firecrawl 3.3.0__py3-none-any.whl → 3.3.3__py3-none-any.whl

firecrawl/__init__.py

@@ -17,7 +17,7 @@ from .v1 import (
     V1ChangeTrackingOptions,
 )
 
-__version__ = "3.3.0"
+__version__ = "3.3.3"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

firecrawl/__tests__/e2e/v2/test_scrape.py

@@ -151,4 +151,40 @@ class TestScrapeE2E:
             max_age=0,
             store_in_cache=False,
         )
-        assert isinstance(doc, Document)
+        assert isinstance(doc, Document)
+
+    def test_scrape_images_format(self):
+        """Test images format extraction."""
+        doc = self.client.scrape(
+            "https://firecrawl.dev",
+            formats=["images"]
+        )
+        assert isinstance(doc, Document)
+        assert doc.images is not None
+        assert isinstance(doc.images, list)
+        assert len(doc.images) > 0
+        # Should find firecrawl logo/branding images
+        assert any("firecrawl" in img.lower() or "logo" in img.lower() for img in doc.images)
+
+    def test_scrape_images_with_multiple_formats(self):
+        """Test images format works with other formats."""
+        doc = self.client.scrape(
+            "https://github.com",
+            formats=["markdown", "links", "images"]
+        )
+        assert isinstance(doc, Document)
+        assert doc.markdown is not None
+        assert doc.links is not None  
+        assert doc.images is not None
+        assert isinstance(doc.images, list)
+        assert len(doc.images) > 0
+        
+        # Images should find content not available in links format
+        image_extensions = ['.jpg', '.jpeg', '.png', '.gif', '.webp', '.svg', '.ico']
+        link_images = [
+            link for link in (doc.links or [])
+            if any(ext in link.lower() for ext in image_extensions)
+        ]
+        
+        # Should discover additional images beyond those with obvious extensions
+        assert len(doc.images) >= len(link_images)

firecrawl/client.py

@@ -56,7 +56,6 @@ class V2Proxy:
         self._client = client_instance
 
         if client_instance:
-            # self.scrape = client_instance.scrape
             self.search = client_instance.search
             self.crawl = client_instance.crawl
             self.get_crawl_status = client_instance.get_crawl_status
@@ -168,14 +167,17 @@ class Firecrawl:
         self.v1 = V1Proxy(self._v1_client) if self._v1_client else None
         self.v2 = V2Proxy(self._v2_client)
         
-        
         self.scrape = self._v2_client.scrape
+        self.search = self._v2_client.search
+        self.map = self._v2_client.map
+
         self.crawl = self._v2_client.crawl
         self.start_crawl = self._v2_client.start_crawl
         self.crawl_params_preview = self._v2_client.crawl_params_preview
         self.get_crawl_status = self._v2_client.get_crawl_status
         self.cancel_crawl = self._v2_client.cancel_crawl
         self.get_crawl_errors = self._v2_client.get_crawl_errors
+        self.get_active_crawls = self._v2_client.get_active_crawls
         self.active_crawls = self._v2_client.active_crawls
 
         self.start_batch_scrape = self._v2_client.start_batch_scrape
@@ -183,13 +185,15 @@ class Firecrawl:
         self.cancel_batch_scrape = self._v2_client.cancel_batch_scrape
         self.batch_scrape = self._v2_client.batch_scrape
         self.get_batch_scrape_errors = self._v2_client.get_batch_scrape_errors
+
+        self.start_extract = self._v2_client.start_extract
         self.get_extract_status = self._v2_client.get_extract_status
-        self.map = self._v2_client.map
-        self.search = self._v2_client.search
         self.extract = self._v2_client.extract
+
         self.get_concurrency = self._v2_client.get_concurrency
         self.get_credit_usage = self._v2_client.get_credit_usage
         self.get_token_usage = self._v2_client.get_token_usage
+
         self.watcher = self._v2_client.watcher
         
 class AsyncFirecrawl:

firecrawl/v2/client.py

@@ -13,6 +13,7 @@ from .types import (
     SearchRequest,
     SearchData,
     SourceOption,
+    CategoryOption,
     CrawlRequest,
     CrawlResponse,
     CrawlJob,
@@ -171,6 +172,7 @@ class FirecrawlClient:
         query: str,
         *,
         sources: Optional[List[SourceOption]] = None,
+        categories: Optional[List[CategoryOption]] = None,
         limit: Optional[int] = None,
         tbs: Optional[str] = None,
         location: Optional[str] = None,
@@ -195,6 +197,7 @@ class FirecrawlClient:
         request = SearchRequest(
             query=query,
             sources=sources,
+            categories=categories,
             limit=limit,
             tbs=tbs,
             location=location,

firecrawl/v2/types.py

@@ -114,6 +114,12 @@ class DocumentMetadata(BaseModel):
     def coerce_status_code_to_int(cls, v):
         return cls._coerce_string_to_int(v)
 
+class AttributeResult(BaseModel):
+    """Result of attribute extraction."""
+    selector: str
+    attribute: str
+    values: List[str]
+
 class Document(BaseModel):
     """A scraped document."""
     markdown: Optional[str] = None
@@ -123,6 +129,7 @@ class Document(BaseModel):
     summary: Optional[str] = None
     metadata: Optional[DocumentMetadata] = None
     links: Optional[List[str]] = None
+    images: Optional[List[str]] = None
     screenshot: Optional[str] = None
     actions: Optional[Dict[str, Any]] = None
     warning: Optional[str] = None
@@ -182,7 +189,7 @@ CategoryOption = Union[str, Category]
 
 FormatString = Literal[
     # camelCase versions (API format)
-    "markdown", "html", "rawHtml", "links", "screenshot", "summary", "changeTracking", "json",
+    "markdown", "html", "rawHtml", "links",  "images", "screenshot", "summary", "changeTracking", "json", "attributes",
     # snake_case versions (user-friendly)
     "raw_html", "change_tracking"
 ]
@@ -214,9 +221,18 @@ class ScreenshotFormat(BaseModel):
     full_page: Optional[bool] = None
     quality: Optional[int] = None
     viewport: Optional[Union[Dict[str, int], Viewport]] = None
+    
+class AttributeSelector(BaseModel):
+    """Selector and attribute pair for attribute extraction."""
+    selector: str
+    attribute: str
 
-FormatOption = Union[Dict[str, Any], FormatString, JsonFormat, ChangeTrackingFormat, ScreenshotFormat, Format]
+class AttributesFormat(Format):
+    """Configuration for attribute extraction."""
+    type: Literal["attributes"] = "attributes"
+    selectors: List[AttributeSelector]
 
+FormatOption = Union[Dict[str, Any], FormatString, JsonFormat, ChangeTrackingFormat, ScreenshotFormat, AttributesFormat, Format]
 # Scrape types
 class ScrapeFormats(BaseModel):
     """Output formats for scraping."""
@@ -226,6 +242,7 @@ class ScrapeFormats(BaseModel):
     raw_html: bool = False
     summary: bool = False
     links: bool = False
+    images: bool = False
     screenshot: bool = False
     change_tracking: bool = False
     json: bool = False

{firecrawl-3.3.0.dist-info → firecrawl-3.3.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: firecrawl
-Version: 3.3.0
+Version: 3.3.3
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/firecrawl/firecrawl
 Author: Mendable.ai
@@ -38,8 +38,12 @@ Requires-Dist: httpx
 Requires-Dist: python-dotenv
 Requires-Dist: websockets
 Requires-Dist: nest-asyncio
-Requires-Dist: pydantic (>=2.0)
+Requires-Dist: pydantic>=2.0
 Requires-Dist: aiohttp
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
 
 # Firecrawl Python SDK
 

{firecrawl-3.3.0.dist-info → firecrawl-3.3.3.dist-info}/RECORD

@@ -1,5 +1,5 @@
-firecrawl/__init__.py,sha256=B7SJY_289oeNIVIPxklkrqFQQURmszzwEqFjYXDfd20,2192
-firecrawl/client.py,sha256=2BGIRTiW2eR6q3wu_g2s3VTQtrHYauoDeNF1YklQpHo,11089
+firecrawl/__init__.py,sha256=1MYT5_7-p8sfruL_5y1m1n9AoWG_6aNduWGW4NId86M,2192
+firecrawl/client.py,sha256=tp3mUo_3aGPuZ53kpU4bhM-5EtwD_IUWrJ7wm0GMuCc,11159
 firecrawl/firecrawl.backup.py,sha256=v1FEN3jR4g5Aupg4xp6SLkuFvYMQuUKND2YELbYjE6c,200430
 firecrawl/types.py,sha256=W9N2pqQuevEIIjYHN9rbDf31E-nwdCECqIn11Foz2T8,2836
 firecrawl/__tests__/e2e/v2/conftest.py,sha256=I28TUpN5j0-9gM79NlbrDS8Jlsheao657od2f-2xK0Y,2587
@@ -8,7 +8,7 @@ firecrawl/__tests__/e2e/v2/test_batch_scrape.py,sha256=H9GtuwHIFdOQ958SOVThi_kvD
 firecrawl/__tests__/e2e/v2/test_crawl.py,sha256=cOssZvIwtghAtLiM1QdNLhPEwAxZ9j9umTrBUPtJjpU,9951
 firecrawl/__tests__/e2e/v2/test_extract.py,sha256=HgvGiDlyWtFygiPo5EP44Dem1oWrwgRF-hfc1LfeVSU,1670
 firecrawl/__tests__/e2e/v2/test_map.py,sha256=9sT-Yq8V_8c9esl_bv5hnTA9WXb2Dg81kj6M-s0484c,1618
-firecrawl/__tests__/e2e/v2/test_scrape.py,sha256=psW2nfcA_hMFpZ4msL_VJWJTMa3Sidp11ubhftbm52g,5759
+firecrawl/__tests__/e2e/v2/test_scrape.py,sha256=oyroF_WaEdxgD8t_SHkLBBfDRv1_6xZ_7vSTQpwlmA8,7198
 firecrawl/__tests__/e2e/v2/test_search.py,sha256=tvU9_eg_3H5em0fhIwPPjuYe9BRAQ5St-BLM0l_FfVs,9079
 firecrawl/__tests__/e2e/v2/test_usage.py,sha256=JlBkYblhThua5qF2crRjsPpq4Ja0cBsdzxZ5zxXnQ_Y,805
 firecrawl/__tests__/e2e/v2/test_watcher.py,sha256=OPTKLhVAKWqXl2Tieo6zCN1xpEwZDsz-B977CVJgLMA,1932
@@ -43,9 +43,9 @@ firecrawl/__tests__/unit/v2/watcher/test_ws_watcher.py,sha256=87w47n0iOihtu4jTR4
 firecrawl/v1/__init__.py,sha256=aP1oisPeZVGGZynvENc07JySMOZfv_4zAlxQ0ecMJXA,481
 firecrawl/v1/client.py,sha256=sydurfEFTsXyowyaGryA1lkPxN_r9Nf6iQpM43OwJyM,201672
 firecrawl/v2/__init__.py,sha256=Jc6a8tBjYG5OPkjDM5pl-notyys-7DEj7PLEfepv3fc,137
-firecrawl/v2/client.py,sha256=P6WAzwYGLLIANTrqAM-K4EUdGWQoFsi-zCjBibbxKQw,30507
+firecrawl/v2/client.py,sha256=_DZFZO1aWvODzznK0g2Svcd2-xxXgWGR0d9vniNlk1w,30621
 firecrawl/v2/client_async.py,sha256=zwxHis1bSh0tSF1480ze-4XDQEDJ5yDur1ZqtL94dwc,10127
-firecrawl/v2/types.py,sha256=rBdTaTQmb1SmdR8O0GvA_gCfBG-QCtBOrMsFgA9Usms,22114
+firecrawl/v2/types.py,sha256=F-RCADQFdpAmF5t8LUabLOgyIV02Ol34yNa9y3S3ZMg,22667
 firecrawl/v2/watcher.py,sha256=FOU71tqSKxgeuGycu4ye0SLc2dw7clIcoQjPsi-4Csc,14229
 firecrawl/v2/watcher_async.py,sha256=AVjW2mgABniolSsauK4u0FW8ya6WzRUdyEg2R-8vGCw,10278
 firecrawl/v2/methods/batch.py,sha256=us7zUGl7u9ZDIEk2J3rNqj87bkaNjXU27SMFW_fdcg8,11932
@@ -70,10 +70,10 @@ firecrawl/v2/utils/http_client.py,sha256=_n8mp4xi6GGihg662Lsv6TSlvw9zykyADwEk0fg
 firecrawl/v2/utils/http_client_async.py,sha256=iy89_bk2HS3afSRHZ8016eMCa9Fk-5MFTntcOHfbPgE,1936
 firecrawl/v2/utils/normalize.py,sha256=nlTU6QRghT1YKZzNZlIQj4STSRuSUGrS9cCErZIcY5w,3636
 firecrawl/v2/utils/validation.py,sha256=L8by7z-t6GuMGIYkK7il1BM8d-4_-sAdG9hDMF_LeG4,14518
+firecrawl-3.3.3.dist-info/licenses/LICENSE,sha256=nPCunEDwjRGHlmjvsiDUyIWbkqqyj3Ej84ntnh0g0zA,1084
 tests/test_change_tracking.py,sha256=_IJ5ShLcoj2fHDBaw-nE4I4lHdmDB617ocK_XMHhXps,4177
 tests/test_timeout_conversion.py,sha256=PWlIEMASQNhu4cp1OW_ebklnE9NCiigPnEFCtI5N3w0,3996
-firecrawl-3.3.0.dist-info/LICENSE,sha256=nPCunEDwjRGHlmjvsiDUyIWbkqqyj3Ej84ntnh0g0zA,1084
-firecrawl-3.3.0.dist-info/METADATA,sha256=Yk4-i0M6LdZdXoOQgdXyaclEX695WhU0JjhfdPePg9w,7313
-firecrawl-3.3.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-firecrawl-3.3.0.dist-info/top_level.txt,sha256=8T3jOaSN5mtLghO-R3MQ8KO290gIX8hmfxQmglBPdLE,16
-firecrawl-3.3.0.dist-info/RECORD,,
+firecrawl-3.3.3.dist-info/METADATA,sha256=4KbMa3eOGJ3SXkPWvDwQP92ceCcEfuPp3AQMNj3o7lE,7392
+firecrawl-3.3.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+firecrawl-3.3.3.dist-info/top_level.txt,sha256=8T3jOaSN5mtLghO-R3MQ8KO290gIX8hmfxQmglBPdLE,16
+firecrawl-3.3.3.dist-info/RECORD,,

{firecrawl-3.3.0.dist-info → firecrawl-3.3.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.38.4)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any