(python/js/ts-sdks): readmes, e2e tests w idmux etc all good

rafaelmmiller committed 1 year ago

Commit 537f6c41 parent f4d904631 files · +788 −226Browse files

Showing the changes to apps/python-sdk (14 of 31 files). Show all

Unified · Split

14 files

apps/python-sdk/.env.example +4 −1
apps/python-sdk/README.md +44 −28
apps/python-sdk/firecrawl/__tests__/e2e/v2/.env.example +5 −2
apps/python-sdk/firecrawl/__tests__/e2e/v2/aio/test_aio_map.py +0 −2
apps/python-sdk/firecrawl/__tests__/e2e/v2/conftest.py +73 −0
apps/python-sdk/firecrawl/__tests__/e2e/v2/test_map.py +1 −4
apps/python-sdk/firecrawl/__tests__/e2e/v2/test_search.py +0 −6
apps/python-sdk/firecrawl/__tests__/e2e/v2/test_usage.py +1 −6
apps/python-sdk/firecrawl/__tests__/e2e/v2/test_watcher.py +1 −0
apps/python-sdk/firecrawl/client.py +39 −17
apps/python-sdk/firecrawl/firecrawl.backup.py +0 −0
apps/python-sdk/firecrawl/v2/client.py +128 −14
apps/python-sdk/firecrawl/v2/methods/aio/crawl.py +1 −2
apps/python-sdk/firecrawl/v2/methods/aio/usage.py +2 −2

apps/python-sdk/.env.example+4−1

@@ -1,2 +1,5 @@
1	1	FIRECRAWL_API_KEY=<your api key>
2		−FIRECRAWL_API_URL=https://api.firecrawl.dev
	2	+FIRECRAWL_API_URL=https://api.firecrawl.dev
	3	+
	4	+# TESTING PURPOSE:
	5	+IDMUX_URL=

apps/python-sdk/README.md+44−28

@@ -13,24 +13,25 @@ pip install firecrawl-py · 12 unmodified lines
13	13	## Usage
14	14
15	15	1. Get an API key from [firecrawl.dev](https://firecrawl.dev)
16		−2. Set the API key as an environment variable named `FIRECRAWL_API_KEY` or pass it as a parameter to the `FirecrawlApp` class.
	16	+2. Set the API key as an environment variable named `FIRECRAWL_API_KEY` or pass it as a parameter to the `Firecrawl` class.
17	17
18	18	Here's an example of how to use the SDK:
19	19
20	20	```python
21		−from firecrawl import FirecrawlApp, ScrapeOptions
	21	+from firecrawl import Firecrawl
	22	+from firecrawl.types import ScrapeOptions
22	23
23		−app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
	24	+firecrawl = Firecrawl(api_key="fc-YOUR_API_KEY")
24	25
25		−# Scrape a website:
26		−data = app.scrape_url(
	26	+# Scrape a website (v2):
	27	+data = firecrawl.scrape(
27	28	'https://firecrawl.dev',
28	29	formats=['markdown', 'html']
29	30	)
30	31	print(data)
31	32
32		−# Crawl a website:
33		−crawl_status = app.crawl_url(
	33	+# Crawl a website (v2 waiter):
	34	+crawl_status = firecrawl.crawl(
34	35	'https://firecrawl.dev',
35	36	limit=100,
36	37	scrape_options=ScrapeOptions(formats=['markdown', 'html'])
@@ -40,20 +41,20 @@ print(crawl_status) · 3 unmodified lines
40	41
41	42	### Scraping a URL
42	43
43		−To scrape a single URL, use the `scrape_url` method. It takes the URL as a parameter and returns the scraped data as a dictionary.
	44	+To scrape a single URL, use the `scrape` method. It takes the URL as a parameter and returns a document with the requested formats.
44	45
45	46	```python
46		−# Scrape a website:
47		−scrape_result = app.scrape_url('firecrawl.dev', formats=['markdown', 'html'])
	47	+# Scrape a website (v2):
	48	+scrape_result = firecrawl.scrape('https://firecrawl.dev', formats=['markdown', 'html'])
48	49	print(scrape_result)
49	50	```
50	51
51	52	### Crawling a Website
52	53
53		−To crawl a website, use the `crawl_url` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
	54	+To crawl a website, use the `crawl` method. It takes the starting URL and optional parameters as arguments. You can control depth, limits, formats, and more.
54	55
55	56	```python
56		−crawl_status = app.crawl_url(
	57	+crawl_status = firecrawl.crawl(
57	58	'https://firecrawl.dev',
58	59	limit=100,
59	60	scrape_options=ScrapeOptions(formats=['markdown', 'html']),
@@ -66,23 +67,23 @@ print(crawl_status) · 6 unmodified lines
66	67
67	68	<Tip>Looking for async operations? Check out the [Async Class](#async-class) section below.</Tip>
68	69
69		−To crawl a website asynchronously, use the `crawl_url_async` method. It returns the crawl `ID` which you can use to check the status of the crawl job. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
	70	+To enqueue a crawl asynchronously, use `start_crawl`. It returns the crawl `ID` which you can use to check the status of the crawl job.
70	71
71	72	```python
72		−crawl_status = app.async_crawl_url(
	73	+crawl_job = firecrawl.start_crawl(
73	74	'https://firecrawl.dev',
74	75	limit=100,
75	76	scrape_options=ScrapeOptions(formats=['markdown', 'html']),
76	77	)
77		−print(crawl_status)
	78	+print(crawl_job)
78	79	```
79	80
80	81	### Checking Crawl Status
81	82
82		−To check the status of a crawl job, use the `check_crawl_status` method. It takes the job ID as a parameter and returns the current status of the crawl job.
	83	+To check the status of a crawl job, use the `get_crawl_status` method. It takes the job ID as a parameter and returns the current status of the crawl job.
83	84
84	85	```python
85		−crawl_status = app.check_crawl_status("<crawl_id>")
	86	+crawl_status = firecrawl.get_crawl_status("<crawl_id>")
86	87	print(crawl_status)
87	88	```
88	89
@@ -91,17 +92,17 @@ print(crawl_status) · 2 unmodified lines
91	92	To cancel an asynchronous crawl job, use the `cancel_crawl` method. It takes the job ID of the asynchronous crawl as a parameter and returns the cancellation status.
92	93
93	94	```python
94		−cancel_crawl = app.cancel_crawl(id)
	95	+cancel_crawl = firecrawl.cancel_crawl(id)
95	96	print(cancel_crawl)
96	97	```
97	98
98	99	### Map a Website
99	100
100		−Use `map_url` to generate a list of URLs from a website. The `params` argument let you customize the mapping process, including options to exclude subdomains or to utilize the sitemap.
	101	+Use `map` to generate a list of URLs from a website. Options let you customize the mapping process, including whether to use the sitemap or include subdomains.
101	102
102	103	```python
103		−# Map a website:
104		−map_result = app.map_url('https://firecrawl.dev')
	104	+# Map a website (v2):
	105	+map_result = firecrawl.map('https://firecrawl.dev')
105	106	print(map_result)
106	107	```
107	108
@@ -152,20 +153,35 @@ The SDK handles errors returned by the Firecrawl API and raises appropriate exce · 44 unmodified lines
152	153
153	154	## Async Class
154	155
155		−For async operations, you can use the `AsyncFirecrawlApp` class. Its methods are the same as the `FirecrawlApp` class, but they don't block the main thread.
	156	+For async operations, you can use the `AsyncFirecrawl` class. Its methods mirror the `Firecrawl` class, but you `await` them.
156	157
157	158	```python
158		−from firecrawl import AsyncFirecrawlApp
	159	+from firecrawl import AsyncFirecrawl
159	160
160		−app = AsyncFirecrawlApp(api_key="YOUR_API_KEY")
	161	+firecrawl = AsyncFirecrawl(api_key="YOUR_API_KEY")
161	162
162		−# Async Scrape
	163	+# Async Scrape (v2)
163	164	async def example_scrape():
164		− scrape_result = await app.scrape_url(url="https://example.com")
	165	+ scrape_result = await firecrawl.scrape(url="https://example.com")
165	166	print(scrape_result)
166	167
167		−# Async Crawl
	168	+# Async Crawl (v2)
168	169	async def example_crawl():
169		− crawl_result = await app.crawl_url(url="https://example.com")
	170	+ crawl_result = await firecrawl.crawl(url="https://example.com")
170	171	print(crawl_result)
	172	+```
	173	+
	174	+## v1 compatibility
	175	+
	176	+For legacy code paths, v1 remains available under `firecrawl.v1` with the original method names.
	177	+
	178	+```python
	179	+from firecrawl import Firecrawl
	180	+
	181	+firecrawl = Firecrawl(api_key="YOUR_API_KEY")
	182	+
	183	+# v1 methods (feature‑frozen)
	184	+doc_v1 = firecrawl.v1.scrape_url('https://firecrawl.dev', formats=['markdown', 'html'])
	185	+crawl_v1 = firecrawl.v1.crawl_url('https://firecrawl.dev', limit=100)
	186	+map_v1 = firecrawl.v1.map_url('https://firecrawl.dev')
171	187	```

apps/python-sdk/firecrawl/__tests__/e2e/v2/.env.example+5−2

@@ -1,2 +1,5 @@
1		−API_URL=http://localhost:3002
2		−API_KEY=fc-YOUR_API_KEY
	1	+FIRECRAWL_API_KEY=<your api key>
	2	+FIRECRAWL_API_URL=https://api.firecrawl.dev
	3	+
	4	+# TESTING PURPOSE:
	5	+IDMUX_URL=

apps/python-sdk/firecrawl/__tests__/e2e/v2/aio/test_aio_map.py+0−2

@@ -17,7 +17,6 @@ if not os.getenv("API_URL"): · 16 unmodified lines
17	17	async def test_async_map_minimal():
18	18	client = AsyncFirecrawl(api_key=os.getenv("API_KEY"), api_url=os.getenv("API_URL"))
19	19	resp = await client.v2.map("https://docs.firecrawl.dev")
20		− assert resp.success is True
21	20	assert hasattr(resp, "links") and isinstance(resp.links, list)
22	21	if resp.links:
23	22	first = resp.links[0]
@@ -36,7 +35,6 @@ async def test_async_map_with_all_params(sitemap): · 12 unmodified lines
36	35	sitemap=sitemap,
37	36	timeout=15000,
38	37	)
39		− assert resp.success is True
40	38	assert hasattr(resp, "links") and isinstance(resp.links, list)
41	39	assert len(resp.links) <= 10
42	40

apps/python-sdk/firecrawl/__tests__/e2e/v2/conftest.py+73−0

@@ -0,0 +1,73 @@
	1	+import os
	2	+import json
	3	+import pytest
	4	+import requests
	5	+from dotenv import load_dotenv
	6	+
	7	+load_dotenv()
	8	+
	9	+def _idmux(identity_request: dict) -> dict:
	10	+ idmux_url = os.getenv("IDMUX_URL")
	11	+ if not idmux_url:
	12	+ raise EnvironmentError("IDMUX_URL is not set. E2E tests must use idmux for credentials.")
	13	+ run_number = int(os.getenv("GITHUB_RUN_NUMBER") or 0)
	14	+ payload = {
	15	+ "refName": os.getenv("GITHUB_REF_NAME") or "local",
	16	+ "runNumber": run_number,
	17	+ "concurrency": identity_request.get("concurrency", 100),
	18	+ **identity_request,
	19	+ }
	20	+ resp = requests.post(idmux_url + "/", json=payload)
	21	+ resp.raise_for_status()
	22	+ return resp.json()
	23	+
	24	+@pytest.fixture(scope="session")
	25	+def api_url():
	26	+ # Prefer TEST_URL, then FIRECRAWL_API_URL (for parity with JS), then legacy API_URL
	27	+ return (
	28	+ os.getenv("TEST_URL")
	29	+ or os.getenv("FIRECRAWL_API_URL")
	30	+ or os.getenv("API_URL")
	31	+ or "https://api.firecrawl.dev"
	32	+ )
	33	+
	34	+# Resolve identity and export environment at import time so tests that read env at module import succeed
	35	+_IDENTITY = None
	36	+_API_URL = (
	37	+ os.getenv("TEST_URL")
	38	+ or os.getenv("FIRECRAWL_API_URL")
	39	+ or os.getenv("API_URL")
	40	+ or "https://api.firecrawl.dev"
	41	+)
	42	+
	43	+_IDMUX_URL = os.getenv("IDMUX_URL")
	44	+if _IDMUX_URL:
	45	+ run_name = os.getenv("PYTEST_RUN_NAME") or "py-e2e"
	46	+ # If IDMUX_URL is set, idmux MUST succeed; do not silently fall back
	47	+ _IDENTITY = _idmux({"name": run_name})
	48	+ os.environ["API_KEY"] = _IDENTITY.get("apiKey", "")
	49	+ os.environ["API_URL"] = _API_URL
	50	+
	51	+@pytest.fixture(scope="session")
	52	+def api_identity():
	53	+ return _IDENTITY or {"apiKey": os.getenv("API_KEY") or "", "teamId": os.getenv("TEST_TEAM_ID") or os.getenv("TEAM_ID") or ""}
	54	+
	55	+@pytest.fixture(autouse=True)
	56	+def _inject_client(request, api_identity, api_url):
	57	+ # For class-based tests that rely on self.client, inject a client if missing
	58	+ inst = getattr(request, "instance", None)
	59	+ if inst is not None and not hasattr(inst, "client"):
	60	+ try:
	61	+ from firecrawl import Firecrawl
	62	+ inst.client = Firecrawl(api_key=api_identity.get("apiKey", ""), api_url=api_url)
	63	+ except Exception:
	64	+ pass
	65	+ # For function-based modules that expect a module-level `firecrawl` symbol
	66	+ mod = getattr(request, "module", None)
	67	+ if mod is not None and not hasattr(mod, "firecrawl"):
	68	+ try:
	69	+ from firecrawl import Firecrawl
	70	+ setattr(mod, "firecrawl", Firecrawl(api_key=api_identity.get("apiKey", ""), api_url=api_url))
	71	+ except Exception:
	72	+ pass
	73	+

apps/python-sdk/firecrawl/__tests__/e2e/v2/test_map.py+1−4

@@ -24,7 +24,6 @@ class TestMapE2E: · 23 unmodified lines
24	24	def test_map_minimal_request(self):
25	25	resp = self.client.map("https://docs.firecrawl.dev")
26	26
27		− assert hasattr(resp, "success") and resp.success is True
28	27	assert hasattr(resp, "links") and resp.links is not None
29	28	assert isinstance(resp.links, list)
30	29
@@ -46,13 +45,11 @@ class TestMapE2E: · 15 unmodified lines
46	45	resp = self.client.map(
47	46	"https://docs.firecrawl.dev",
48	47	search="docs",
49		− include_subdomains=True,
50		− limit=10,
	48	+ include_subdomains=True, limit=10,
51	49	sitemap=sitemap,
52	50	timeout=15000,
53	51	)
54	52
55		− assert hasattr(resp, "success") and resp.success is True
56	53	assert hasattr(resp, "links") and isinstance(resp.links, list)
57	54
58	55	# Limit should be respected (server-side)

apps/python-sdk/firecrawl/__tests__/e2e/v2/test_search.py+0−6

@@ -5,12 +5,6 @@ from firecrawl.types import SearchData, SearchResult, Document, ScrapeFormats, S · 4 unmodified lines
5	5
6	6	load_dotenv()
7	7
8		−if not os.getenv("API_KEY"):
9		− raise ValueError("API_KEY is not set")
10		−
11		−if not os.getenv("API_URL"):
12		− raise ValueError("API_URL is not set")
13		−
14	8	firecrawl = Firecrawl(api_key=os.getenv("API_KEY"), api_url=os.getenv("API_URL"))
15	9
16	10	def _collect_texts(entries):

apps/python-sdk/firecrawl/__tests__/e2e/v2/test_usage.py+1−6

@@ -4,15 +4,10 @@ from firecrawl import Firecrawl · 3 unmodified lines
4	4
5	5	load_dotenv()
6	6
7		−if not os.getenv("API_KEY"):
8		− raise ValueError("API_KEY is not set")
9		−
10		−if not os.getenv("API_URL"):
11		− raise ValueError("API_URL is not set")
12		−
13	7
14	8	class TestUsageE2E:
15	9	def setup_method(self):
	10	+ # Environment is exported by conftest at import time
16	11	self.client = Firecrawl(api_key=os.getenv("API_KEY"), api_url=os.getenv("API_URL"))
17	12
18	13	def test_get_concurrency(self):

apps/python-sdk/firecrawl/__tests__/e2e/v2/test_watcher.py+1−0

@@ -14,6 +14,7 @@ if not os.getenv("API_URL"): · 13 unmodified lines
14	14
15	15	class TestWatcherE2E:
16	16	def setup_method(self):
	17	+ from firecrawl import Firecrawl
17	18	self.client = Firecrawl(api_key=os.getenv("API_KEY"), api_url=os.getenv("API_URL"))
18	19
19	20	def test_crawl_watcher(self):

apps/python-sdk/firecrawl/client.py+39−17

@@ -113,20 +113,18 @@ class AsyncV2Proxy: · 112 unmodified lines
113	113
114	114	class Firecrawl:
115	115	"""
116		− Unified Firecrawl client with version-specific access patterns.
117		−
118		− This class provides a unified interface that allows users to access
119		− different API versions through version-specific attributes (v1, v2)
120		− while defaulting to v2 for direct method calls.
	116	+ Unified Firecrawl client (v2 by default, v1 under ``.v1``).
	117	+
	118	+ Provides a single entrypoint that exposes the latest API directly while
	119	+ keeping a feature-frozen v1 available for incremental migration.
121	120	"""
122	121
123	122	def __init__(self, api_key: str = None, api_url: str = "https://api.firecrawl.dev"):
124		− """
125		− Initialize the unified Firecrawl client.
126		−
	123	+ """Initialize the unified client.
	124	+
127	125	Args:
128		− api_key: Your Firecrawl API key
129		− api_url: The Firecrawl API URL (defaults to production)
	126	+ api_key: Firecrawl API key (or set ``FIRECRAWL_API_KEY``)
	127	+ api_url: Base API URL (defaults to production)
130	128	"""
131	129	self.api_key = api_key
132	130	self.api_url = api_url
@@ -164,13 +162,7 @@ class Firecrawl: · 31 unmodified lines
164	162	self.watcher = self._v2_client.watcher
165	163
166	164	class AsyncFirecrawl:
167		− """
168		− Unified Firecrawl client with version-specific access patterns.
169		−
170		− This class provides a unified interface that allows users to access
171		− different API versions through version-specific attributes (v1, v2)
172		− while defaulting to v2 for direct method calls.
173		− """
	165	+ """Async unified Firecrawl client (v2 by default, v1 under ``.v1``)."""
174	166
175	167	def __init__(self, api_key: str = None, api_url: str = "https://api.firecrawl.dev"):
176	168	self.api_key = api_key
@@ -185,6 +177,36 @@ class AsyncFirecrawl: · 8 unmodified lines
185	177	self.v1 = AsyncV1Proxy(self._v1_client) if self._v1_client else None
186	178	self.v2 = AsyncV2Proxy(self._v2_client)
187	179
	180	+ # Expose v2 async surface directly on the top-level client for ergonomic access
	181	+ # Keep method names aligned with the sync client
	182	+ self.scrape = self._v2_client.scrape
	183	+ self.search = self._v2_client.search
	184	+ self.map = self._v2_client.map
	185	+
	186	+ self.start_crawl = self._v2_client.start_crawl
	187	+ self.get_crawl_status = self._v2_client.get_crawl_status
	188	+ self.cancel_crawl = self._v2_client.cancel_crawl
	189	+ self.crawl = self._v2_client.crawl
	190	+ self.get_crawl_errors = self._v2_client.get_crawl_errors
	191	+ self.active_crawls = self._v2_client.active_crawls
	192	+ self.crawl_params_preview = self._v2_client.crawl_params_preview
	193	+
	194	+ self.start_batch_scrape = self._v2_client.start_batch_scrape
	195	+ self.get_batch_scrape_status = self._v2_client.get_batch_scrape_status
	196	+ self.cancel_batch_scrape = self._v2_client.cancel_batch_scrape
	197	+ self.batch_scrape = self._v2_client.batch_scrape
	198	+ self.get_batch_scrape_errors = self._v2_client.get_batch_scrape_errors
	199	+
	200	+ self.start_extract = self._v2_client.start_extract
	201	+ self.get_extract_status = self._v2_client.get_extract_status
	202	+ self.extract = self._v2_client.extract
	203	+
	204	+ self.get_concurrency = self._v2_client.get_concurrency
	205	+ self.get_credit_usage = self._v2_client.get_credit_usage
	206	+ self.get_token_usage = self._v2_client.get_token_usage
	207	+
	208	+ self.watcher = self._v2_client.watcher
	209	+
188	210	# Export Firecrawl as an alias for FirecrawlApp
189	211	FirecrawlApp = Firecrawl
190	212	AsyncFirecrawlApp = AsyncFirecrawl

apps/python-sdk/firecrawl/firecrawl.backup.pyrenamed from apps/python-sdk/firecrawl/DELETE_firecrawl.py+0−0

File renamed without changes.

apps/python-sdk/firecrawl/v2/client.py+128−14

@@ -408,8 +408,18 @@ class FirecrawlClient: · 407 unmodified lines
408	408	sitemap: Optional[Literal["only", "include", "skip"]] = None,
409	409	timeout: Optional[int] = None,
410	410	) -> MapData:
411		− """
412		− Map a URL and return discovered links (with optional titles/descriptions).
	411	+ """Map a URL and return discovered links.
	412	+
	413	+ Args:
	414	+ url: Root URL to explore
	415	+ search: Optional substring filter for discovered links
	416	+ include_subdomains: Whether to include subdomains
	417	+ limit: Maximum number of links to return
	418	+ sitemap: Sitemap usage mode ("only" \| "include" \| "skip")
	419	+ timeout: Request timeout in milliseconds
	420	+
	421	+ Returns:
	422	+ MapData containing the discovered links
413	423	"""
414	424	options = MapOptions(
415	425	search=search,
@@ -434,8 +444,14 @@ class FirecrawlClient: · 18 unmodified lines
434	444	return crawl_module.cancel_crawl(self.http_client, crawl_id)
435	445
436	446	def crawl_params_preview(self, url: str, prompt: str) -> CrawlParamsData:
437		− """
438		− Get crawl parameters from LLM based on URL and prompt.
	447	+ """Derive crawl parameters from natural-language prompt.
	448	+
	449	+ Args:
	450	+ url: Root URL
	451	+ prompt: Instruction describing how to crawl
	452	+
	453	+ Returns:
	454	+ CrawlParamsData with normalized crawl configuration
439	455	"""
440	456	request = CrawlParamsRequest(url=url, prompt=prompt)
441	457	return crawl_module.crawl_params_preview(self.http_client, request)
@@ -453,8 +469,21 @@ class FirecrawlClient: · 11 unmodified lines
453	469	scrape_options: Optional['ScrapeOptions'] = None,
454	470	ignore_invalid_urls: Optional[bool] = None,
455	471	):
456		− """
457		− Start an extract job (non-blocking). Use get_extract_status to poll.
	472	+ """Start an extract job (non-blocking).
	473	+
	474	+ Args:
	475	+ urls: URLs to extract from (optional)
	476	+ prompt: Natural-language instruction for extraction
	477	+ schema: Target JSON schema for the output
	478	+ system_prompt: Optional system instruction
	479	+ allow_external_links: Allow hyperlinks in output
	480	+ enable_web_search: Whether to augment with web search
	481	+ show_sources: Include per-field/source mapping when available
	482	+ scrape_options: Scrape options applied prior to extraction
	483	+ ignore_invalid_urls: Skip invalid URLs instead of failing
	484	+
	485	+ Returns:
	486	+ Response payload with job id/status (poll with get_extract_status)
458	487	"""
459	488	return extract_module.start_extract(
460	489	self.http_client,
@@ -484,8 +513,23 @@ class FirecrawlClient: · 23 unmodified lines
484	513	poll_interval: int = 2,
485	514	timeout: Optional[int] = None,
486	515	):
487		− """
488		− Extract structured data using the v2 client surface, waiting until completion.
	516	+ """Extract structured data and wait until completion.
	517	+
	518	+ Args:
	519	+ urls: URLs to extract from (optional)
	520	+ prompt: Natural-language instruction for extraction
	521	+ schema: Target JSON schema for the output
	522	+ system_prompt: Optional system instruction
	523	+ allow_external_links: Allow hyperlinks in output
	524	+ enable_web_search: Whether to augment with web search
	525	+ show_sources: Include per-field/source mapping when available
	526	+ scrape_options: Scrape options applied prior to extraction
	527	+ ignore_invalid_urls: Skip invalid URLs instead of failing
	528	+ poll_interval: Seconds between status checks
	529	+ timeout: Maximum seconds to wait (None for no timeout)
	530	+
	531	+ Returns:
	532	+ Final extract response when completed
489	533	"""
490	534	return extract_module.extract(
491	535	self.http_client,
@@ -533,8 +577,39 @@ class FirecrawlClient: · 41 unmodified lines
533	577	integration: Optional[str] = None,
534	578	idempotency_key: Optional[str] = None,
535	579	):
536		− """
537		− Start a batch scrape job over multiple URLs.
	580	+ """Start a batch scrape job over multiple URLs (non-blocking).
	581	+
	582	+ Args:
	583	+ urls: List of URLs to scrape
	584	+ formats: Output formats to collect per URL
	585	+ headers: HTTP headers
	586	+ include_tags: HTML tags to include
	587	+ exclude_tags: HTML tags to exclude
	588	+ only_main_content: Restrict scraping to main content
	589	+ timeout: Per-request timeout in milliseconds
	590	+ wait_for: Wait condition in milliseconds
	591	+ mobile: Emulate mobile viewport
	592	+ parsers: Parser list (e.g., ["pdf"])
	593	+ actions: Browser actions to perform
	594	+ location: Location settings
	595	+ skip_tls_verification: Skip TLS verification
	596	+ remove_base64_images: Remove base64 images from output
	597	+ fast_mode: Prefer faster scraping modes
	598	+ use_mock: Use a mock data source (internal/testing)
	599	+ block_ads: Block ads during scraping
	600	+ proxy: Proxy setting
	601	+ max_age: Cache max age
	602	+ store_in_cache: Whether to store results in cache
	603	+ webhook: Webhook configuration
	604	+ append_to_id: Append to an existing batch job
	605	+ ignore_invalid_urls: Skip invalid URLs without failing
	606	+ max_concurrency: Max concurrent scrapes
	607	+ zero_data_retention: Delete data after 24 hours
	608	+ integration: Integration tag/name
	609	+ idempotency_key: Header used to deduplicate starts
	610	+
	611	+ Returns:
	612	+ Response payload with job id (poll with get_batch_scrape_status)
538	613	"""
539	614	options = ScrapeOptions(
540	615	**{k: v for k, v in dict(
@@ -574,18 +649,47 @@ class FirecrawlClient: · 33 unmodified lines
574	649	)
575	650
576	651	def get_batch_scrape_status(self, job_id: str):
577		− """Get current status and any scraped data for a batch scrape job."""
	652	+ """Get current status and any scraped data for a batch job.
	653	+
	654	+ Args:
	655	+ job_id: Batch job ID
	656	+
	657	+ Returns:
	658	+ Status payload including counts and partial data
	659	+ """
578	660	return batch_module.get_batch_scrape_status(self.http_client, job_id)
579	661
580	662	def cancel_batch_scrape(self, job_id: str) -> bool:
581		− """Cancel a running batch scrape job."""
	663	+ """Cancel a running batch scrape job.
	664	+
	665	+ Args:
	666	+ job_id: Batch job ID
	667	+
	668	+ Returns:
	669	+ True if the job was cancelled
	670	+ """
582	671	return batch_module.cancel_batch_scrape(self.http_client, job_id)
583	672
584	673	def get_batch_scrape_errors(self, job_id: str):
585		− """Retrieve error details for a batch scrape job."""
	674	+ """Retrieve error details for a batch scrape job.
	675	+
	676	+ Args:
	677	+ job_id: Batch job ID
	678	+
	679	+ Returns:
	680	+ Errors and robots-blocked URLs for the job
	681	+ """
586	682	return batch_methods.get_batch_scrape_errors(self.http_client, job_id)
587	683
588	684	def get_extract_status(self, job_id: str):
	685	+ """Get the current status (and data if completed) of an extract job.
	686	+
	687	+ Args:
	688	+ job_id: Extract job ID
	689	+
	690	+ Returns:
	691	+ Extract response payload with status and optional data
	692	+ """
589	693	return extract_module.get_extract_status(self.http_client, job_id)
590	694
591	695	def get_concurrency(self):
@@ -608,7 +712,17 @@ class FirecrawlClient: · 16 unmodified lines
608	712	poll_interval: int = 2,
609	713	timeout: Optional[int] = None,
610	714	) -> Watcher:
611		− """Create a polling-based watcher for crawl or batch jobs."""
	715	+ """Create a watcher for crawl or batch jobs.
	716	+
	717	+ Args:
	718	+ job_id: Job ID to watch
	719	+ kind: Job kind ("crawl" or "batch")
	720	+ poll_interval: Seconds between status checks
	721	+ timeout: Maximum seconds to watch (None for no timeout)
	722	+
	723	+ Returns:
	724	+ Watcher instance
	725	+ """
612	726	return Watcher(self, job_id, kind=kind, poll_interval=poll_interval, timeout=timeout)
613	727
614	728	def batch_scrape(

apps/python-sdk/firecrawl/v2/methods/aio/crawl.py+1−2

@@ -160,8 +160,7 @@ async def get_active_crawls(client: AsyncHttpClient) -> ActiveCrawlsResponse: · 159 unmodified lines
160	160	body = response.json()
161	161	if not body.get("success"):
162	162	raise Exception(body.get("error", "Unknown error occurred"))
163		− data = body.get("data", {})
164		− crawls_in = data.get("crawls", [])
	163	+ crawls_in = body.get("crawls", [])
165	164	normalized = []
166	165	for c in crawls_in:
167	166	if isinstance(c, dict):

apps/python-sdk/firecrawl/v2/methods/aio/usage.py+2−2

@@ -18,7 +18,7 @@ async def get_concurrency(client: AsyncHttpClient) -> ConcurrencyCheck: · 17 unmodified lines
18	18
19	19
20	20	async def get_credit_usage(client: AsyncHttpClient) -> CreditUsage:
21		− resp = await client.get("/v2/team/credit-usage")
	21	+ resp = await client.get("/v2/credit-usage")
22	22	if resp.status_code >= 400:
23	23	handle_response_error(resp, "get credit usage")
24	24	body = resp.json()
@@ -29,7 +29,7 @@ async def get_credit_usage(client: AsyncHttpClient) -> CreditUsage: · 4 unmodified lines
29	29
30	30
31	31	async def get_token_usage(client: AsyncHttpClient) -> TokenUsage:
32		− resp = await client.get("/v2/team/token-usage")
	32	+ resp = await client.get("/v2/token-usage")
33	33	if resp.status_code >= 400:
34	34	handle_response_error(resp, "get token usage")
35	35	body = resp.json()