firecrawl 2.5.3__py3-none-any.whl → 2.6.0__py3-none-any.whl

firecrawl/__init__.py

@@ -13,7 +13,7 @@ import os
 
 from .firecrawl import FirecrawlApp, AsyncFirecrawlApp, JsonConfig, ScrapeOptions, ChangeTrackingOptions # noqa
 
-__version__ = "2.5.3"
+__version__ = "2.6.0"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

firecrawl/firecrawl.py

@@ -161,7 +161,7 @@ class ScrapeOptions(pydantic.BaseModel):
 class WaitAction(pydantic.BaseModel):
     """Wait action to perform during scraping."""
     type: Literal["wait"]
-    milliseconds: int
+    milliseconds: Optional[int] = None
     selector: Optional[str] = None
 
 class ScreenshotAction(pydantic.BaseModel):
@@ -259,6 +259,7 @@ class CrawlParams(pydantic.BaseModel):
     deduplicateSimilarURLs: Optional[bool] = None
     ignoreQueryParameters: Optional[bool] = None
     regexOnFullURL: Optional[bool] = None
+    delay: Optional[int] = None  # Delay in seconds between scrapes
 
 class CrawlResponse(pydantic.BaseModel):
     """Response from crawling operations."""
@@ -346,6 +347,7 @@ class GenerateLLMsTextParams(pydantic.BaseModel):
     """
     maxUrls: Optional[int] = 10
     showFullText: Optional[bool] = False
+    cache: Optional[bool] = True
     __experimental_stream: Optional[bool] = None
 
 class DeepResearchParams(pydantic.BaseModel):
@@ -681,6 +683,7 @@ class FirecrawlApp:
         deduplicate_similar_urls: Optional[bool] = None,
         ignore_query_parameters: Optional[bool] = None,
         regex_on_full_url: Optional[bool] = None,
+        delay: Optional[int] = None,
         poll_interval: Optional[int] = 2,
         idempotency_key: Optional[str] = None,
         **kwargs
@@ -703,6 +706,7 @@ class FirecrawlApp:
             deduplicate_similar_urls (Optional[bool]): Remove similar URLs
             ignore_query_parameters (Optional[bool]): Ignore URL parameters
             regex_on_full_url (Optional[bool]): Apply regex to full URLs
+            delay (Optional[int]): Delay in seconds between scrapes
             poll_interval (Optional[int]): Seconds between status checks (default: 2)
             idempotency_key (Optional[str]): Unique key to prevent duplicate requests
             **kwargs: Additional parameters to pass to the API
@@ -748,6 +752,8 @@ class FirecrawlApp:
             crawl_params['ignoreQueryParameters'] = ignore_query_parameters
         if regex_on_full_url is not None:
             crawl_params['regexOnFullURL'] = regex_on_full_url
+        if delay is not None:
+            crawl_params['delay'] = delay
 
         # Add any additional kwargs
         crawl_params.update(kwargs)
@@ -788,6 +794,7 @@ class FirecrawlApp:
         deduplicate_similar_urls: Optional[bool] = None,
         ignore_query_parameters: Optional[bool] = None,
         regex_on_full_url: Optional[bool] = None,
+        delay: Optional[int] = None,
         idempotency_key: Optional[str] = None,
         **kwargs
     ) -> CrawlResponse:
@@ -854,6 +861,8 @@ class FirecrawlApp:
             crawl_params['ignoreQueryParameters'] = ignore_query_parameters
         if regex_on_full_url is not None:
             crawl_params['regexOnFullURL'] = regex_on_full_url
+        if delay is not None:
+            crawl_params['delay'] = delay
 
         # Add any additional kwargs
         crawl_params.update(kwargs)
@@ -1862,6 +1871,7 @@ class FirecrawlApp:
             *,
             max_urls: Optional[int] = None,
             show_full_text: Optional[bool] = None,
+            cache: Optional[bool] = None,
             experimental_stream: Optional[bool] = None) -> GenerateLLMsTextStatusResponse:
         """
         Generate LLMs.txt for a given URL and poll until completion.
@@ -1870,6 +1880,7 @@ class FirecrawlApp:
             url (str): Target URL to generate LLMs.txt from
             max_urls (Optional[int]): Maximum URLs to process (default: 10)
             show_full_text (Optional[bool]): Include full text in output (default: False)
+            cache (Optional[bool]): Whether to use cached content if available (default: True)
             experimental_stream (Optional[bool]): Enable experimental streaming
 
         Returns:
@@ -1885,6 +1896,7 @@ class FirecrawlApp:
         params = GenerateLLMsTextParams(
             maxUrls=max_urls,
             showFullText=show_full_text,
+            cache=cache,
             __experimental_stream=experimental_stream
         )
 
@@ -1892,6 +1904,7 @@ class FirecrawlApp:
             url,
             max_urls=max_urls,
             show_full_text=show_full_text,
+            cache=cache,
             experimental_stream=experimental_stream
         )
         
@@ -1927,6 +1940,7 @@ class FirecrawlApp:
             *,
             max_urls: Optional[int] = None,
             show_full_text: Optional[bool] = None,
+            cache: Optional[bool] = None,
             experimental_stream: Optional[bool] = None) -> GenerateLLMsTextResponse:
         """
         Initiate an asynchronous LLMs.txt generation operation.
@@ -1935,6 +1949,7 @@ class FirecrawlApp:
             url (str): The target URL to generate LLMs.txt from. Must be a valid HTTP/HTTPS URL.
             max_urls (Optional[int]): Maximum URLs to process (default: 10)
             show_full_text (Optional[bool]): Include full text in output (default: False)
+            cache (Optional[bool]): Whether to use cached content if available (default: True)
             experimental_stream (Optional[bool]): Enable experimental streaming
 
         Returns:
@@ -1949,6 +1964,7 @@ class FirecrawlApp:
         params = GenerateLLMsTextParams(
             maxUrls=max_urls,
             showFullText=show_full_text,
+            cache=cache,
             __experimental_stream=experimental_stream
         )
 
@@ -3240,6 +3256,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
         deduplicate_similar_urls: Optional[bool] = None,
         ignore_query_parameters: Optional[bool] = None,
         regex_on_full_url: Optional[bool] = None,
+        delay: Optional[int] = None,
         poll_interval: Optional[int] = 2,
         idempotency_key: Optional[str] = None,
         **kwargs
@@ -3262,6 +3279,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
             deduplicate_similar_urls (Optional[bool]): Remove similar URLs
             ignore_query_parameters (Optional[bool]): Ignore URL parameters
             regex_on_full_url (Optional[bool]): Apply regex to full URLs
+            delay (Optional[int]): Delay in seconds between scrapes
             poll_interval (Optional[int]): Seconds between status checks (default: 2)
             idempotency_key (Optional[str]): Unique key to prevent duplicate requests
             **kwargs: Additional parameters to pass to the API
@@ -3307,6 +3325,8 @@ class AsyncFirecrawlApp(FirecrawlApp):
             crawl_params['ignoreQueryParameters'] = ignore_query_parameters
         if regex_on_full_url is not None:
             crawl_params['regexOnFullURL'] = regex_on_full_url
+        if delay is not None:
+            crawl_params['delay'] = delay
 
         # Add any additional kwargs
         crawl_params.update(kwargs)
@@ -3348,6 +3368,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
         deduplicate_similar_urls: Optional[bool] = None,
         ignore_query_parameters: Optional[bool] = None,
         regex_on_full_url: Optional[bool] = None,
+        delay: Optional[int] = None,
         poll_interval: Optional[int] = 2,
         idempotency_key: Optional[str] = None,
         **kwargs
@@ -3412,6 +3433,8 @@ class AsyncFirecrawlApp(FirecrawlApp):
             crawl_params['ignoreQueryParameters'] = ignore_query_parameters
         if regex_on_full_url is not None:
             crawl_params['regexOnFullURL'] = regex_on_full_url
+        if delay is not None:
+            crawl_params['delay'] = delay
 
         # Add any additional kwargs
         crawl_params.update(kwargs)
@@ -3986,6 +4009,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
             url,
             max_urls=max_urls,
             show_full_text=show_full_text,
+            cache=cache,
             experimental_stream=experimental_stream
         )
         if not response.get('success') or 'id' not in response:
@@ -4012,6 +4036,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
             *,
             max_urls: Optional[int] = None,
             show_full_text: Optional[bool] = None,
+            cache: Optional[bool] = None,
             experimental_stream: Optional[bool] = None) -> GenerateLLMsTextResponse:
         """
         Initiate an asynchronous LLMs.txt generation job without waiting for completion.
@@ -4020,6 +4045,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
             url (str): Target URL to generate LLMs.txt from
             max_urls (Optional[int]): Maximum URLs to process (default: 10)
             show_full_text (Optional[bool]): Include full text in output (default: False)
+            cache (Optional[bool]): Whether to use cached content if available (default: True)
             experimental_stream (Optional[bool]): Enable experimental streaming
 
         Returns:
@@ -4042,6 +4068,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
         params = GenerateLLMsTextParams(
             maxUrls=max_urls,
             showFullText=show_full_text,
+            cache=cache,
             __experimental_stream=experimental_stream
         )
 

{firecrawl-2.5.3.dist-info → firecrawl-2.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 2.5.3
+Version: 2.6.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai

firecrawl-2.6.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+firecrawl/__init__.py,sha256=bds9ny9yl_8sXYAmfjaVd_32uf8Qm0ZPbZ2V-LGTgGQ,2612
+firecrawl/firecrawl.py,sha256=Y_8gS4vBPQZ_LP8UXdZAOEMEmK0kRv88Jst2dZ3VW8c,190089
+firecrawl/__tests__/e2e_withAuth/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+firecrawl/__tests__/e2e_withAuth/test.py,sha256=-Fq2vPcMo0iQi4dwsUkkCd931ybDaTxMBnZbRfGdDcA,7931
+firecrawl/__tests__/v1/e2e_withAuth/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+firecrawl/__tests__/v1/e2e_withAuth/test.py,sha256=DcCw-cohtnL-t9XPekUtRoQrgg3UCWu8Ikqudf9ory8,19880
+tests/test_change_tracking.py,sha256=_IJ5ShLcoj2fHDBaw-nE4I4lHdmDB617ocK_XMHhXps,4177
+firecrawl-2.6.0.dist-info/LICENSE,sha256=nPCunEDwjRGHlmjvsiDUyIWbkqqyj3Ej84ntnh0g0zA,1084
+firecrawl-2.6.0.dist-info/METADATA,sha256=gOm5xIZTdtTxAIVZbjZFf5ALWIrIOGpYCFqQ9zW4PAU,7165
+firecrawl-2.6.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+firecrawl-2.6.0.dist-info/top_level.txt,sha256=8T3jOaSN5mtLghO-R3MQ8KO290gIX8hmfxQmglBPdLE,16
+firecrawl-2.6.0.dist-info/RECORD,,

{firecrawl-2.5.3.dist-info → firecrawl-2.6.0.dist-info}/top_level.txt

@@ -1,4 +1,2 @@
-build
-dist
 firecrawl
 tests

build/lib/build/lib/build/lib/firecrawl/__init__.py

@@ -1,79 +0,0 @@
-"""
-This is the Firecrawl package.
-
-This package provides a Python SDK for interacting with the Firecrawl API.
-It includes methods to scrape URLs, perform searches, initiate and monitor crawl jobs,
-and check the status of these jobs.
-
-For more information visit https://github.com/firecrawl/
-"""
-
-import logging
-import os
-
-from .firecrawl import FirecrawlApp, AsyncFirecrawlApp, JsonConfig, ScrapeOptions, ChangeTrackingOptions # noqa
-
-__version__ = "2.5.3"
-
-# Define the logger for the Firecrawl project
-logger: logging.Logger = logging.getLogger("firecrawl")
-
-
-def _configure_logger() -> None:
-    """
-    Configure the firecrawl logger for console output.
-
-    The function attaches a handler for console output with a specific format and date
-    format to the firecrawl logger.
-    """
-    try:
-        # Create the formatter
-        formatter = logging.Formatter(
-            "[%(asctime)s - %(name)s:%(lineno)d - %(levelname)s] %(message)s",
-            datefmt="%Y-%m-%d %H:%M:%S",
-        )
-
-        # Create the console handler and set the formatter
-        console_handler = logging.StreamHandler()
-        console_handler.setFormatter(formatter)
-
-        # Add the console handler to the firecrawl logger
-        logger.addHandler(console_handler)
-    except Exception as e:
-        logger.error("Failed to configure logging: %s", e)
-
-
-def setup_logging() -> None:
-    """Set up logging based on the FIRECRAWL_LOGGING_LEVEL environment variable."""
-    # Check if the firecrawl logger already has a handler
-    if logger.hasHandlers():
-        return # To prevent duplicate logging
-
-    # Check if the FIRECRAWL_LOGGING_LEVEL environment variable is set
-    if not (env := os.getenv("FIRECRAWL_LOGGING_LEVEL", "").upper()):
-        # Attach a no-op handler to prevent warnings about no handlers
-        logger.addHandler(logging.NullHandler()) 
-        return
-
-    # Attach the console handler to the firecrawl logger
-    _configure_logger()
-
-    # Set the logging level based on the FIRECRAWL_LOGGING_LEVEL environment variable
-    if env == "DEBUG":
-        logger.setLevel(logging.DEBUG)
-    elif env == "INFO":
-        logger.setLevel(logging.INFO)
-    elif env == "WARNING":
-        logger.setLevel(logging.WARNING)
-    elif env == "ERROR":
-        logger.setLevel(logging.ERROR)
-    elif env == "CRITICAL":
-        logger.setLevel(logging.CRITICAL)
-    else:
-        logger.setLevel(logging.INFO)
-        logger.warning("Unknown logging level: %s, defaulting to INFO", env)
-
-
-# Initialize logging configuration when the module is imported
-setup_logging()
-logger.debug("Debugging logger setup")

build/lib/build/lib/build/lib/firecrawl/__tests__/e2e_withAuth/test.py

@@ -1,170 +0,0 @@
-import importlib.util
-import pytest
-import time
-import os
-from uuid import uuid4
-from dotenv import load_dotenv
-
-load_dotenv()
-
-API_URL = "http://127.0.0.1:3002"
-ABSOLUTE_FIRECRAWL_PATH = "firecrawl/firecrawl.py"
-TEST_API_KEY = os.getenv('TEST_API_KEY')
-
-print(f"ABSOLUTE_FIRECRAWL_PATH: {ABSOLUTE_FIRECRAWL_PATH}")
-
-spec = importlib.util.spec_from_file_location("FirecrawlApp", ABSOLUTE_FIRECRAWL_PATH)
-firecrawl = importlib.util.module_from_spec(spec)
-spec.loader.exec_module(firecrawl)
-FirecrawlApp = firecrawl.FirecrawlApp
-
-def test_no_api_key():
-    with pytest.raises(Exception) as excinfo:
-      invalid_app = FirecrawlApp(api_url=API_URL, version='v0')
-    assert "No API key provided" in str(excinfo.value)
-
-def test_scrape_url_invalid_api_key():
-    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key", version='v0')
-    with pytest.raises(Exception) as excinfo:
-        invalid_app.scrape_url('https://firecrawl.dev')
-    assert "Unexpected error during scrape URL: Status code 401. Unauthorized: Invalid token" in str(excinfo.value)
-
-# def test_blocklisted_url():
-#     blocklisted_url = "https://facebook.com/fake-test"
-#     app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-#     with pytest.raises(Exception) as excinfo:
-#         app.scrape_url(blocklisted_url)
-#     assert "Unexpected error during scrape URL: Status code 403. Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it." in str(excinfo.value)
-
-def test_successful_response_with_valid_preview_token():
-    app = FirecrawlApp(api_url=API_URL, api_key=os.getenv('PREVIEW_TOKEN'), version='v0')
-    response = app.scrape_url('https://roastmywebsite.ai')
-    assert response is not None
-    assert 'content' in response
-    assert "_Roast_" in response['content']
-
-def test_scrape_url_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.scrape_url('https://roastmywebsite.ai')
-    print(response)
-
-    assert response is not None
-    assert 'content' in response
-    assert 'markdown' in response
-    assert 'metadata' in response
-    assert 'html' not in response
-    assert "_Roast_" in response['content']
-
-def test_successful_response_with_valid_api_key_and_include_html():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.scrape_url('https://roastmywebsite.ai', {'pageOptions': {'includeHtml': True}})
-    assert response is not None
-    assert 'content' in response
-    assert 'markdown' in response
-    assert 'html' in response
-    assert 'metadata' in response
-    assert "_Roast_" in response['content']
-    assert "_Roast_" in response['markdown']
-    assert "<h1" in response['html']
-
-def test_successful_response_for_valid_scrape_with_pdf_file():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.scrape_url('https://arxiv.org/pdf/astro-ph/9301001.pdf')
-    assert response is not None
-    assert 'content' in response
-    assert 'metadata' in response
-    assert 'We present spectrophotometric observations of the Broad Line Radio Galaxy' in response['content']
-
-def test_successful_response_for_valid_scrape_with_pdf_file_without_explicit_extension():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.scrape_url('https://arxiv.org/pdf/astro-ph/9301001')
-    time.sleep(6)  # wait for 6 seconds
-    assert response is not None
-    assert 'content' in response
-    assert 'metadata' in response
-    assert 'We present spectrophotometric observations of the Broad Line Radio Galaxy' in response['content']
-
-def test_crawl_url_invalid_api_key():
-    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key", version='v0')
-    with pytest.raises(Exception) as excinfo:
-        invalid_app.crawl_url('https://firecrawl.dev')
-    assert "Unexpected error during start crawl job: Status code 401. Unauthorized: Invalid token" in str(excinfo.value)
-
-# def test_should_return_error_for_blocklisted_url():
-#     app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-#     blocklisted_url = "https://twitter.com/fake-test"
-#     with pytest.raises(Exception) as excinfo:
-#         app.crawl_url(blocklisted_url)
-#     assert "Unexpected error during start crawl job: Status code 403. Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it." in str(excinfo.value)
-
-def test_crawl_url_wait_for_completion_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.crawl_url('https://roastmywebsite.ai', {'crawlerOptions': {'excludes': ['blog/*']}}, True)
-    assert response is not None
-    assert len(response) > 0
-    assert 'content' in response[0]
-    assert "_Roast_" in response[0]['content']
-
-def test_crawl_url_with_idempotency_key_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    uniqueIdempotencyKey = str(uuid4())
-    response = app.crawl_url('https://roastmywebsite.ai', {'crawlerOptions': {'excludes': ['blog/*']}}, True, 2, uniqueIdempotencyKey)
-    assert response is not None
-    assert len(response) > 0
-    assert 'content' in response[0]
-    assert "_Roast_" in response[0]['content']
-
-    with pytest.raises(Exception) as excinfo:
-        app.crawl_url('https://firecrawl.dev', {'crawlerOptions': {'excludes': ['blog/*']}}, True, 2, uniqueIdempotencyKey)
-    assert "Conflict: Failed to start crawl job due to a conflict. Idempotency key already used" in str(excinfo.value) 
-
-def test_check_crawl_status_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.crawl_url('https://firecrawl.dev', {'crawlerOptions': {'excludes': ['blog/*']}}, False)
-    assert response is not None
-    assert 'jobId' in response
-    
-    time.sleep(30)  # wait for 30 seconds
-    status_response = app.check_crawl_status(response['jobId'])
-    assert status_response is not None
-    assert 'status' in status_response
-    assert status_response['status'] == 'completed'
-    assert 'data' in status_response
-    assert len(status_response['data']) > 0
-
-def test_search_e2e():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.search("test query")
-    assert response is not None
-    assert 'content' in response[0]
-    assert len(response) > 2
-
-def test_search_invalid_api_key():
-    invalid_app = FirecrawlApp(api_url=API_URL, api_key="invalid_api_key", version='v0')
-    with pytest.raises(Exception) as excinfo:
-        invalid_app.search("test query")
-    assert "Unexpected error during search: Status code 401. Unauthorized: Invalid token" in str(excinfo.value)
-
-def test_llm_extraction():
-    app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY, version='v0')
-    response = app.scrape_url("https://firecrawl.dev", {
-        'extractorOptions': {
-            'mode': 'llm-extraction',
-            'extractionPrompt': "Based on the information on the page, find what the company's mission is and whether it supports SSO, and whether it is open source",
-            'extractionSchema': {
-                'type': 'object',
-                'properties': {
-                    'company_mission': {'type': 'string'},
-                    'supports_sso': {'type': 'boolean'},
-                    'is_open_source': {'type': 'boolean'}
-                },
-                'required': ['company_mission', 'supports_sso', 'is_open_source']
-            }
-        }
-    })
-    assert response is not None
-    assert 'llm_extraction' in response
-    llm_extraction = response['llm_extraction']
-    assert 'company_mission' in llm_extraction
-    assert isinstance(llm_extraction['supports_sso'], bool)
-    assert isinstance(llm_extraction['is_open_source'], bool)