d25d482dc2
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
105 lines
2.9 KiB
TypeScript
105 lines
2.9 KiB
TypeScript
import type {
|
|
BrightDataScrapeDatasetParams,
|
|
BrightDataScrapeDatasetResponse,
|
|
} from '@/tools/brightdata/types'
|
|
import type { ToolConfig } from '@/tools/types'
|
|
|
|
export const brightDataScrapeDatasetTool: ToolConfig<
|
|
BrightDataScrapeDatasetParams,
|
|
BrightDataScrapeDatasetResponse
|
|
> = {
|
|
id: 'brightdata_scrape_dataset',
|
|
name: 'Bright Data Scrape Dataset',
|
|
description:
|
|
'Trigger a Bright Data pre-built scraper to extract structured data from URLs. Supports 660+ scrapers for platforms like Amazon, LinkedIn, Instagram, and more.',
|
|
version: '1.0.0',
|
|
|
|
params: {
|
|
apiKey: {
|
|
type: 'string',
|
|
required: true,
|
|
visibility: 'user-only',
|
|
description: 'Bright Data API token',
|
|
},
|
|
datasetId: {
|
|
type: 'string',
|
|
required: true,
|
|
visibility: 'user-or-llm',
|
|
description:
|
|
'Dataset scraper ID from your Bright Data dashboard (e.g., "gd_l1viktl72bvl7bjuj0")',
|
|
},
|
|
urls: {
|
|
type: 'string',
|
|
required: true,
|
|
visibility: 'user-or-llm',
|
|
description:
|
|
'JSON array of URL objects to scrape (e.g., [{"url": "https://example.com/product"}])',
|
|
},
|
|
format: {
|
|
type: 'string',
|
|
required: false,
|
|
visibility: 'user-or-llm',
|
|
description: 'Output format: "json" or "csv". Defaults to "json"',
|
|
},
|
|
includeErrors: {
|
|
type: 'boolean',
|
|
required: false,
|
|
visibility: 'user-or-llm',
|
|
description: 'Whether to include a per-input error report in the results',
|
|
},
|
|
},
|
|
|
|
request: {
|
|
method: 'POST',
|
|
url: (params) => {
|
|
const queryParams = new URLSearchParams()
|
|
queryParams.set('dataset_id', params.datasetId.trim())
|
|
queryParams.set('format', params.format || 'json')
|
|
if (params.includeErrors) queryParams.set('include_errors', 'true')
|
|
return `https://api.brightdata.com/datasets/v3/trigger?${queryParams.toString()}`
|
|
},
|
|
headers: (params) => ({
|
|
'Content-Type': 'application/json',
|
|
Authorization: `Bearer ${params.apiKey}`,
|
|
}),
|
|
body: (params) => {
|
|
if (typeof params.urls === 'string') {
|
|
try {
|
|
return JSON.parse(params.urls)
|
|
} catch {
|
|
return [{ url: params.urls }]
|
|
}
|
|
}
|
|
return params.urls
|
|
},
|
|
},
|
|
|
|
transformResponse: async (response: Response) => {
|
|
if (!response.ok) {
|
|
const errorText = await response.text()
|
|
throw new Error(errorText || `Dataset trigger failed with status ${response.status}`)
|
|
}
|
|
|
|
const data = await response.json()
|
|
|
|
return {
|
|
success: true,
|
|
output: {
|
|
snapshotId: data.snapshot_id ?? data.snapshotId ?? '',
|
|
status: data.status ?? 'triggered',
|
|
},
|
|
}
|
|
},
|
|
|
|
outputs: {
|
|
snapshotId: {
|
|
type: 'string',
|
|
description: 'The snapshot ID to retrieve results later',
|
|
},
|
|
status: {
|
|
type: 'string',
|
|
description: 'Status of the scraping job (e.g., "triggered", "running")',
|
|
},
|
|
},
|
|
}
|