firecrawl 4.3.2__tar.gz → 4.3.3__tar.gz

{firecrawl-4.3.2 → firecrawl-4.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: firecrawl
-Version: 4.3.2
+Version: 4.3.3
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/firecrawl/firecrawl
 Author: Mendable.ai

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__init__.py

@@ -17,7 +17,7 @@ from .v1 import (
     V1ChangeTrackingOptions,
 )
 
-__version__ = "4.3.2"
+__version__ = "4.3.3"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/aio/test_aio_batch_scrape.py

@@ -63,6 +63,7 @@ async def test_async_batch_wait_with_all_params():
         zero_data_retention=False,
         poll_interval=1,
         timeout=180,
+        integration="_e2e-test",
     )
     assert job.status in ("completed", "failed")
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/aio/test_aio_crawl.py

@@ -53,6 +53,7 @@ async def test_async_crawl_with_all_params():
         allow_subdomains=True,
         delay=1,
         max_concurrency=2,
+        integration="_e2e-test",
         webhook="https://example.com/hook",
         scrape_options=ScrapeOptions(
             formats=[

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/aio/test_aio_extract.py

@@ -32,6 +32,7 @@ async def test_async_extract_with_schema_and_options():
         allow_external_links=False,
         enable_web_search=False,
         show_sources=False,
+        integration="_e2e-test",
         # agent={"model": "FIRE-1", "prompt": "Extract title"}, # Skipping agent test in CI
     )
     assert res is not None

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/aio/test_aio_map.py

@@ -34,6 +34,7 @@ async def test_async_map_with_all_params(sitemap):
         limit=10,
         sitemap=sitemap,
         timeout=15000,
+        integration="_e2e-test",
     )
     assert hasattr(resp, "links") and isinstance(resp.links, list)
     assert len(resp.links) <= 10

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/aio/test_aio_scrape.py

@@ -64,6 +64,7 @@ async def test_async_scrape_with_all_params():
         proxy="basic",
         max_age=0,
         store_in_cache=False,
+        integration="_e2e-test",
     )
     assert isinstance(doc, Document)
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/aio/test_aio_search.py

@@ -140,6 +140,7 @@ async def test_async_search_all_parameters():
         location="US",
         ignore_invalid_urls=True,
         timeout=60000,
+        integration="_e2e-test",
         scrape_options=ScrapeOptions(
             formats=[
                 "markdown",

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/test_batch_scrape.py

@@ -83,6 +83,7 @@ class TestBatchScrapeE2E:
             zero_data_retention=False,
             poll_interval=1,
             wait_timeout=180,
+            integration="_e2e-test",
         )
 
         assert job.status in ["completed", "failed"]

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/test_crawl.py

@@ -168,7 +168,8 @@ class TestCrawlE2E:
             limit=3,
             max_discovery_depth=2,
             poll_interval=1,
-            timeout=120
+            timeout=120,
+            integration="_e2e-test",
         )
         
         assert crawl_job.status in ["completed", "failed"]
@@ -257,7 +258,8 @@ class TestCrawlE2E:
             max_concurrency=2,
             webhook="https://example.com/hook",
             scrape_options=scrape_opts,
-            zero_data_retention=False
+            zero_data_retention=False,
+            integration="_e2e-test",
         )
         
         assert crawl_job.id is not None

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/test_extract.py

@@ -42,6 +42,7 @@ class TestExtractE2E:
             prompt="Extract the main page title",
             show_sources=True,
             enable_web_search=False,
+            integration="_e2e-test",
         )
 
         assert hasattr(resp, "success")

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/test_map.py

@@ -48,6 +48,7 @@ class TestMapE2E:
             include_subdomains=True,            limit=10,
             sitemap=sitemap,
             timeout=15000,
+            integration="_e2e-test",
         )
 
         assert hasattr(resp, "links") and isinstance(resp.links, list)

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/test_scrape.py

@@ -150,6 +150,7 @@ class TestScrapeE2E:
             proxy="basic",
             max_age=0,
             store_in_cache=False,
+            integration="_e2e-test",
         )
         assert isinstance(doc, Document)
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/e2e/v2/test_search.py

@@ -144,6 +144,7 @@ def test_search_all_parameters():
         location="US",
         ignore_invalid_urls=True,
         timeout=60000,
+        integration="_e2e-test",
         scrape_options=ScrapeOptions(
             formats=[
                 "markdown",

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/unit/v2/methods/aio/test_aio_crawl_request_preparation.py

@@ -59,3 +59,21 @@ class TestAsyncCrawlRequestPreparation:
         assert "metadata" not in webhook
         assert "events" not in webhook
 
+    def test_all_fields_including_integration(self):
+        req = CrawlRequest(
+            url="https://example.com",
+            include_paths=["/docs/*"],
+            exclude_paths=["/admin/*"],
+            max_discovery_depth=2,
+            sitemap="include",
+            ignore_query_parameters=True,
+            crawl_entire_domain=False,
+            allow_external_links=True,
+            allow_subdomains=True,
+            max_concurrency=3,
+            zero_data_retention=False,
+            integration="  _unit-test  ",
+        )
+        payload = _prepare_crawl_request(req)
+        assert payload["integration"] == "_unit-test"
+

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/unit/v2/methods/aio/test_aio_map_request_preparation.py

@@ -9,11 +9,12 @@ class TestAsyncMapRequestPreparation:
         assert payload["url"] == "https://example.com"
 
     def test_fields(self):
-        opts = MapOptions(search="docs", include_subdomains=True, limit=10, sitemap="only", timeout=15000)
+        opts = MapOptions(search="docs", include_subdomains=True, limit=10, sitemap="only", timeout=15000, integration="  _unit-test  ")
         payload = _prepare_map_request("https://example.com", opts)
         assert payload["search"] == "docs"
         assert payload["includeSubdomains"] is True
         assert payload["limit"] == 10
         assert payload["sitemap"] == "only"
         assert payload["timeout"] == 15000
+        assert payload["integration"] == "_unit-test"
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/unit/v2/methods/aio/test_aio_search_request_preparation.py

@@ -33,10 +33,12 @@ class TestAsyncSearchRequestPreparation:
             ignore_invalid_urls=False,
             timeout=30000,
             scrape_options=scrape_opts,
+            integration="  _unit-test  ",
         )
         data = _prepare_search_request(request)
         assert data["ignoreInvalidURLs"] is False
         assert "scrapeOptions" in data
+        assert data["integration"] == "_unit-test"
 
     def test_exclude_none_behavior(self):
         request = SearchRequest(
@@ -59,5 +61,4 @@ class TestAsyncSearchRequestPreparation:
         assert "scrapeOptions" in data
         scrape_data = data["scrapeOptions"]
         assert "onlyMainContent" in scrape_data
-        assert "mobile" in scrape_data
-
+        assert "mobile" in scrape_data

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/unit/v2/methods/test_batch_request_preparation.py

@@ -76,14 +76,14 @@ class TestBatchScrapeRequestPreparation:
             ignore_invalid_urls=True,
             max_concurrency=5,
             zero_data_retention=True,
-            integration="test",
+            integration="_unit-test",
         )
         assert isinstance(data["webhook"], dict) and data["webhook"]["url"] == "https://hook.test"
         assert data["appendToId"] == "00000000-0000-0000-0000-000000000000"
         assert data["ignoreInvalidURLs"] is True
         assert data["maxConcurrency"] == 5
         assert data["zeroDataRetention"] is True
-        assert data["integration"] == "test"
+        assert data["integration"] == "_unit-test"
 
     def test_string_webhook_is_passed_verbatim(self):
         data = prepare_batch_scrape_request(["https://example.com"], webhook="https://hook.simple")

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/unit/v2/methods/test_map_request_preparation.py

@@ -35,6 +35,7 @@ class TestMapRequestPreparation:
             limit=25,
             sitemap="only",
             timeout=15000,
+            integration="  _unit-test  ",
         )
         data = _prepare_map_request("https://example.com", opts)
 
@@ -44,10 +45,10 @@ class TestMapRequestPreparation:
         assert data["limit"] == 25
         assert data["sitemap"] == "only"
         assert data["timeout"] == 15000
+        assert data["integration"] == "_unit-test"
 
     def test_invalid_url(self):
         with pytest.raises(ValueError):
             _prepare_map_request("")
         with pytest.raises(ValueError):
-            _prepare_map_request("   ")
-
+            _prepare_map_request("   ")

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/unit/v2/methods/test_scrape_request_preparation.py

@@ -89,4 +89,21 @@ class TestScrapeRequestPreparation:
     def test_whitespace_url_validation(self):
         """Test validation with whitespace-only URL."""
         with pytest.raises(ValueError, match="URL cannot be empty"):
-            _prepare_scrape_request("   ") 
+            _prepare_scrape_request("   ")
+
+    def test_all_params_including_integration(self):
+        opts = ScrapeOptions(
+            formats=["markdown"],
+            headers={"User-Agent": "Test"},
+            include_tags=["h1"],
+            exclude_tags=["nav"],
+            only_main_content=False,
+            timeout=15000,
+            wait_for=2000,
+            mobile=True,
+            skip_tls_verification=True,
+            remove_base64_images=False,
+            integration="  _unit-test  ",
+        )
+        data = _prepare_scrape_request("https://example.com", opts)
+        assert data["integration"] == "_unit-test"

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/__tests__/unit/v2/methods/test_search_request_preparation.py

@@ -43,7 +43,8 @@ class TestSearchRequestPreparation:
             location="US",
             ignore_invalid_urls=False,
             timeout=30000,
-            scrape_options=scrape_opts
+            scrape_options=scrape_opts,
+            integration="  _e2e-test  ",
         )
         
         data = _prepare_search_request(request)
@@ -83,6 +84,7 @@ class TestSearchRequestPreparation:
         assert scrape_data["skipTlsVerification"] is True
         assert "removeBase64Images" in scrape_data
         assert scrape_data["removeBase64Images"] is False
+        assert data["integration"] == "_e2e-test"
 
     def test_exclude_none_behavior(self):
         """Test that exclude_none=True behavior is working."""
@@ -164,4 +166,4 @@ class TestSearchRequestPreparation:
         assert "only_main_content" not in scrape_data
         assert "wait_for" not in scrape_data
         assert "skip_tls_verification" not in scrape_data
-        assert "remove_base64_images" not in scrape_data 
+        assert "remove_base64_images" not in scrape_data

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/client.py

@@ -117,6 +117,7 @@ class FirecrawlClient:
         proxy: Optional[str] = None,
         max_age: Optional[int] = None,
         store_in_cache: Optional[bool] = None,
+        integration: Optional[str] = None,
     ) -> Document:
         """
         Scrape a single URL and return the document.
@@ -165,8 +166,9 @@ class FirecrawlClient:
                 proxy=proxy,
                 max_age=max_age,
                 store_in_cache=store_in_cache,
+                integration=integration,
             ).items() if v is not None}
-        ) if any(v is not None for v in [formats, headers, include_tags, exclude_tags, only_main_content, timeout, wait_for, mobile, parsers, actions, location, skip_tls_verification, remove_base64_images, fast_mode, use_mock, block_ads, proxy, max_age, store_in_cache]) else None
+        ) if any(v is not None for v in [formats, headers, include_tags, exclude_tags, only_main_content, timeout, wait_for, mobile, parsers, actions, location, skip_tls_verification, remove_base64_images, fast_mode, use_mock, block_ads, proxy, max_age, store_in_cache, integration]) else None
         return scrape_module.scrape(self.http_client, url, options)
 
     def search(
@@ -181,6 +183,7 @@ class FirecrawlClient:
         ignore_invalid_urls: Optional[bool] = None,
         timeout: Optional[int] = None,
         scrape_options: Optional[ScrapeOptions] = None,
+        integration: Optional[str] = None,
     ) -> SearchData:
         """
         Search for documents.
@@ -206,6 +209,7 @@ class FirecrawlClient:
             ignore_invalid_urls=ignore_invalid_urls,
             timeout=timeout,
             scrape_options=scrape_options,
+            integration=integration,
         )
 
         return search_module.search(self.http_client, request)
@@ -230,7 +234,8 @@ class FirecrawlClient:
         scrape_options: Optional[ScrapeOptions] = None,
         zero_data_retention: bool = False,
         poll_interval: int = 2,
-        timeout: Optional[int] = None
+        timeout: Optional[int] = None,
+        integration: Optional[str] = None,
     ) -> CrawlJob:
         """
         Start a crawl job and wait for it to complete.
@@ -279,7 +284,8 @@ class FirecrawlClient:
             max_concurrency=max_concurrency,
             webhook=webhook,
             scrape_options=scrape_options,
-            zero_data_retention=zero_data_retention
+            zero_data_retention=zero_data_retention,
+            integration=integration,
         )
         
         return crawl_module.crawl(
@@ -307,7 +313,8 @@ class FirecrawlClient:
         max_concurrency: Optional[int] = None,
         webhook: Optional[Union[str, WebhookConfig]] = None,
         scrape_options: Optional[ScrapeOptions] = None,
-        zero_data_retention: bool = False
+        zero_data_retention: bool = False,
+        integration: Optional[str] = None,
     ) -> CrawlResponse:
         """
         Start an asynchronous crawl job.
@@ -353,7 +360,8 @@ class FirecrawlClient:
             max_concurrency=max_concurrency,
             webhook=webhook,
             scrape_options=scrape_options,
-            zero_data_retention=zero_data_retention
+            zero_data_retention=zero_data_retention,
+            integration=integration,
         )
         
         return crawl_module.start_crawl(self.http_client, request)
@@ -421,6 +429,7 @@ class FirecrawlClient:
         limit: Optional[int] = None,
         sitemap: Optional[Literal["only", "include", "skip"]] = None,
         timeout: Optional[int] = None,
+        integration: Optional[str] = None,
         location: Optional[Location] = None,
     ) -> MapData:
         """Map a URL and return discovered links.
@@ -442,8 +451,9 @@ class FirecrawlClient:
             limit=limit,
             sitemap=sitemap if sitemap is not None else "include",
             timeout=timeout,
+            integration=integration,
             location=location
-        ) if any(v is not None for v in [search, include_subdomains, limit, sitemap, timeout, location]) else None
+        ) if any(v is not None for v in [search, include_subdomains, limit, sitemap, timeout, integration, location]) else None
 
         return map_module.map(self.http_client, url, options)
     
@@ -484,6 +494,7 @@ class FirecrawlClient:
         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).
 
@@ -512,6 +523,7 @@ class FirecrawlClient:
             show_sources=show_sources,
             scrape_options=scrape_options,
             ignore_invalid_urls=ignore_invalid_urls,
+            integration=integration,
         )
 
     def extract(
@@ -528,6 +540,7 @@ class FirecrawlClient:
         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.
 
@@ -560,6 +573,7 @@ class FirecrawlClient:
             ignore_invalid_urls=ignore_invalid_urls,
             poll_interval=poll_interval,
             timeout=timeout,
+            integration=integration,
         )
 
     def start_batch_scrape(

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/client_async.py

@@ -132,6 +132,7 @@ class AsyncFirecrawlClient:
         limit: Optional[int] = None,
         sitemap: Optional[Literal["only", "include", "skip"]] = None,
         timeout: Optional[int] = None,
+        integration: Optional[str] = None,
     ) -> MapData:
         options = MapOptions(
             search=search,
@@ -139,7 +140,8 @@ class AsyncFirecrawlClient:
             limit=limit,
             sitemap=sitemap if sitemap is not None else "include",
             timeout=timeout,
-        ) if any(v is not None for v in [search, include_subdomains, limit, sitemap, timeout]) else None
+            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 start_batch_scrape(self, urls: List[str], **kwargs) -> Any:
@@ -196,6 +198,7 @@ class AsyncFirecrawlClient:
         ignore_invalid_urls: Optional[bool] = None,
         poll_interval: int = 2,
         timeout: Optional[int] = None,
+        integration: Optional[str] = None,
     ):
         return await async_extract.extract(
             self.async_http_client,
@@ -210,6 +213,7 @@ class AsyncFirecrawlClient:
             ignore_invalid_urls=ignore_invalid_urls,
             poll_interval=poll_interval,
             timeout=timeout,
+            integration=integration,
         )
 
     async def get_extract_status(self, job_id: str):
@@ -227,6 +231,7 @@ class AsyncFirecrawlClient:
         show_sources: Optional[bool] = None,
         scrape_options: Optional['ScrapeOptions'] = None,
         ignore_invalid_urls: Optional[bool] = None,
+        integration: Optional[str] = None,
     ):
         return await async_extract.start_extract(
             self.async_http_client,
@@ -239,6 +244,7 @@ class AsyncFirecrawlClient:
             show_sources=show_sources,
             scrape_options=scrape_options,
             ignore_invalid_urls=ignore_invalid_urls,
+            integration=integration,
         )
 
     # Usage endpoints

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/aio/batch.py

@@ -26,7 +26,9 @@ def _prepare(urls: List[str], *, options: Optional[ScrapeOptions] = None, **kwar
     if (v := kwargs.get("zero_data_retention")) is not None:
         payload["zeroDataRetention"] = v
     if (v := kwargs.get("integration")) is not None:
-        payload["integration"] = v
+        trimmed_integration = str(v).strip()
+        if trimmed_integration:
+            payload["integration"] = trimmed_integration
     return payload
 
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/aio/crawl.py

@@ -56,6 +56,8 @@ def _prepare_crawl_request(request: CrawlRequest) -> dict:
         if snake in request_data:
             data[camel] = request_data.pop(snake)
     data.update(request_data)
+    if getattr(request, "integration", None) is not None:
+        data["integration"] = str(getattr(request, "integration")).strip()
     return data
 
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/aio/extract.py

@@ -17,6 +17,7 @@ def _prepare_extract_request(
     show_sources: Optional[bool] = None,
     scrape_options: Optional[ScrapeOptions] = None,
     ignore_invalid_urls: Optional[bool] = None,
+    integration: Optional[str] = None,
 ) -> Dict[str, Any]:
     body: Dict[str, Any] = {}
     if urls is not None:
@@ -39,6 +40,8 @@ def _prepare_extract_request(
         prepared = prepare_scrape_options(scrape_options)
         if prepared:
             body["scrapeOptions"] = prepared
+    if integration is not None and str(integration).strip():
+        body["integration"] = str(integration).strip()
     return body
 
 
@@ -54,6 +57,7 @@ async def start_extract(
     show_sources: Optional[bool] = None,
     scrape_options: Optional[ScrapeOptions] = None,
     ignore_invalid_urls: Optional[bool] = None,
+    integration: Optional[str] = None,
 ) -> ExtractResponse:
     body = _prepare_extract_request(
         urls,
@@ -65,6 +69,7 @@ async def start_extract(
         show_sources=show_sources,
         scrape_options=scrape_options,
         ignore_invalid_urls=ignore_invalid_urls,
+        integration=integration,
     )
     resp = await client.post("/v2/extract", body)
     return ExtractResponse(**resp.json())
@@ -106,6 +111,7 @@ async def extract(
     ignore_invalid_urls: Optional[bool] = None,
     poll_interval: int = 2,
     timeout: Optional[int] = None,
+    integration: Optional[str] = None,
 ) -> ExtractResponse:
     started = await start_extract(
         client,
@@ -118,6 +124,7 @@ async def extract(
         show_sources=show_sources,
         scrape_options=scrape_options,
         ignore_invalid_urls=ignore_invalid_urls,
+        integration=integration,
     )
     job_id = getattr(started, "id", None)
     if not job_id:

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/aio/map.py

@@ -20,6 +20,8 @@ def _prepare_map_request(url: str, options: Optional[MapOptions] = None) -> Dict
             data["limit"] = options.limit
         if options.timeout is not None:
             data["timeout"] = options.timeout
+        if options.integration is not None:
+            data["integration"] = options.integration.strip()
         if options.location is not None:
             data["location"] = options.location.model_dump(exclude_none=True)
         payload.update(data)

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/aio/search.py

@@ -10,6 +10,7 @@ from ...types import (
 )
 from ...utils.http_client_async import AsyncHttpClient
 from ...utils.error_handler import handle_response_error
+from ...utils.normalize import normalize_document_input
 from ...utils.validation import validate_scrape_options, prepare_scrape_options
 
 T = TypeVar("T")
@@ -73,7 +74,7 @@ def _transform_array(arr: List[Any], result_type: Type[T]) -> List[Union[T, Docu
                 "summary" in item or
                 "json" in item
             ):
-                results.append(Document(**item))
+                results.append(Document(**normalize_document_input(item)))
             else:
                 results.append(result_type(**item))
         else:
@@ -168,5 +169,8 @@ def _prepare_search_request(request: SearchRequest) -> Dict[str, Any]:
         if scrape_data:
             data["scrapeOptions"] = scrape_data
         data.pop("scrape_options", None)
+    
+    if (v := getattr(validated_request, "integration", None)) is not None and str(v).strip():
+        data["integration"] = str(validated_request.integration).strip()
 
     return data

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/batch.py

@@ -407,7 +407,7 @@ def prepare_batch_scrape_request(
     if zero_data_retention is not None:
         request_data["zeroDataRetention"] = zero_data_retention
     if integration is not None:
-        request_data["integration"] = integration
+        request_data["integration"] = str(integration).strip()
 
     return request_data
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/crawl.py

@@ -99,6 +99,9 @@ def _prepare_crawl_request(request: CrawlRequest) -> dict:
     
     # Add any remaining fields that don't need conversion (like limit)
     data.update(request_data)
+    # Trim integration if present
+    if "integration" in data and isinstance(data["integration"], str):
+        data["integration"] = data["integration"].strip()
     
     return data
 

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/extract.py

@@ -18,6 +18,7 @@ def _prepare_extract_request(
     show_sources: Optional[bool] = None,
     scrape_options: Optional[ScrapeOptions] = None,
     ignore_invalid_urls: Optional[bool] = None,
+    integration: Optional[str] = None,
 ) -> Dict[str, Any]:
     body: Dict[str, Any] = {}
     if urls is not None:
@@ -40,6 +41,8 @@ def _prepare_extract_request(
         prepared = prepare_scrape_options(scrape_options)
         if prepared:
             body["scrapeOptions"] = prepared
+    if integration is not None and str(integration).strip():
+        body["integration"] = str(integration).strip()
     return body
 
 
@@ -55,6 +58,7 @@ def start_extract(
     show_sources: Optional[bool] = None,
     scrape_options: Optional[ScrapeOptions] = None,
     ignore_invalid_urls: Optional[bool] = None,
+    integration: Optional[str] = None,
 ) -> ExtractResponse:
     body = _prepare_extract_request(
         urls,
@@ -66,6 +70,7 @@ def start_extract(
         show_sources=show_sources,
         scrape_options=scrape_options,
         ignore_invalid_urls=ignore_invalid_urls,
+        integration=integration,
     )
     resp = client.post("/v2/extract", body)
     if not resp.ok:
@@ -111,6 +116,7 @@ def extract(
     ignore_invalid_urls: Optional[bool] = None,
     poll_interval: int = 2,
     timeout: Optional[int] = None,
+    integration: Optional[str] = None,
 ) -> ExtractResponse:
     started = start_extract(
         client,
@@ -123,6 +129,7 @@ def extract(
         show_sources=show_sources,
         scrape_options=scrape_options,
         ignore_invalid_urls=ignore_invalid_urls,
+        integration=integration,
     )
     job_id = getattr(started, "id", None)
     if not job_id:

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/map.py

@@ -27,6 +27,8 @@ def _prepare_map_request(url: str, options: Optional[MapOptions] = None) -> Dict
             data["limit"] = options.limit
         if options.timeout is not None:
             data["timeout"] = options.timeout
+        if options.integration is not None and options.integration.strip():
+            data["integration"] = options.integration.strip()
         if options.location is not None:
             data["location"] = options.location.model_dump(exclude_none=True)
         payload.update(data)

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/methods/search.py

@@ -71,7 +71,7 @@ def _transform_array(arr: List[Any], result_type: Type[T]) -> List[Union[T, 'Doc
                 "summary" in item or
                 "json" in item
             ):
-                results.append(Document(**item))
+                results.append(Document(**normalize_document_input(item)))
             else:
                 results.append(result_type(**item))
         else:
@@ -194,4 +194,7 @@ def _prepare_search_request(request: SearchRequest) -> Dict[str, Any]:
             data["scrapeOptions"] = scrape_data
         data.pop("scrape_options", None)
     
+    if (str(getattr(validated_request, "integration", "")).strip()):
+        data["integration"] = str(validated_request.integration).strip()
+    
     return data

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/types.py

@@ -289,6 +289,7 @@ class ScrapeOptions(BaseModel):
     proxy: Optional[Literal["basic", "stealth", "auto"]] = None
     max_age: Optional[int] = None
     store_in_cache: Optional[bool] = None
+    integration: Optional[str] = None
 
     @field_validator('formats')
     @classmethod
@@ -334,6 +335,7 @@ class CrawlRequest(BaseModel):
     webhook: Optional[Union[str, WebhookConfig]] = None
     scrape_options: Optional[ScrapeOptions] = None
     zero_data_retention: bool = False
+    integration: Optional[str] = None
 
 class CrawlResponse(BaseModel):
     """Information about a crawl job."""
@@ -350,6 +352,10 @@ class CrawlJob(BaseModel):
     next: Optional[str] = None
     data: List[Document] = []
 
+class CrawlStatusRequest(BaseModel):
+    """Request to get crawl job status."""
+    job_id: str
+
 class SearchResultWeb(BaseModel):
     """A web search result with URL, title, and description."""
     url: str
@@ -410,6 +416,7 @@ class CrawlParamsData(BaseModel):
     scrape_options: Optional[ScrapeOptions] = None
     zero_data_retention: bool = False
     warning: Optional[str] = None
+    integration: Optional[str] = None
 
 class CrawlParamsResponse(BaseResponse[CrawlParamsData]):
     """Response from crawl params endpoint."""
@@ -420,6 +427,12 @@ class BatchScrapeRequest(BaseModel):
     """Request for batch scraping multiple URLs (internal helper only)."""
     urls: List[str]
     options: Optional[ScrapeOptions] = None
+    webhook: Optional[Union[str, WebhookConfig]] = None
+    append_to_id: Optional[str] = None
+    ignore_invalid_urls: Optional[bool] = None
+    max_concurrency: Optional[int] = None
+    zero_data_retention: Optional[bool] = None
+    integration: Optional[str] = None
 
 class BatchScrapeResponse(BaseModel):
     """Response from starting a batch scrape job (mirrors CrawlResponse naming)."""
@@ -437,6 +450,14 @@ class BatchScrapeJob(BaseModel):
     next: Optional[str] = None
     data: List[Document] = []
 
+class BatchScrapeStatusRequest(BaseModel):
+    """Request to get batch scrape job status."""
+    job_id: str
+
+class BatchScrapeErrorsRequest(BaseModel):
+    """Request to get errors for a batch scrape job."""
+    job_id: str
+
 # Map types
 class MapOptions(BaseModel):
     """Options for mapping operations."""
@@ -445,6 +466,7 @@ class MapOptions(BaseModel):
     include_subdomains: Optional[bool] = None
     limit: Optional[int] = None
     timeout: Optional[int] = None
+    integration: Optional[str] = None
     location: Optional['Location'] = None
 
 class MapRequest(BaseModel):
@@ -452,6 +474,8 @@ class MapRequest(BaseModel):
     url: str
     options: Optional[MapOptions] = None
 
+
+
 class MapData(BaseModel):
     """Map results data."""
     links: List['SearchResult']
@@ -461,6 +485,19 @@ class MapResponse(BaseResponse[MapData]):
     pass
 
 # Extract types
+class ExtractRequest(BaseModel):
+    """Request for extract operations."""
+    urls: Optional[List[str]] = None
+    prompt: Optional[str] = None
+    schema_: Optional[Dict[str, Any]] = Field(default=None, alias="schema")
+    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
+    
 class ExtractResponse(BaseModel):
     """Response for extract operations (start/status/final)."""
     success: Optional[bool] = None
@@ -492,6 +529,10 @@ class TokenUsage(BaseModel):
     billing_period_start: Optional[str] = None
     billing_period_end: Optional[str] = None
 
+class QueueStatusRequest(BaseModel):
+    """Request to retrieve queue status."""
+    pass
+
 class QueueStatusResponse(BaseModel):
     """Metrics about the team's scrape queue."""
     jobs_in_queue: int
@@ -593,6 +634,7 @@ class SearchRequest(BaseModel):
     ignore_invalid_urls: Optional[bool] = None
     timeout: Optional[int] = 60000
     scrape_options: Optional[ScrapeOptions] = None
+    integration: Optional[str] = None
 
     @field_validator('sources')
     @classmethod
@@ -692,6 +734,10 @@ class CrawlErrorsResponse(BaseModel):
     errors: List[CrawlError]
     robots_blocked: List[str]
 
+class CrawlErrorsRequest(BaseModel):
+    """Request for crawl error monitoring."""
+    crawl_id: str
+
 class ActiveCrawl(BaseModel):
     """Information about an active crawl job."""
     id: str
@@ -704,6 +750,10 @@ class ActiveCrawlsResponse(BaseModel):
     success: bool = True
     crawls: List[ActiveCrawl]
 
+class ActiveCrawlsRequest(BaseModel):
+    """Request for listing active crawl jobs."""
+    pass
+
 # Configuration types
 class ClientConfig(BaseModel):
     """Configuration for the Firecrawl client."""

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl/v2/utils/validation.py

@@ -177,6 +177,9 @@ def prepare_scrape_options(options: Optional[ScrapeOptions]) -> Optional[Dict[st
     # Handle special cases
     for key, value in options_data.items():
         if value is not None:
+            if key == "integration":
+                scrape_data["integration"] = (str(value).strip() or None)
+                continue
             if key == "formats":
                 # Handle formats conversion
                 converted_formats: List[Any] = []

{firecrawl-4.3.2 → firecrawl-4.3.3}/firecrawl.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: firecrawl
-Version: 4.3.2
+Version: 4.3.3
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/firecrawl/firecrawl
 Author: Mendable.ai