AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-14 04:15:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Nick: fixed the sdks

Browse Source
This commit is contained in:
Nicolas 2025-01-07 17:20:49 -03:00
parent dd14744850
commit 9ec08d7020
3 changed files with 50 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
apps/api/src/controllers/v1/extract.ts
View File

@ -69,7 +69,7 @@ export async function extractController(
});
}
return res.status(202).json({
return res.status(200).json({
success: true,
id: extractId,
urlTrace: [],

26
apps/js-sdk/firecrawl/src/index.ts
View File

@ -887,18 +887,32 @@ export default class FirecrawlApp {
{ ...jsonData, schema: jsonSchema },
headers
);
if (response.status === 200) {
const responseData = response.data as ExtractResponse<T>;
if (responseData.success) {
const jobId = response.data.id;
let extractStatus;
do {
const statusResponse: AxiosResponse = await this.getRequest(
`${this.apiUrl}/v1/extract/${jobId}`,
headers
);
extractStatus = statusResponse.data;
if (extractStatus.status === "completed") {
if (extractStatus.success) {
return {
success: true,
data: responseData.data,
warning: responseData.warning,
error: responseData.error
data: extractStatus.data,
warning: extractStatus.warning,
error: extractStatus.error
};
} else {
throw new FirecrawlError(`Failed to scrape URL. Error: ${responseData.error}`, response.status);
throw new FirecrawlError(`Failed to extract data. Error: ${extractStatus.error}`, statusResponse.status);
}
} else if (extractStatus.status === "failed" || extractStatus.status === "cancelled") {
throw new FirecrawlError(`Extract job ${extractStatus.status}. Error: ${extractStatus.error}`, statusResponse.status);
}
await new Promise(resolve => setTimeout(resolve, 1000)); // Polling interval
} while (extractStatus.status !== "completed");
} else {
this.handleError(response, "extract");
}

25
apps/python-sdk/firecrawl/firecrawl.py
View File

@ -542,6 +542,7 @@ class FirecrawlApp:
}
try:
# Send the initial extract request
response = self._post_request(
f'{self.api_url}/v1/extract',
request_data,
@ -550,7 +551,29 @@ 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: