fix: fix firecrawl url concat (#30008)

This commit is contained in:
wangxiaolei
2025-12-24 09:40:32 +08:00
committed by GitHub
parent 4d48791f3c
commit 111a39b549
4 changed files with 79 additions and 29 deletions

View File

@ -25,7 +25,7 @@ class FirecrawlApp:
}
if params:
json_data.update(params)
response = self._post_request(f"{self.base_url}/v2/scrape", json_data, headers)
response = self._post_request(self._build_url("v2/scrape"), json_data, headers)
if response.status_code == 200:
response_data = response.json()
data = response_data["data"]
@ -42,7 +42,7 @@ class FirecrawlApp:
json_data = {"url": url}
if params:
json_data.update(params)
response = self._post_request(f"{self.base_url}/v2/crawl", json_data, headers)
response = self._post_request(self._build_url("v2/crawl"), json_data, headers)
if response.status_code == 200:
# There's also another two fields in the response: "success" (bool) and "url" (str)
job_id = response.json().get("id")
@ -58,7 +58,7 @@ class FirecrawlApp:
if params:
# Pass through provided params, including optional "sitemap": "only" | "include" | "skip"
json_data.update(params)
response = self._post_request(f"{self.base_url}/v2/map", json_data, headers)
response = self._post_request(self._build_url("v2/map"), json_data, headers)
if response.status_code == 200:
return cast(dict[str, Any], response.json())
elif response.status_code in {402, 409, 500, 429, 408}:
@ -69,7 +69,7 @@ class FirecrawlApp:
def check_crawl_status(self, job_id) -> dict[str, Any]:
headers = self._prepare_headers()
response = self._get_request(f"{self.base_url}/v2/crawl/{job_id}", headers)
response = self._get_request(self._build_url(f"v2/crawl/{job_id}"), headers)
if response.status_code == 200:
crawl_status_response = response.json()
if crawl_status_response.get("status") == "completed":
@ -120,6 +120,10 @@ class FirecrawlApp:
def _prepare_headers(self) -> dict[str, Any]:
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, retries=3, backoff_factor=0.5) -> httpx.Response:
for attempt in range(retries):
response = httpx.post(url, headers=headers, json=data)
@ -139,7 +143,11 @@ class FirecrawlApp:
return response
def _handle_error(self, response, action):
error_message = response.json().get("error", "Unknown error occurred")
try:
payload = response.json()
error_message = payload.get("error") or payload.get("message") or response.text or "Unknown error occurred"
except json.JSONDecodeError:
error_message = response.text or "Unknown error occurred"
raise Exception(f"Failed to {action}. Status code: {response.status_code}. Error: {error_message}") # type: ignore[return]
def search(self, query: str, params: dict[str, Any] | None = None) -> dict[str, Any]:
@ -160,7 +168,7 @@ class FirecrawlApp:
}
if params:
json_data.update(params)
response = self._post_request(f"{self.base_url}/v2/search", json_data, headers)
response = self._post_request(self._build_url("v2/search"), json_data, headers)
if response.status_code == 200:
response_data = response.json()
if not response_data.get("success"):