, options = nil)
raise ArgumentError, "URLs list is required" if urls.nil?
body = { "urls" => urls }
extra_headers = {}
if options
opts_hash = options.to_h
# idempotencyKey goes as a header, not in body
if options.idempotency_key && !options.idempotency_key.empty?
extra_headers["x-idempotency-key"] = options.idempotency_key
end
# Flatten nested scrape options to top level (API expects this)
nested = opts_hash.delete("options")
body.merge!(opts_hash)
body.merge!(nested) if nested
end
raw = @http.post("/v2/batch/scrape", body, extra_headers: extra_headers)
Models::BatchScrapeResponse.new(raw)
end
# Gets the status and results of a batch scrape job.
#
# @param job_id [String] the batch scrape job ID
# @return [Models::BatchScrapeJob]
def get_batch_scrape_status(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
raw = @http.get("/v2/batch/scrape/#{job_id}")
Models::BatchScrapeJob.new(raw)
end
# Batch-scrapes URLs and waits for completion (auto-polling).
#
# @param urls [Array<String>] the URLs to scrape
# @param options [Models::BatchScrapeOptions, nil] batch scrape configuration
# @param poll_interval [Integer] seconds between status checks
# @param timeout [Integer] maximum seconds to wait
# @return [Models::BatchScrapeJob]
def batch_scrape(urls, options = nil, poll_interval: DEFAULT_POLL_INTERVAL, timeout: DEFAULT_JOB_TIMEOUT)
start = start_batch_scrape(urls, options)
poll_batch_scrape(start.id, poll_interval, timeout)
end
# Cancels a running batch scrape job.
#
# @param job_id [String] the batch scrape job ID
# @return [Hash]
def cancel_batch_scrape(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
@http.delete("/v2/batch/scrape/#{job_id}")
end
# ================================================================
# MAP
# ================================================================
# Discovers URLs on a website.
#
# @param url [String] the URL to map
# @param options [Models::MapOptions, nil] map configuration
# @return [Models::MapData]
def map(url, options = nil)
raise ArgumentError, "URL is required" if url.nil?
body = { "url" => url }
body.merge!(options.to_h) if options
raw = @http.post("/v2/map", body)
data = raw["data"] || raw
Models::MapData.new(data)
end
# ================================================================
# MONITOR
# ================================================================
def create_monitor(name:, schedule:, targets:, webhook: nil, notification: nil,
retention_days: nil, goal: nil, judge_enabled: nil)
body = {
"name" => name,
"schedule" => schedule,
"targets" => targets,
"webhook" => webhook,
"notification" => notification,
"retentionDays" => retention_days,
"goal" => goal,
"judgeEnabled" => judge_enabled,
}.compact
raw = @http.post("/v2/monitor", body)
Models::Monitor.new(raw["data"] || raw)
end
def list_monitors(limit: nil, offset: nil)
raw = @http.get("/v2/monitor#{query(limit: limit, offset: offset)}")
(raw["data"] || []).map { |item| Models::Monitor.new(item) }
end
def get_monitor(monitor_id)
raise ArgumentError, "Monitor ID is required" if monitor_id.nil?
raw = @http.get("/v2/monitor/#{monitor_id}")
Models::Monitor.new(raw["data"] || raw)
end
def update_monitor(monitor_id, **attrs)
raise ArgumentError, "Monitor ID is required" if monitor_id.nil?
body = {
"name" => attrs[:name],
"status" => attrs[:status],
"schedule" => attrs[:schedule],
"webhook" => attrs[:webhook],
"notification" => attrs[:notification],
"targets" => attrs[:targets],
"retentionDays" => attrs[:retention_days],
"goal" => attrs[:goal],
"judgeEnabled" => attrs[:judge_enabled],
}.compact
raw = @http.patch("/v2/monitor/#{monitor_id}", body)
Models::Monitor.new(raw["data"] || raw)
end
def delete_monitor(monitor_id)
raise ArgumentError, "Monitor ID is required" if monitor_id.nil?
@http.delete("/v2/monitor/#{monitor_id}")["success"] == true
end
def run_monitor(monitor_id)
raise ArgumentError, "Monitor ID is required" if monitor_id.nil?
raw = @http.post("/v2/monitor/#{monitor_id}/run", {})
Models::MonitorCheck.new(raw["data"] || raw)
end
def list_monitor_checks(monitor_id, limit: nil, offset: nil)
raise ArgumentError, "Monitor ID is required" if monitor_id.nil?
raw = @http.get("/v2/monitor/#{monitor_id}/checks#{query(limit: limit, offset: offset)}")
(raw["data"] || []).map { |item| Models::MonitorCheck.new(item) }
end
def get_monitor_check(monitor_id, check_id, limit: nil, skip: nil, status: nil, auto_paginate: true)
raise ArgumentError, "Monitor ID is required" if monitor_id.nil?
raise ArgumentError, "Check ID is required" if check_id.nil?
params = query(limit: limit, skip: skip, status: status)
raw = @http.get("/v2/monitor/#{monitor_id}/checks/#{check_id}#{params}")
data = raw["data"] || raw
data["next"] = raw["next"] if raw["next"]
check = Models::MonitorCheckDetail.new(data)
auto_paginate ? paginate_monitor_check(check) : check
end
# ================================================================
# SEARCH
# ================================================================
# Performs a web search.
#
# @param query [String] the search query
# @param options [Models::SearchOptions, nil] search configuration
# @return [Models::SearchData]
def search(query, options = nil)
raise ArgumentError, "Query is required" if query.nil?
body = { "query" => query }
body.merge!(options.to_h) if options
raw = @http.post("/v2/search", body)
data = raw["data"] || raw
Models::SearchData.new(data)
end
# ================================================================
# AGENT
# ================================================================
# Starts an async agent task.
#
# @param options [Models::AgentOptions] agent configuration
# @return [Models::AgentResponse]
def start_agent(options)
raise ArgumentError, "Agent options are required" if options.nil?
raw = @http.post("/v2/agent", options.to_h)
Models::AgentResponse.new(raw)
end
# Gets the status of an agent task.
#
# @param job_id [String] the agent job ID
# @return [Models::AgentStatusResponse]
def get_agent_status(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
raw = @http.get("/v2/agent/#{job_id}")
Models::AgentStatusResponse.new(raw)
end
# Runs an agent task and waits for completion (auto-polling).
#
# @param options [Models::AgentOptions] agent configuration
# @param poll_interval [Integer] seconds between status checks
# @param timeout [Integer] maximum seconds to wait
# @return [Models::AgentStatusResponse]
def agent(options, poll_interval: DEFAULT_POLL_INTERVAL, timeout: DEFAULT_JOB_TIMEOUT)
start = start_agent(options)
raise FirecrawlError, "Agent start did not return a job ID" if start.id.nil?
deadline = Time.now + timeout
while Time.now < deadline
status = get_agent_status(start.id)
return status if status.done?
sleep(poll_interval)
end
raise JobTimeoutError.new(start.id, timeout, "Agent")
end
# Cancels a running agent task.
#
# @param job_id [String] the agent job ID
# @return [Hash]
def cancel_agent(job_id)
raise ArgumentError, "Job ID is required" if job_id.nil?
@http.delete("/v2/agent/#{job_id}")
end
# ================================================================
# USAGE & METRICS
# ================================================================
# Gets current concurrency usage.
#
# @return [Models::ConcurrencyCheck]
def get_concurrency
raw = @http.get("/v2/concurrency-check")
Models::ConcurrencyCheck.new(raw)
end
# Gets current credit usage.
#
# @return [Models::CreditUsage]
def get_credit_usage
raw = @http.get("/v2/team/credit-usage")
data = raw["data"] || raw
Models::CreditUsage.new(data)
end
private
def query(**params)
compact = params.compact
compact.empty? ? "" : "?#{URI.encode_www_form(compact)}"
end
def poll_crawl(job_id, poll_interval, timeout)
deadline = Time.now + timeout
while Time.now < deadline
job = get_crawl_status(job_id)
return paginate_crawl(job) if job.done?
sleep(poll_interval)
end
raise JobTimeoutError.new(job_id, timeout, "Crawl")
end
def poll_batch_scrape(job_id, poll_interval, timeout)
deadline = Time.now + timeout
while Time.now < deadline
job = get_batch_scrape_status(job_id)
return paginate_batch_scrape(job) if job.done?
sleep(poll_interval)
end
raise JobTimeoutError.new(job_id, timeout, "Batch scrape")
end
def paginate_crawl(job)
job.data ||= []
current = job
while current.next_url && !current.next_url.empty?
raw = @http.get_absolute(current.next_url)
next_page = Models::CrawlJob.new(raw)
job.data.concat(next_page.data) unless next_page.data.empty?
current = next_page
end
job
end
def paginate_batch_scrape(job)
job.data ||= []
current = job
while current.next_url && !current.next_url.empty?
raw = @http.get_absolute(current.next_url)
next_page = Models::BatchScrapeJob.new(raw)
job.data.concat(next_page.data) unless next_page.data.empty?
current = next_page
end
job
end
def paginate_monitor_check(check)
check.pages ||= []
current = check
while current.next_url && !current.next_url.empty?
raw = @http.get_absolute(current.next_url)
data = raw["data"] || raw
data["next"] = raw["next"] if raw["next"]
next_page = Models::MonitorCheckDetail.new(data)
check.pages.concat(next_page.pages) unless next_page.pages.empty?
current = next_page
end
check.next_url = nil
check
end
end
end
|