firecrawl 1.8.0__tar.gz → 1.9.0__tar.gz

{firecrawl-1.8.0 → firecrawl-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 1.8.0
+Version: 1.9.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai

{firecrawl-1.8.0 → firecrawl-1.9.0}/firecrawl/__init__.py

@@ -13,7 +13,7 @@ import os
 
 from .firecrawl import FirecrawlApp # noqa
 
-__version__ = "1.8.0"
+__version__ = "1.9.0"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

{firecrawl-1.8.0 → firecrawl-1.9.0}/firecrawl/firecrawl.py

@@ -250,6 +250,8 @@ class FirecrawlApp:
                 if 'data' in status_data:
                     data = status_data['data']
                     while 'next' in status_data:
+                        if len(status_data['data']) == 0:
+                            break
                         next_url = status_data.get('next')
                         if not next_url:
                             logger.warning("Expected 'next' URL is missing.")
@@ -266,17 +268,25 @@ class FirecrawlApp:
                             logger.error(f"Error during pagination request: {e}")
                             break
                     status_data['data'] = data
-                    
-            return {
-                'success': True,
+
+            response = {
                 'status': status_data.get('status'),
                 'total': status_data.get('total'),
                 'completed': status_data.get('completed'),
                 'creditsUsed': status_data.get('creditsUsed'),
                 'expiresAt': status_data.get('expiresAt'),
-                'data': status_data.get('data'),
-                'error': status_data.get('error'),
-                'next': status_data.get('next', None)
+                'data': status_data.get('data')
+            }
+
+            if 'error' in status_data:
+                response['error'] = status_data['error']
+
+            if 'next' in status_data:
+                response['next'] = status_data['next']
+
+            return {
+                'success': False if 'error' in status_data else True,
+                **response
             }
         else:
             self._handle_error(response, 'check crawl status')
@@ -459,6 +469,8 @@ class FirecrawlApp:
                 if 'data' in status_data:
                     data = status_data['data']
                     while 'next' in status_data:
+                        if len(status_data['data']) == 0:
+                            break
                         next_url = status_data.get('next')
                         if not next_url:
                             logger.warning("Expected 'next' URL is missing.")
@@ -476,16 +488,24 @@ class FirecrawlApp:
                             break
                     status_data['data'] = data
 
-            return {
-                'success': True,
+            response = {
                 'status': status_data.get('status'),
                 'total': status_data.get('total'),
                 'completed': status_data.get('completed'),
                 'creditsUsed': status_data.get('creditsUsed'),
                 'expiresAt': status_data.get('expiresAt'),
-                'data': status_data.get('data'),
-                'error': status_data.get('error'),
-                'next': status_data.get('next', None)
+                'data': status_data.get('data')
+            }
+
+            if 'error' in status_data:
+                response['error'] = status_data['error']
+
+            if 'next' in status_data:
+                response['next'] = status_data['next']
+
+            return {
+                'success': False if 'error' in status_data else True,
+                **response
             }
         else:
             self._handle_error(response, 'check batch scrape status')
@@ -518,10 +538,12 @@ class FirecrawlApp:
         request_data = {
             **jsonData,
             'allowExternalLinks': params.get('allow_external_links', False),
-            'schema': schema
+            'schema': schema,
+            'origin': 'api-sdk'
         }
 
         try:
+            # Send the initial extract request
             response = self._post_request(
                 f'{self.api_url}/v1/extract',
                 request_data,
@@ -530,7 +552,29 @@ class FirecrawlApp:
             if response.status_code == 200:
                 data = response.json()
                 if data['success']:
-                    return data
+                    job_id = data.get('id')
+                    if not job_id:
+                        raise Exception('Job ID not returned from extract request.')
+
+                    # Poll for the extract status
+                    while True:
+                        status_response = self._get_request(
+                            f'{self.api_url}/v1/extract/{job_id}',
+                            headers
+                        )
+                        if status_response.status_code == 200:
+                            status_data = status_response.json()
+                            if status_data['status'] == 'completed':
+                                if status_data['success']:
+                                    return status_data
+                                else:
+                                    raise Exception(f'Failed to extract. Error: {status_data["error"]}')
+                            elif status_data['status'] in ['failed', 'cancelled']:
+                                raise Exception(f'Extract job {status_data["status"]}. Error: {status_data["error"]}')
+                        else:
+                            self._handle_error(status_response, "extract-status")
+
+                        time.sleep(2)  # Polling interval
                 else:
                     raise Exception(f'Failed to extract. Error: {data["error"]}')
             else:
@@ -539,6 +583,69 @@ class FirecrawlApp:
             raise ValueError(str(e), 500)
 
         return {'success': False, 'error': "Internal server error."}
+    
+    def get_extract_status(self, job_id: str) -> Dict[str, Any]:
+        """
+        Retrieve the status of an extract job.
+
+        Args:
+            job_id (str): The ID of the extract job.
+
+        Returns:
+            Dict[str, Any]: The status of the extract job.
+
+        Raises:
+            ValueError: If there is an error retrieving the status.
+        """
+        headers = self._prepare_headers()
+        try:
+            response = self._get_request(f'{self.api_url}/v1/extract/{job_id}', headers)
+            if response.status_code == 200:
+                return response.json()
+            else:
+                self._handle_error(response, "get extract status")
+        except Exception as e:
+            raise ValueError(str(e), 500)
+
+    def async_extract(self, urls: List[str], params: Optional[Dict[str, Any]] = None, idempotency_key: Optional[str] = None) -> Dict[str, Any]:
+        """
+        Initiate an asynchronous extract job.
+
+        Args:
+            urls (List[str]): The URLs to extract data from.
+            params (Optional[Dict[str, Any]]): Additional parameters for the extract request.
+            idempotency_key (Optional[str]): A unique key to ensure idempotency of requests.
+
+        Returns:
+            Dict[str, Any]: The response from the extract operation.
+
+        Raises:
+            ValueError: If there is an error initiating the extract job.
+        """
+        headers = self._prepare_headers(idempotency_key)
+        
+        schema = params.get('schema') if params else None
+        if schema:
+            if hasattr(schema, 'model_json_schema'):
+                # Convert Pydantic model to JSON schema
+                schema = schema.model_json_schema()
+            # Otherwise assume it's already a JSON schema dict
+
+        jsonData = {'urls': urls, **(params or {})}
+        request_data = {
+            **jsonData,
+            'allowExternalLinks': params.get('allow_external_links', False) if params else False,
+            'schema': schema
+        }
+
+        try:
+            response = self._post_request(f'{self.api_url}/v1/extract', request_data, headers)
+            if response.status_code == 200:
+                return response.json()
+            else:
+                self._handle_error(response, "async extract")
+        except Exception as e:
+            raise ValueError(str(e), 500)
 
     def _prepare_headers(self, idempotency_key: Optional[str] = None) -> Dict[str, str]:
         """
@@ -669,6 +776,8 @@ class FirecrawlApp:
                     if 'data' in status_data:
                         data = status_data['data']
                         while 'next' in status_data:
+                          if len(status_data['data']) == 0:
+                              break
                           status_response = self._get_request(status_data['next'], headers)
                           status_data = status_response.json()
                           data.extend(status_data.get('data', []))

{firecrawl-1.8.0 → firecrawl-1.9.0}/firecrawl.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 1.8.0
+Version: 1.9.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai