firecrawl-py 0.0.1__py3-none-any.whl

firecrawl_py-0.0.1.dist-info/METADATA

@@ -0,0 +1,9 @@
+Metadata-Version: 2.1
+Name: firecrawl-py
+Version: 0.0.1
+Summary: Python SDK for Firecrawl API
+Home-page: https://github.com/mendableai/firecrawl-py
+Author: Eric Ciarla
+Author-email: nick@mendable.ai
+Requires-Dist: requests
+

firecrawl_py-0.0.1.dist-info/RECORD

@@ -0,0 +1,6 @@
+mendable/__init__.py,sha256=Z0tfQTnh-Rr7V-_3yjYlgxt3cREhhqV8s1LVXSmNCuo,31
+mendable/firecrawl.py,sha256=ReCvqTWgxHEtgYakT8nOkWYv1KsEiLzkSSQ9-3HyZc8,3362
+firecrawl_py-0.0.1.dist-info/METADATA,sha256=qGKynQcGLplfRP6XN5IUweLZp9E4N1M7cTx0edBef38,224
+firecrawl_py-0.0.1.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+firecrawl_py-0.0.1.dist-info/top_level.txt,sha256=HV-vVOHTsAD2b_EZNXwuUyiCCD4Ex74C2SPkTf1h2eA,9
+firecrawl_py-0.0.1.dist-info/RECORD,,

firecrawl_py-0.0.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.38.4)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

firecrawl_py-0.0.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+mendable

mendable/__init__.py

@@ -0,0 +1 @@
+from .firecrawl import ChatApp

mendable/firecrawl.py

@@ -0,0 +1,78 @@
+import os
+import requests
+
+class FireCrawl:
+    def __init__(self, api_key=None):
+        self.api_key = api_key or os.getenv('FIRECRAWL_API_KEY')
+        if self.api_key is None:
+            raise ValueError('No API key provided')
+    
+    def scrape_url(self, url, params):
+        headers = {
+            'Content-Type': 'application/json',
+            'Authorization': f'Bearer {self.api_key}'
+        }
+        response = requests.post(
+            'https://api.firecrawl.dev/v0/scrape',
+            headers=headers,
+            json={'url': url, **params}
+        )
+        if response.status_code == 200:
+            return response.json()
+        elif response.status_code in [402, 409, 500]:
+            error_message = response.json().get('error', 'Unknown error occurred')
+            raise Exception(f'Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}')
+        else:
+            raise Exception(f'Failed to scrape URL. Status code: {response.status_code}')
+
+    def crawl_url(self, url, params):
+        import time
+        headers = self._prepare_headers()
+        response = self._post_request('https://api.firecrawl.dev/v0/crawl', {'url': url, **params}, headers)
+        if response.status_code == 200:
+            job_id = response.json().get('jobId')
+            return self._monitor_job_status(job_id, headers)
+        else:
+            self._handle_error(response, 'start crawl job')
+
+    def check_crawl_status(self, job_id):
+        headers = self._prepare_headers()
+        response = self._get_request(f'https://api.firecrawl.dev/v0/crawl/status/{job_id}', headers)
+        if response.status_code == 200:
+            return response.json()
+        else:
+            self._handle_error(response, 'check crawl status')
+
+    def _prepare_headers(self):
+        return {
+            'Content-Type': 'application/json',
+            'Authorization': f'Bearer {self.api_key}'
+        }
+
+    def _post_request(self, url, data, headers):
+        return requests.post(url, headers=headers, json=data)
+
+    def _get_request(self, url, headers):
+        return requests.get(url, headers=headers)
+
+    def _monitor_job_status(self, job_id, headers):
+        import time
+        while True:
+            status_response = self._get_request(f'https://api.firecrawl.dev/v0/crawl/status/{job_id}', headers)
+            if status_response.status_code == 200:
+                status_data = status_response.json()
+                if status_data['status'] == 'completed':
+                    return status_data
+                elif status_data['status'] in ['active', 'paused', 'pending', 'queued']:
+                    time.sleep(2)  # Wait for 2 seconds before checking again
+                else:
+                    raise Exception(f'Crawl job failed or was stopped. Status: {status_data["status"]}')
+            else:
+                self._handle_error(status_response, 'check crawl status')
+
+    def _handle_error(self, response, action):
+        if response.status_code in [402, 409, 500]:
+            error_message = response.json().get('error', 'Unknown error occurred')
+            raise Exception(f'Failed to {action}. Status code: {response.status_code}. Error: {error_message}')
+        else:
+            raise Exception(f'Unexpected error occurred while trying to {action}. Status code: {response.status_code}')