dify/api/services/auth/firecrawl/firecrawl.py

52 lines
1.9 KiB
Python

import json
import httpx
from services.auth.api_key_auth_base import ApiKeyAuthBase
class FirecrawlAuth(ApiKeyAuthBase):
def __init__(self, credentials: dict):
super().__init__(credentials)
auth_type = credentials.get("auth_type")
if auth_type != "bearer":
raise ValueError("Invalid auth type, Firecrawl auth type must be Bearer")
self.api_key = credentials.get("config", {}).get("api_key", None)
self.base_url = credentials.get("config", {}).get("base_url", "https://api.firecrawl.dev")
if not self.api_key:
raise ValueError("No API key provided")
def validate_credentials(self):
headers = self._prepare_headers()
options = {
"url": "https://example.com",
"includePaths": [],
"excludePaths": [],
"limit": 1,
"scrapeOptions": {"onlyMainContent": True},
}
response = self._post_request(self._build_url("v1/crawl"), options, headers)
if response.status_code == 200:
return True
else:
self._handle_error(response)
def _prepare_headers(self):
return {"Content-Type": "application/json", "Authorization": f"Bearer {self.api_key}"}
def _build_url(self, path: str) -> str:
# ensure exactly one slash between base and path, regardless of user-provided base_url
return f"{self.base_url.rstrip('/')}/{path.lstrip('/')}"
def _post_request(self, url, data, headers):
return httpx.post(url, headers=headers, json=data)
def _handle_error(self, response):
try:
payload = response.json()
except json.JSONDecodeError:
payload = {}
error_message = payload.get("error") or payload.get("message") or (response.text or "Unknown error occurred")
raise Exception(f"Failed to authorize. Status code: {response.status_code}. Error: {error_message}")