Spaces:
Sleeping
Sleeping
File size: 30,205 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 | """
Async v2 client mirroring the regular client surface using true async HTTP transport.
"""
import os
import asyncio
import time
from pathlib import Path
from typing import Optional, List, Dict, Any, Union, Callable, Literal, BinaryIO
from .types import (
ParseOptions,
ScrapeOptions,
CrawlRequest,
WebhookConfig,
AgentWebhookConfig,
MonitorWebhookConfig,
SearchRequest,
SearchData,
SourceOption,
CrawlResponse,
CrawlJob,
CrawlParamsRequest,
CrawlParamsData,
CrawlErrorsResponse,
ActiveCrawlsResponse,
MapOptions,
MapData,
FormatOption,
WaitAction,
ScreenshotAction,
ClickAction,
WriteAction,
PressAction,
ScrollAction,
ScrapeAction,
ExecuteJavascriptAction,
PDFAction,
Location,
PaginationConfig,
Monitor,
MonitorCheck,
MonitorCheckDetail,
MonitorCreateRequest,
MonitorNotification,
MonitorSchedule,
MonitorTarget,
MonitorUpdateRequest,
)
from .utils.http_client import HttpClient
from .utils.http_client_async import AsyncHttpClient
from .methods.aio import scrape as async_scrape # type: ignore[attr-defined]
from .methods.aio import parse as async_parse # type: ignore[attr-defined]
from .methods.aio import batch as async_batch # type: ignore[attr-defined]
from .methods.aio import crawl as async_crawl # type: ignore[attr-defined]
from .methods.aio import search as async_search # type: ignore[attr-defined]
from .methods.aio import map as async_map # type: ignore[attr-defined]
from .methods.aio import usage as async_usage # type: ignore[attr-defined]
from .methods.aio import extract as async_extract # type: ignore[attr-defined]
from .methods.aio import agent as async_agent # type: ignore[attr-defined]
from .methods.aio import browser as async_browser # type: ignore[attr-defined]
from .methods.aio import monitor as async_monitor # type: ignore[attr-defined]
from .client import _SCRAPE_OPTION_KEYS
from .watcher_async import AsyncWatcher
class AsyncFirecrawlClient:
@staticmethod
def _is_cloud_service(url: str) -> bool:
return "api.firecrawl.dev" in url.lower()
def __init__(
self,
api_key: Optional[str] = None,
api_url: str = "https://api.firecrawl.dev",
timeout: Optional[float] = None,
max_retries: int = 3,
backoff_factor: float = 0.5,
):
if api_key is None:
api_key = os.getenv("FIRECRAWL_API_KEY")
if self._is_cloud_service(api_url) and not api_key:
raise ValueError("API key is required for the cloud API. Set FIRECRAWL_API_KEY or pass api_key.")
self.http_client = HttpClient(
api_key,
api_url,
timeout=timeout,
max_retries=max_retries,
backoff_factor=backoff_factor,
)
self.async_http_client = AsyncHttpClient(
api_key,
api_url,
timeout=timeout,
max_retries=max_retries,
backoff_factor=backoff_factor,
)
# Scrape
async def scrape(
self,
url: str,
**kwargs,
):
options = ScrapeOptions(**{k: v for k, v in kwargs.items() if v is not None}) if kwargs else None
return await async_scrape.scrape(self.async_http_client, url, options)
async def interact(
self,
job_id: str,
code: Optional[str] = None,
*,
prompt: Optional[str] = None,
language: Literal["python", "node", "bash"] = "node",
timeout: Optional[int] = None,
origin: Optional[str] = None,
):
return await async_scrape.interact(
self.async_http_client,
job_id,
code,
prompt=prompt,
language=language,
timeout=timeout,
origin=origin,
)
async def stop_interaction(self, job_id: str):
return await async_scrape.stop_interaction(
self.async_http_client,
job_id,
)
async def stop_interactive_browser(self, job_id: str):
"""Deprecated alias for stop_interaction()."""
return await self.stop_interaction(job_id)
async def scrape_execute(
self,
job_id: str,
code: Optional[str] = None,
*,
prompt: Optional[str] = None,
language: Literal["python", "node", "bash"] = "node",
timeout: Optional[int] = None,
origin: Optional[str] = None,
):
"""Deprecated alias for interact()."""
return await self.interact(
job_id,
code,
prompt=prompt,
language=language,
timeout=timeout,
origin=origin,
)
async def delete_scrape_browser(self, job_id: str):
"""Deprecated alias for stop_interaction()."""
return await self.stop_interaction(job_id)
async def scrape_url(self, url: str, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer scrape()."""
return await self.scrape(url, **kwargs)
async def crawl_url(self, url: str, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer crawl()."""
return await self.crawl(url=url, **kwargs)
async def map_url(self, url: str, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer map()."""
return await self.map(url, **kwargs)
async def async_crawl_url(self, url: str, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer start_crawl()."""
return await self.start_crawl(url, **kwargs)
async def check_crawl_status(self, id: str, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer get_crawl_status()."""
return await self.get_crawl_status(id, **kwargs)
async def check_crawl_errors(self, id: str):
"""V1 compatibility alias for agent recovery. Prefer get_crawl_errors()."""
return await self.get_crawl_errors(id)
async def batch_scrape_urls(self, urls, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer batch_scrape()."""
return await self.batch_scrape(urls, **kwargs)
async def async_batch_scrape_urls(self, urls, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer start_batch_scrape()."""
return await self.start_batch_scrape(urls, **kwargs)
async def check_batch_scrape_status(self, id: str, **kwargs):
"""V1 compatibility alias for agent recovery. Prefer get_batch_scrape_status()."""
return await self.get_batch_scrape_status(id, **kwargs)
async def check_batch_scrape_errors(self, id: str):
"""V1 compatibility alias for agent recovery. Prefer get_batch_scrape_errors()."""
return await self.get_batch_scrape_errors(id)
async def parse(
self,
file: Union[str, Path, bytes, bytearray, BinaryIO],
*,
filename: Optional[str] = None,
content_type: Optional[str] = None,
options: Optional[ParseOptions] = None,
):
return await async_parse.parse(
self.async_http_client,
file,
options=options,
filename=filename,
content_type=content_type,
)
# Search
async def search(
self,
query: str,
**kwargs,
) -> SearchData:
request = SearchRequest(query=query, **{k: v for k, v in kwargs.items() if v is not None})
return await async_search.search(self.async_http_client, request)
async def start_crawl(self, url: str, **kwargs) -> CrawlResponse:
if kwargs.get("scrape_options") is None:
scrape_kwargs = {k: kwargs.pop(k) for k in list(kwargs) if k in _SCRAPE_OPTION_KEYS and kwargs[k] is not None}
if scrape_kwargs:
kwargs["scrape_options"] = ScrapeOptions(**scrape_kwargs)
else:
for k in list(kwargs):
if k in _SCRAPE_OPTION_KEYS:
kwargs.pop(k)
sitemap = kwargs.pop("sitemap", None)
ignore_sitemap = kwargs.pop("ignore_sitemap", None)
if sitemap is None and ignore_sitemap is not None:
sitemap = "skip" if ignore_sitemap else "include"
if sitemap is not None:
kwargs["sitemap"] = sitemap
request = CrawlRequest(url=url, **kwargs)
return await async_crawl.start_crawl(self.async_http_client, request)
async def wait_crawl(
self,
job_id: str,
poll_interval: int = 2,
timeout: Optional[int] = None,
*,
request_timeout: Optional[float] = None,
) -> CrawlJob:
"""
Polls the status of a crawl job until it reaches a terminal state.
Args:
job_id (str): The ID of the crawl job to poll.
poll_interval (int, optional): Number of seconds to wait between polling attempts. Defaults to 2.
timeout (Optional[int], optional): Maximum number of seconds to wait for the entire crawl job to complete before timing out. If None, waits indefinitely. Defaults to None.
request_timeout (Optional[float], optional): Timeout (in seconds) for each individual HTTP request, including pagination requests when fetching results. If there are multiple pages, each page request gets this timeout. If None, no per-request timeout is set. Defaults to None.
Returns:
CrawlJob: The final status of the crawl job when it reaches a terminal state.
Raises:
TimeoutError: If the crawl does not reach a terminal state within the specified timeout.
Terminal states:
- "completed": The crawl finished successfully.
- "failed": The crawl finished with an error.
- "cancelled": The crawl was cancelled.
"""
start = time.monotonic()
while True:
status = await async_crawl.get_crawl_status(
self.async_http_client,
job_id,
request_timeout=request_timeout,
)
if status.status in ["completed", "failed", "cancelled"]:
return status
if timeout and (time.monotonic() - start) > timeout:
raise TimeoutError("Crawl wait timed out")
await asyncio.sleep(poll_interval)
async def crawl(self, **kwargs) -> CrawlJob:
# wrapper combining start and wait
resp = await self.start_crawl(
**{k: v for k, v in kwargs.items() if k not in ("poll_interval", "timeout", "request_timeout")}
)
poll_interval = kwargs.get("poll_interval", 2)
timeout = kwargs.get("timeout")
request_timeout = kwargs.get("request_timeout")
effective_request_timeout = request_timeout if request_timeout is not None else timeout
return await self.wait_crawl(
resp.id,
poll_interval=poll_interval,
timeout=timeout,
request_timeout=effective_request_timeout,
)
async def get_crawl_status(
self,
job_id: str,
pagination_config: Optional[PaginationConfig] = None,
*,
request_timeout: Optional[float] = None,
) -> CrawlJob:
"""
Get the status of a crawl job.
Args:
job_id: ID of the crawl job
pagination_config: Optional configuration for pagination behavior
request_timeout: Timeout (in seconds) for each individual HTTP request. When auto-pagination
is enabled (default) and there are multiple pages of results, this timeout applies to
each page request separately, not to the entire operation
Returns:
CrawlJob with current status and data
Raises:
Exception: If the status check fails
"""
return await async_crawl.get_crawl_status(
self.async_http_client,
job_id,
pagination_config=pagination_config,
request_timeout=request_timeout,
)
async def get_crawl_status_page(
self,
next_url: str,
*,
request_timeout: Optional[float] = None,
) -> CrawlJob:
"""
Fetch a single page of crawl results using a next URL.
Args:
next_url: Opaque next URL from a prior crawl status response
request_timeout: Timeout (in seconds) for the HTTP request
Returns:
CrawlJob with the page data and next URL (if any)
"""
return await async_crawl.get_crawl_status_page(
self.async_http_client,
next_url,
request_timeout=request_timeout,
)
async def cancel_crawl(self, job_id: str) -> bool:
return await async_crawl.cancel_crawl(self.async_http_client, job_id)
async def crawl_params_preview(self, url: str, prompt: str) -> CrawlParamsData:
req = CrawlParamsRequest(url=url, prompt=prompt)
return await async_crawl.crawl_params_preview(self.async_http_client, req)
async def get_crawl_errors(self, crawl_id: str) -> CrawlErrorsResponse:
return await async_crawl.get_crawl_errors(self.async_http_client, crawl_id)
async def get_active_crawls(self) -> ActiveCrawlsResponse:
return await async_crawl.get_active_crawls(self.async_http_client)
async def active_crawls(self) -> ActiveCrawlsResponse:
return await self.get_active_crawls()
# Map
async def map(
self,
url: str,
*,
search: Optional[str] = None,
include_subdomains: Optional[bool] = None,
limit: Optional[int] = None,
sitemap: Optional[Literal["only", "include", "skip"]] = None,
timeout: Optional[int] = None,
integration: Optional[str] = None,
) -> MapData:
options = MapOptions(
search=search,
include_subdomains=include_subdomains,
limit=limit,
sitemap=sitemap if sitemap is not None else "include",
timeout=timeout,
integration=integration,
) if any(v is not None for v in [search, include_subdomains, limit, sitemap, integration, timeout]) else None
return await async_map.map(self.async_http_client, url, options)
async def create_monitor(
self,
name: str,
schedule: Union[MonitorSchedule, Dict[str, Any]],
targets: List[Union[MonitorTarget, Dict[str, Any]]],
*,
webhook: Optional[Union[MonitorWebhookConfig, Dict[str, Any]]] = None,
notification: Optional[MonitorNotification] = None,
retention_days: Optional[int] = None,
goal: Optional[str] = None,
judge_enabled: Optional[bool] = None,
) -> Monitor:
if isinstance(schedule, dict):
schedule = MonitorSchedule(**schedule)
request = MonitorCreateRequest(
name=name,
schedule=schedule,
targets=targets,
webhook=webhook,
notification=notification,
retention_days=retention_days,
goal=goal,
judge_enabled=judge_enabled,
)
return await async_monitor.create_monitor(self.async_http_client, request)
async def list_monitors(
self,
*,
limit: Optional[int] = None,
offset: Optional[int] = None,
) -> List[Monitor]:
return await async_monitor.list_monitors(
self.async_http_client,
limit=limit,
offset=offset,
)
async def get_monitor(self, monitor_id: str) -> Monitor:
return await async_monitor.get_monitor(self.async_http_client, monitor_id)
async def update_monitor(
self,
monitor_id: str,
*,
name: Optional[str] = None,
status: Optional[Literal["active", "paused"]] = None,
schedule: Optional[Union[MonitorSchedule, Dict[str, Any]]] = None,
webhook: Optional[Union[MonitorWebhookConfig, Dict[str, Any]]] = None,
notification: Optional[Union[MonitorNotification, Dict[str, Any]]] = None,
targets: Optional[List[Union[MonitorTarget, Dict[str, Any]]]] = None,
retention_days: Optional[int] = None,
goal: Optional[str] = None,
judge_enabled: Optional[bool] = None,
) -> Monitor:
if isinstance(schedule, dict):
schedule = MonitorSchedule(**schedule)
request = MonitorUpdateRequest(
name=name,
status=status,
schedule=schedule,
webhook=webhook,
notification=notification,
targets=targets,
retention_days=retention_days,
goal=goal,
judge_enabled=judge_enabled,
)
return await async_monitor.update_monitor(
self.async_http_client,
monitor_id,
request,
)
async def delete_monitor(self, monitor_id: str) -> bool:
return await async_monitor.delete_monitor(self.async_http_client, monitor_id)
async def run_monitor(self, monitor_id: str) -> MonitorCheck:
return await async_monitor.run_monitor(self.async_http_client, monitor_id)
async def list_monitor_checks(
self,
monitor_id: str,
*,
limit: Optional[int] = None,
offset: Optional[int] = None,
) -> List[MonitorCheck]:
return await async_monitor.list_monitor_checks(
self.async_http_client,
monitor_id,
limit=limit,
offset=offset,
)
async def get_monitor_check(
self,
monitor_id: str,
check_id: str,
*,
limit: Optional[int] = None,
skip: Optional[int] = None,
status: Optional[Literal["same", "new", "changed", "removed", "error"]] = None,
pagination_config: Optional[PaginationConfig] = None,
) -> MonitorCheckDetail:
return await async_monitor.get_monitor_check(
self.async_http_client,
monitor_id,
check_id,
limit=limit,
skip=skip,
status=status,
pagination_config=pagination_config,
)
async def start_batch_scrape(self, urls: List[str], **kwargs) -> Any:
return await async_batch.start_batch_scrape(self.async_http_client, urls, **kwargs)
async def wait_batch_scrape(self, job_id: str, poll_interval: int = 2, timeout: Optional[int] = None) -> Any:
start = asyncio.get_event_loop().time()
while True:
status = await async_batch.get_batch_scrape_status(self.async_http_client, job_id)
if status.status in ["completed", "failed", "cancelled"]:
return status
if timeout and (asyncio.get_event_loop().time() - start) > timeout:
raise TimeoutError("Batch wait timed out")
await asyncio.sleep(poll_interval)
async def batch_scrape(self, urls: List[str], **kwargs) -> Any:
# waiter wrapper
start = await self.start_batch_scrape(urls, **{k: v for k, v in kwargs.items() if k not in ("poll_interval", "timeout")})
job_id = start.id
poll_interval = kwargs.get("poll_interval", 2)
timeout = kwargs.get("timeout")
return await self.wait_batch_scrape(job_id, poll_interval=poll_interval, timeout=timeout)
async def get_batch_scrape_status(
self,
job_id: str,
pagination_config: Optional[PaginationConfig] = None
):
return await async_batch.get_batch_scrape_status(
self.async_http_client,
job_id,
pagination_config=pagination_config
)
async def get_batch_scrape_status_page(
self,
next_url: str,
*,
request_timeout: Optional[float] = None,
):
return await async_batch.get_batch_scrape_status_page(
self.async_http_client,
next_url,
request_timeout=request_timeout,
)
async def cancel_batch_scrape(self, job_id: str) -> bool:
return await async_batch.cancel_batch_scrape(self.async_http_client, job_id)
async def get_batch_scrape_errors(self, job_id: str) -> CrawlErrorsResponse:
# Returns v2 errors structure; typed as CrawlErrorsResponse for parity
return await async_batch.get_batch_scrape_errors(self.async_http_client, job_id) # type: ignore[return-value]
# Extract (proxy to v1 async) — deprecated
async def extract(
self,
urls: Optional[List[str]] = None,
*,
prompt: Optional[str] = None,
schema: Optional[Dict[str, Any]] = None,
system_prompt: Optional[str] = None,
allow_external_links: Optional[bool] = None,
enable_web_search: Optional[bool] = None,
show_sources: Optional[bool] = None,
scrape_options: Optional['ScrapeOptions'] = None,
ignore_invalid_urls: Optional[bool] = None,
poll_interval: int = 2,
timeout: Optional[int] = None,
integration: Optional[str] = None,
):
"""Extract structured data and wait until completion (async).
.. deprecated::
The extract endpoint is in maintenance mode and its use is discouraged.
Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor
to find a replacement.
"""
return await async_extract.extract(
self.async_http_client,
urls,
prompt=prompt,
schema=schema,
system_prompt=system_prompt,
allow_external_links=allow_external_links,
enable_web_search=enable_web_search,
show_sources=show_sources,
scrape_options=scrape_options,
ignore_invalid_urls=ignore_invalid_urls,
poll_interval=poll_interval,
timeout=timeout,
integration=integration,
)
async def get_extract_status(self, job_id: str):
"""Get the current status (and data if completed) of an extract job (async).
.. deprecated::
The extract endpoint is in maintenance mode and its use is discouraged.
Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor
to find a replacement.
"""
return await async_extract.get_extract_status(self.async_http_client, job_id)
async def start_extract(
self,
urls: Optional[List[str]] = None,
*,
prompt: Optional[str] = None,
schema: Optional[Dict[str, Any]] = None,
system_prompt: Optional[str] = None,
allow_external_links: Optional[bool] = None,
enable_web_search: Optional[bool] = None,
show_sources: Optional[bool] = None,
scrape_options: Optional['ScrapeOptions'] = None,
ignore_invalid_urls: Optional[bool] = None,
integration: Optional[str] = None,
):
"""Start an extract job (non-blocking, async).
.. deprecated::
The extract endpoint is in maintenance mode and its use is discouraged.
Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor
to find a replacement.
"""
return await async_extract.start_extract(
self.async_http_client,
urls,
prompt=prompt,
schema=schema,
system_prompt=system_prompt,
allow_external_links=allow_external_links,
enable_web_search=enable_web_search,
show_sources=show_sources,
scrape_options=scrape_options,
ignore_invalid_urls=ignore_invalid_urls,
integration=integration,
)
# Agent
async def agent(
self,
urls: Optional[List[str]] = None,
*,
prompt: str,
schema: Optional[Any] = None,
integration: Optional[str] = None,
poll_interval: int = 2,
timeout: Optional[int] = None,
max_credits: Optional[int] = None,
strict_constrain_to_urls: Optional[bool] = None,
model: Optional[Literal["spark-1-pro", "spark-1-mini"]] = None,
webhook: Optional[Union[str, AgentWebhookConfig]] = None,
):
return await async_agent.agent(
self.async_http_client,
urls,
prompt=prompt,
schema=schema,
integration=integration,
poll_interval=poll_interval,
timeout=timeout,
max_credits=max_credits,
strict_constrain_to_urls=strict_constrain_to_urls,
model=model,
webhook=webhook,
)
async def get_agent_status(self, job_id: str):
return await async_agent.get_agent_status(self.async_http_client, job_id)
async def start_agent(
self,
urls: Optional[List[str]] = None,
*,
prompt: str,
schema: Optional[Any] = None,
integration: Optional[str] = None,
max_credits: Optional[int] = None,
strict_constrain_to_urls: Optional[bool] = None,
model: Optional[Literal["spark-1-pro", "spark-1-mini"]] = None,
webhook: Optional[Union[str, AgentWebhookConfig]] = None,
):
return await async_agent.start_agent(
self.async_http_client,
urls,
prompt=prompt,
schema=schema,
integration=integration,
max_credits=max_credits,
strict_constrain_to_urls=strict_constrain_to_urls,
model=model,
webhook=webhook,
)
async def cancel_agent(self, job_id: str) -> bool:
"""Cancel a running agent job.
Args:
job_id: Agent job ID
Returns:
True if the agent was cancelled
"""
return await async_agent.cancel_agent(self.async_http_client, job_id)
# Browser
async def browser(
self,
*,
ttl: Optional[int] = None,
activity_ttl: Optional[int] = None,
stream_web_view: Optional[bool] = None,
profile: Optional[Dict[str, Any]] = None,
):
"""Create a new browser session.
Args:
ttl: Total time-to-live in seconds (30-3600, default 300)
activity_ttl: Inactivity TTL in seconds (10-3600)
stream_web_view: Whether to enable webview streaming
profile: Profile config with ``name`` (str) and
optional ``save_changes`` (bool, default ``True``)
Returns:
BrowserCreateResponse with session id and CDP URL
"""
return await async_browser.browser(
self.async_http_client,
ttl=ttl,
activity_ttl=activity_ttl,
stream_web_view=stream_web_view,
profile=profile,
)
async def browser_execute(
self,
session_id: str,
code: str,
*,
language: Literal["python", "node", "bash"] = "bash",
timeout: Optional[int] = None,
):
"""Execute code in a browser session.
Args:
session_id: Browser session ID
code: Code to execute
language: Programming language ("python", "node", or "bash")
timeout: Execution timeout in seconds (1-300, default 30)
Returns:
BrowserExecuteResponse with execution result
"""
return await async_browser.browser_execute(
self.async_http_client,
session_id,
code,
language=language,
timeout=timeout,
)
async def delete_browser(self, session_id: str):
"""Delete a browser session.
Args:
session_id: Browser session ID
Returns:
BrowserDeleteResponse
"""
return await async_browser.delete_browser(
self.async_http_client, session_id
)
async def list_browsers(
self,
*,
status: Optional[Literal["active", "destroyed"]] = None,
):
"""List browser sessions.
Args:
status: Filter by session status ("active" or "destroyed")
Returns:
BrowserListResponse with list of sessions
"""
return await async_browser.list_browsers(
self.async_http_client,
status=status,
)
# Usage endpoints
async def get_concurrency(self):
from .methods.aio import usage as async_usage # type: ignore[attr-defined]
return await async_usage.get_concurrency(self.async_http_client)
async def get_credit_usage(self):
from .methods.aio import usage as async_usage # type: ignore[attr-defined]
return await async_usage.get_credit_usage(self.async_http_client)
async def get_token_usage(self):
from .methods.aio import usage as async_usage # type: ignore[attr-defined]
return await async_usage.get_token_usage(self.async_http_client)
async def get_credit_usage_historical(self, by_api_key: bool = False):
from .methods.aio import usage as async_usage # type: ignore[attr-defined]
return await async_usage.get_credit_usage_historical(self.async_http_client, by_api_key)
async def get_token_usage_historical(self, by_api_key: bool = False):
from .methods.aio import usage as async_usage # type: ignore[attr-defined]
return await async_usage.get_token_usage_historical(self.async_http_client, by_api_key)
async def get_queue_status(self):
from .methods.aio import usage as async_usage # type: ignore[attr-defined]
return await async_usage.get_queue_status(self.async_http_client)
# Watcher (sync object usable from async contexts)
def watcher(
self,
job_id: str,
*,
kind: Literal["crawl", "batch"] = "crawl",
poll_interval: int = 2,
timeout: Optional[int] = None,
) -> AsyncWatcher:
return AsyncWatcher(self, job_id, kind=kind, poll_interval=poll_interval, timeout=timeout)
|