firecrawl-py 4.13.2__tar.gz → 4.14.0__tar.gz

{firecrawl_py-4.13.2/firecrawl_py.egg-info → firecrawl_py-4.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: firecrawl-py
-Version: 4.13.2
+Version: 4.14.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/firecrawl/firecrawl
 Author: Mendable.ai
@@ -134,6 +134,32 @@ crawl_status = firecrawl.get_crawl_status("<crawl_id>")
 print(crawl_status)
 ```
 
+### Manual Pagination (v2)
+
+Crawl and batch scrape status responses may include a `next` URL when more data is available. The SDK auto-paginates by default; to page manually, disable auto-pagination and pass the opaque `next` URL back to the SDK.
+
+```python
+from firecrawl.v2.types import PaginationConfig
+
+# Crawl: fetch one page at a time
+crawl_job = firecrawl.start_crawl("https://firecrawl.dev", limit=100)
+status = firecrawl.get_crawl_status(
+  crawl_job.id,
+  pagination_config=PaginationConfig(auto_paginate=False),
+)
+if status.next:
+  page2 = firecrawl.get_crawl_status_page(status.next)
+
+# Batch scrape: fetch one page at a time
+batch_job = firecrawl.start_batch_scrape(["https://firecrawl.dev"])
+status = firecrawl.get_batch_scrape_status(
+  batch_job.id,
+  pagination_config=PaginationConfig(auto_paginate=False),
+)
+if status.next:
+  page2 = firecrawl.get_batch_scrape_status_page(status.next)
+```
+
 ### Cancelling a Crawl
 
 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.

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/README.md

@@ -87,6 +87,32 @@ crawl_status = firecrawl.get_crawl_status("<crawl_id>")
 print(crawl_status)
 ```
 
+### Manual Pagination (v2)
+
+Crawl and batch scrape status responses may include a `next` URL when more data is available. The SDK auto-paginates by default; to page manually, disable auto-pagination and pass the opaque `next` URL back to the SDK.
+
+```python
+from firecrawl.v2.types import PaginationConfig
+
+# Crawl: fetch one page at a time
+crawl_job = firecrawl.start_crawl("https://firecrawl.dev", limit=100)
+status = firecrawl.get_crawl_status(
+  crawl_job.id,
+  pagination_config=PaginationConfig(auto_paginate=False),
+)
+if status.next:
+  page2 = firecrawl.get_crawl_status_page(status.next)
+
+# Batch scrape: fetch one page at a time
+batch_job = firecrawl.start_batch_scrape(["https://firecrawl.dev"])
+status = firecrawl.get_batch_scrape_status(
+  batch_job.id,
+  pagination_config=PaginationConfig(auto_paginate=False),
+)
+if status.next:
+  page2 = firecrawl.get_batch_scrape_status_page(status.next)
+```
+
 ### Cancelling a Crawl
 
 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.
@@ -184,4 +210,4 @@ firecrawl = Firecrawl(api_key="YOUR_API_KEY")
 doc_v1 = firecrawl.v1.scrape_url('https://firecrawl.dev', formats=['markdown', 'html'])
 crawl_v1 = firecrawl.v1.crawl_url('https://firecrawl.dev', limit=100)
 map_v1 = firecrawl.v1.map_url('https://firecrawl.dev')
-```
+```

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/firecrawl/__init__.py

@@ -17,7 +17,7 @@ from .v1 import (
     V1ChangeTrackingOptions,
 )
 
-__version__ = "4.13.2"
+__version__ = "4.14.0"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/firecrawl/__tests__/e2e/v2/test_batch_scrape.py

@@ -1,8 +1,9 @@
 import os
+import time
 import pytest
 from dotenv import load_dotenv
 from firecrawl import Firecrawl
-from firecrawl.v2.types import ScrapeOptions
+from firecrawl.v2.types import ScrapeOptions, PaginationConfig
 
 load_dotenv()
 
@@ -48,6 +49,39 @@ class TestBatchScrapeE2E:
         assert job.status in ["scraping", "completed", "failed"]
         assert job.total >= 0
 
+    def test_get_batch_scrape_status_page(self):
+        """Fetch a single batch scrape page using the next URL."""
+        urls = [f"https://docs.firecrawl.dev?batch={i}" for i in range(15)]
+
+        start_resp = self.client.start_batch_scrape(
+            urls,
+            formats=["markdown"],
+            ignore_invalid_urls=True,
+        )
+        assert start_resp.id is not None
+
+        pagination_config = PaginationConfig(auto_paginate=False)
+        deadline = time.time() + 120
+        status_job = None
+        while time.time() < deadline:
+            status_job = self.client.get_batch_scrape_status(
+                start_resp.id,
+                pagination_config=pagination_config,
+            )
+            if status_job.next:
+                break
+            if status_job.status in ["completed", "failed", "cancelled"]:
+                break
+            time.sleep(2)
+
+        assert status_job is not None
+        if not status_job.next:
+            pytest.skip("Batch scrape completed without pagination; skipping page fetch.")
+
+        next_page = self.client.get_batch_scrape_status_page(status_job.next)
+        assert isinstance(next_page.data, list)
+        assert next_page.status in ["scraping", "completed", "failed", "cancelled"]
+
     def test_wait_batch_with_all_params(self):
         """Blocking waiter with JSON and changeTracking formats plus many options."""
         urls = [
@@ -103,4 +137,3 @@ class TestBatchScrapeE2E:
 
         cancelled = self.client.cancel_batch_scrape(start_resp.id)
         assert cancelled is True
-

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/firecrawl/__tests__/e2e/v2/test_crawl.py

@@ -3,7 +3,7 @@ import time
 import os
 from dotenv import load_dotenv
 from firecrawl import Firecrawl
-from firecrawl.v2.types import ScrapeOptions
+from firecrawl.v2.types import ScrapeOptions, PaginationConfig
 
 load_dotenv()
 
@@ -66,6 +66,33 @@ class TestCrawlE2E:
         assert status_job.next is None
         assert isinstance(status_job.data, list)
 
+    def test_get_crawl_status_page(self):
+        """Fetch a single crawl page using the next URL."""
+        start_job = self.client.start_crawl("https://docs.firecrawl.dev", limit=25)
+        assert start_job.id is not None
+
+        pagination_config = PaginationConfig(auto_paginate=False)
+        deadline = time.time() + 120
+        status_job = None
+        while time.time() < deadline:
+            status_job = self.client.get_crawl_status(
+                start_job.id,
+                pagination_config=pagination_config,
+            )
+            if status_job.next:
+                break
+            if status_job.status in ["completed", "failed", "cancelled"]:
+                break
+            time.sleep(2)
+
+        assert status_job is not None
+        if not status_job.next:
+            pytest.skip("Crawl completed without pagination; skipping page fetch.")
+
+        next_page = self.client.get_crawl_status_page(status_job.next)
+        assert isinstance(next_page.data, list)
+        assert next_page.status in ["scraping", "completed", "failed", "cancelled"]
+
     def test_cancel_crawl(self):
         """Test canceling a crawl."""
         start_job = self.client.start_crawl("https://docs.firecrawl.dev", limit=3)
@@ -275,4 +302,4 @@ class TestCrawlE2E:
         assert params_data is not None
         assert params_data.limit is not None or params_data.include_paths is not None or params_data.max_discovery_depth is not None 
         assert 'blog/.*' in params_data.include_paths
-        assert 'docs/.*' in params_data.include_paths
+        assert 'docs/.*' in params_data.include_paths

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/firecrawl/__tests__/unit/v2/methods/test_pagination.py

@@ -14,10 +14,18 @@ from firecrawl.v2.types import (
     Document, 
     DocumentMetadata
 )
-from firecrawl.v2.methods.crawl import get_crawl_status, _fetch_all_pages
-from firecrawl.v2.methods.batch import get_batch_scrape_status, _fetch_all_batch_pages
-from firecrawl.v2.methods.aio.crawl import get_crawl_status as get_crawl_status_async, _fetch_all_pages_async
-from firecrawl.v2.methods.aio.batch import get_batch_scrape_status as get_batch_scrape_status_async, _fetch_all_batch_pages_async
+from firecrawl.v2.methods.crawl import get_crawl_status, get_crawl_status_page, _fetch_all_pages
+from firecrawl.v2.methods.batch import get_batch_scrape_status, get_batch_scrape_status_page, _fetch_all_batch_pages
+from firecrawl.v2.methods.aio.crawl import (
+    get_crawl_status as get_crawl_status_async,
+    get_crawl_status_page as get_crawl_status_page_async,
+    _fetch_all_pages_async,
+)
+from firecrawl.v2.methods.aio.batch import (
+    get_batch_scrape_status as get_batch_scrape_status_async,
+    get_batch_scrape_status_page as get_batch_scrape_status_page_async,
+    _fetch_all_batch_pages_async,
+)
 
 
 class TestPaginationConfig:
@@ -123,6 +131,59 @@ class TestCrawlPagination:
         self.mock_client.get.assert_called_with(
             f"/v2/crawl/{self.job_id}", timeout=timeout_seconds
         )
+
+    def test_get_crawl_status_page(self):
+        """Test get_crawl_status_page returns a single page."""
+        mock_response = Mock()
+        mock_response.ok = True
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 10,
+            "total": 20,
+            "creditsUsed": 5,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": "https://api.firecrawl.dev/v2/crawl/test-crawl-123?page=3",
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+        next_url = "https://api.firecrawl.dev/v2/crawl/test-crawl-123?page=2"
+
+        result = get_crawl_status_page(self.mock_client, next_url)
+
+        assert result.status == "completed"
+        assert result.next == "https://api.firecrawl.dev/v2/crawl/test-crawl-123?page=3"
+        assert len(result.data) == 1
+        self.mock_client.get.assert_called_with(next_url, timeout=None)
+
+    def test_get_crawl_status_page_propagates_request_timeout(self):
+        """Ensure request_timeout is forwarded to crawl status page requests."""
+        mock_response = Mock()
+        mock_response.ok = True
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 1,
+            "total": 1,
+            "creditsUsed": 1,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": None,
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+
+        next_url = "https://api.firecrawl.dev/v2/crawl/test-crawl-123?page=2"
+        timeout_seconds = 4.2
+        result = get_crawl_status_page(
+            self.mock_client,
+            next_url,
+            request_timeout=timeout_seconds,
+        )
+
+        assert result.status == "completed"
+        self.mock_client.get.assert_called_with(next_url, timeout=timeout_seconds)
     
     def test_get_crawl_status_with_pagination(self):
         """Test get_crawl_status with auto_paginate=True."""
@@ -326,6 +387,59 @@ class TestBatchScrapePagination:
         assert result.next == "https://api.firecrawl.dev/v2/batch/scrape/test-batch-123?page=2"
         assert len(result.data) == 1
         assert isinstance(result.data[0], Document)
+
+    def test_get_batch_scrape_status_page(self):
+        """Test get_batch_scrape_status_page returns a single page."""
+        mock_response = Mock()
+        mock_response.ok = True
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 10,
+            "total": 20,
+            "creditsUsed": 5,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": "https://api.firecrawl.dev/v2/batch/scrape/test-batch-123?page=3",
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+        next_url = "https://api.firecrawl.dev/v2/batch/scrape/test-batch-123?page=2"
+
+        result = get_batch_scrape_status_page(self.mock_client, next_url)
+
+        assert result.status == "completed"
+        assert result.next == "https://api.firecrawl.dev/v2/batch/scrape/test-batch-123?page=3"
+        assert len(result.data) == 1
+        self.mock_client.get.assert_called_with(next_url, timeout=None)
+
+    def test_get_batch_scrape_status_page_propagates_request_timeout(self):
+        """Ensure request_timeout is forwarded to batch status page requests."""
+        mock_response = Mock()
+        mock_response.ok = True
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 1,
+            "total": 1,
+            "creditsUsed": 1,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": None,
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+
+        next_url = "https://api.firecrawl.dev/v2/batch/scrape/test-batch-123?page=2"
+        timeout_seconds = 2.7
+        result = get_batch_scrape_status_page(
+            self.mock_client,
+            next_url,
+            request_timeout=timeout_seconds,
+        )
+
+        assert result.status == "completed"
+        self.mock_client.get.assert_called_with(next_url, timeout=timeout_seconds)
     
     def test_get_batch_scrape_status_with_pagination(self):
         """Test get_batch_scrape_status with auto_paginate=True."""
@@ -493,6 +607,61 @@ class TestAsyncPagination:
             f"/v2/crawl/{self.job_id}", timeout=timeout_seconds
         )
 
+    @pytest.mark.asyncio
+    async def test_get_crawl_status_page_async(self):
+        """Test async get_crawl_status_page returns a single page."""
+        mock_response = Mock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 10,
+            "total": 20,
+            "creditsUsed": 5,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": "https://api.firecrawl.dev/v2/crawl/test-async-123?page=3",
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+        next_url = "https://api.firecrawl.dev/v2/crawl/test-async-123?page=2"
+
+        result = await get_crawl_status_page_async(self.mock_client, next_url)
+
+        assert result.status == "completed"
+        assert result.next == "https://api.firecrawl.dev/v2/crawl/test-async-123?page=3"
+        assert len(result.data) == 1
+        self.mock_client.get.assert_awaited_with(next_url, timeout=None)
+
+    @pytest.mark.asyncio
+    async def test_get_crawl_status_page_async_propagates_request_timeout(self):
+        """Ensure async request_timeout is forwarded to crawl status page requests."""
+        mock_response = Mock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 1,
+            "total": 1,
+            "creditsUsed": 1,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": None,
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+
+        next_url = "https://api.firecrawl.dev/v2/crawl/test-async-123?page=2"
+        timeout_seconds = 6.1
+        result = await get_crawl_status_page_async(
+            self.mock_client,
+            next_url,
+            request_timeout=timeout_seconds,
+        )
+
+        assert result.status == "completed"
+        self.mock_client.get.assert_awaited_with(next_url, timeout=timeout_seconds)
+
     @pytest.mark.asyncio
     async def test_get_batch_scrape_status_async_with_pagination(self):
         """Test async get_batch_scrape_status with pagination."""
@@ -534,6 +703,61 @@ class TestAsyncPagination:
         assert result.next is None
         assert len(result.data) == 2
         assert self.mock_client.get.call_count == 2
+
+    @pytest.mark.asyncio
+    async def test_get_batch_scrape_status_page_async(self):
+        """Test async get_batch_scrape_status_page returns a single page."""
+        mock_response = Mock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 10,
+            "total": 20,
+            "creditsUsed": 5,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": "https://api.firecrawl.dev/v2/batch/scrape/test-async-123?page=3",
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+        next_url = "https://api.firecrawl.dev/v2/batch/scrape/test-async-123?page=2"
+
+        result = await get_batch_scrape_status_page_async(self.mock_client, next_url)
+
+        assert result.status == "completed"
+        assert result.next == "https://api.firecrawl.dev/v2/batch/scrape/test-async-123?page=3"
+        assert len(result.data) == 1
+        self.mock_client.get.assert_awaited_with(next_url, timeout=None)
+
+    @pytest.mark.asyncio
+    async def test_get_batch_scrape_status_page_async_propagates_request_timeout(self):
+        """Ensure async request_timeout is forwarded to batch status page requests."""
+        mock_response = Mock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = {
+            "success": True,
+            "status": "completed",
+            "completed": 1,
+            "total": 1,
+            "creditsUsed": 1,
+            "expiresAt": "2024-01-01T00:00:00Z",
+            "next": None,
+            "data": [self.sample_doc],
+        }
+
+        self.mock_client.get.return_value = mock_response
+
+        next_url = "https://api.firecrawl.dev/v2/batch/scrape/test-async-123?page=2"
+        timeout_seconds = 4.4
+        result = await get_batch_scrape_status_page_async(
+            self.mock_client,
+            next_url,
+            request_timeout=timeout_seconds,
+        )
+
+        assert result.status == "completed"
+        self.mock_client.get.assert_awaited_with(next_url, timeout=timeout_seconds)
     
     @pytest.mark.asyncio
     async def test_fetch_all_pages_async_limits(self):

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/firecrawl/client.py

@@ -61,6 +61,7 @@ class V2Proxy:
             self.crawl = client_instance.crawl
             self.start_crawl = client_instance.start_crawl
             self.get_crawl_status = client_instance.get_crawl_status
+            self.get_crawl_status_page = client_instance.get_crawl_status_page
             self.cancel_crawl = client_instance.cancel_crawl
             self.get_crawl_errors = client_instance.get_crawl_errors
             self.get_active_crawls = client_instance.get_active_crawls
@@ -78,6 +79,7 @@ class V2Proxy:
 
             self.start_batch_scrape = client_instance.start_batch_scrape
             self.get_batch_scrape_status = client_instance.get_batch_scrape_status
+            self.get_batch_scrape_status_page = client_instance.get_batch_scrape_status_page
             self.cancel_batch_scrape = client_instance.cancel_batch_scrape
             self.batch_scrape = client_instance.batch_scrape
             self.get_batch_scrape_errors = client_instance.get_batch_scrape_errors
@@ -127,6 +129,7 @@ class AsyncV2Proxy:
             self.start_crawl = client_instance.start_crawl
             self.wait_crawl = client_instance.wait_crawl
             self.get_crawl_status = client_instance.get_crawl_status
+            self.get_crawl_status_page = client_instance.get_crawl_status_page
             self.cancel_crawl = client_instance.cancel_crawl
             self.get_crawl_errors = client_instance.get_crawl_errors
             self.get_active_crawls = client_instance.get_active_crawls
@@ -144,6 +147,7 @@ class AsyncV2Proxy:
 
             self.start_batch_scrape = client_instance.start_batch_scrape
             self.get_batch_scrape_status = client_instance.get_batch_scrape_status
+            self.get_batch_scrape_status_page = client_instance.get_batch_scrape_status_page
             self.cancel_batch_scrape = client_instance.cancel_batch_scrape
             self.wait_batch_scrape = client_instance.wait_batch_scrape
             self.batch_scrape = client_instance.batch_scrape
@@ -198,6 +202,7 @@ class Firecrawl:
         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.get_crawl_status_page = self._v2_client.get_crawl_status_page
         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
@@ -205,6 +210,7 @@ class Firecrawl:
 
         self.start_batch_scrape = self._v2_client.start_batch_scrape
         self.get_batch_scrape_status = self._v2_client.get_batch_scrape_status
+        self.get_batch_scrape_status_page = self._v2_client.get_batch_scrape_status_page
         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
@@ -248,6 +254,7 @@ class AsyncFirecrawl:
 
         self.start_crawl = self._v2_client.start_crawl
         self.get_crawl_status = self._v2_client.get_crawl_status
+        self.get_crawl_status_page = self._v2_client.get_crawl_status_page
         self.cancel_crawl = self._v2_client.cancel_crawl
         self.crawl = self._v2_client.crawl
         self.get_crawl_errors = self._v2_client.get_crawl_errors
@@ -256,6 +263,7 @@ class AsyncFirecrawl:
 
         self.start_batch_scrape = self._v2_client.start_batch_scrape
         self.get_batch_scrape_status = self._v2_client.get_batch_scrape_status
+        self.get_batch_scrape_status_page = self._v2_client.get_batch_scrape_status_page
         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
@@ -278,4 +286,4 @@ class AsyncFirecrawl:
 
 # Export Firecrawl as an alias for FirecrawlApp
 FirecrawlApp = Firecrawl
-AsyncFirecrawlApp = AsyncFirecrawl
+AsyncFirecrawlApp = AsyncFirecrawl

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/firecrawl/v1/client.py

@@ -150,7 +150,7 @@ class V1ScrapeOptions(pydantic.BaseModel):
     skipTlsVerification: Optional[bool] = None
     removeBase64Images: Optional[bool] = None
     blockAds: Optional[bool] = None
-    proxy: Optional[Literal["basic", "stealth", "auto"]] = None
+    proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None
     changeTrackingOptions: Optional[V1ChangeTrackingOptions] = None
     maxAge: Optional[int] = None
     storeInCache: Optional[bool] = None
@@ -542,7 +542,7 @@ class V1FirecrawlApp:
             skip_tls_verification: Optional[bool] = None,
             remove_base64_images: Optional[bool] = None,
             block_ads: Optional[bool] = None,
-            proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+            proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None,
             parse_pdf: Optional[bool] = None,
             extract: Optional[V1JsonConfig] = None,
             json_options: Optional[V1JsonConfig] = None,
@@ -1441,7 +1441,7 @@ class V1FirecrawlApp:
         skip_tls_verification: Optional[bool] = None,
         remove_base64_images: Optional[bool] = None,
         block_ads: Optional[bool] = None,
-        proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+        proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None,
         extract: Optional[V1JsonConfig] = None,
         json_options: Optional[V1JsonConfig] = None,
         actions: Optional[List[Union[V1WaitAction, V1ScreenshotAction, V1ClickAction, V1WriteAction, V1PressAction, V1ScrollAction, V1ScrapeAction, V1ExecuteJavascriptAction, V1PDFAction]]] = None,
@@ -1582,7 +1582,7 @@ class V1FirecrawlApp:
         skip_tls_verification: Optional[bool] = None,
         remove_base64_images: Optional[bool] = None,
         block_ads: Optional[bool] = None,
-        proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+        proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None,
         extract: Optional[V1JsonConfig] = None,
         json_options: Optional[V1JsonConfig] = None,
         actions: Optional[List[Union[V1WaitAction, V1ScreenshotAction, V1ClickAction, V1WriteAction, V1PressAction, V1ScrollAction, V1ScrapeAction, V1ExecuteJavascriptAction, V1PDFAction]]] = None,
@@ -1722,7 +1722,7 @@ class V1FirecrawlApp:
         skip_tls_verification: Optional[bool] = None,
         remove_base64_images: Optional[bool] = None,
         block_ads: Optional[bool] = None,
-        proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+        proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None,
         extract: Optional[V1JsonConfig] = None,
         json_options: Optional[V1JsonConfig] = None,
         actions: Optional[List[Union[V1WaitAction, V1ScreenshotAction, V1ClickAction, V1WriteAction, V1PressAction, V1ScrollAction, V1ScrapeAction, V1ExecuteJavascriptAction, V1PDFAction]]] = None,
@@ -3523,7 +3523,7 @@ class AsyncV1FirecrawlApp(V1FirecrawlApp):
             skip_tls_verification: Optional[bool] = None,
             remove_base64_images: Optional[bool] = None,
             block_ads: Optional[bool] = None,
-            proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+            proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None,
             parse_pdf: Optional[bool] = None,
             extract: Optional[V1JsonConfig] = None,
             json_options: Optional[V1JsonConfig] = None,
@@ -3657,7 +3657,7 @@ class AsyncV1FirecrawlApp(V1FirecrawlApp):
         skip_tls_verification: Optional[bool] = None,
         remove_base64_images: Optional[bool] = None,
         block_ads: Optional[bool] = None,
-        proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+        proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None,
         extract: Optional[V1JsonConfig] = None,
         json_options: Optional[V1JsonConfig] = None,
         actions: Optional[List[Union[V1WaitAction, V1ScreenshotAction, V1ClickAction, V1WriteAction, V1PressAction, V1ScrollAction, V1ScrapeAction, V1ExecuteJavascriptAction, V1PDFAction]]] = None,
@@ -3796,7 +3796,7 @@ class AsyncV1FirecrawlApp(V1FirecrawlApp):
         skip_tls_verification: Optional[bool] = None,
         remove_base64_images: Optional[bool] = None,
         block_ads: Optional[bool] = None,
-        proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+        proxy: Optional[Literal["basic", "stealth", "enhanced", "auto"]] = None,
         extract: Optional[V1JsonConfig] = None,
         json_options: Optional[V1JsonConfig] = None,
         actions: Optional[List[Union[V1WaitAction, V1ScreenshotAction, V1ClickAction, V1WriteAction, V1PressAction, V1ScrollAction, V1ScrapeAction, V1ExecuteJavascriptAction, V1PDFAction]]] = None,

{firecrawl_py-4.13.2 → firecrawl_py-4.14.0}/firecrawl/v2/client.py

@@ -423,6 +423,28 @@ class FirecrawlClient:
             pagination_config=pagination_config,
             request_timeout=request_timeout,
         )
+
+    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 crawl_module.get_crawl_status_page(
+            self.http_client,
+            next_url,
+            request_timeout=request_timeout,
+        )
     
     def get_crawl_errors(self, crawl_id: str) -> CrawlErrorsResponse:
         """
@@ -741,6 +763,27 @@ class FirecrawlClient:
             pagination_config=pagination_config
         )
 
+    def get_batch_scrape_status_page(
+        self,
+        next_url: str,
+        *,
+        request_timeout: Optional[float] = None,
+    ):
+        """Fetch a single page of batch scrape results using a next URL.
+
+        Args:
+            next_url: Opaque next URL from a prior batch scrape status response
+            request_timeout: Timeout (in seconds) for the HTTP request
+
+        Returns:
+            BatchScrapeJob with the page data and next URL (if any)
+        """
+        return batch_module.get_batch_scrape_status_page(
+            self.http_client,
+            next_url,
+            request_timeout=request_timeout,
+        )
+
     def cancel_batch_scrape(self, job_id: str) -> bool:
         """Cancel a running batch scrape job.