{ "openapi": "3.0.1", "info": { "title": "ThomasNet US B2B Supplier & Manufacturer Scraper", "description": "Scrape verified US & North American manufacturer and supplier profiles from ThomasNet: capabilities, certifications (ISO, ITAR, AS9100), revenue band, employee count, direct website, and key contacts.", "version": "0.1", "x-build-id": "Hiys2A4y6eF880r5o" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xtracto~thomasnet-suppliers/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xtracto-thomasnet-suppliers", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/xtracto~thomasnet-suppliers/runs": { "post": { "operationId": "runs-sync-xtracto-thomasnet-suppliers", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/xtracto~thomasnet-suppliers/run-sync": { "post": { "operationId": "run-sync-xtracto-thomasnet-suppliers", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "searchTerms" ], "properties": { "searchTerms": { "title": "Search terms (keywords or categories)", "minItems": 1, "uniqueItems": true, "type": "array", "description": "One or more keywords/categories to search ThomasNet for (e.g. 'cnc machining', 'injection molding', 'industrial valves'). Each term returns up to 25 of the most relevant US/North-American suppliers. Use several specific terms for broad coverage.", "items": { "type": "string" } }, "maxSuppliersPerTerm": { "title": "Max suppliers per term", "minimum": 1, "maximum": 250, "type": "integer", "description": "Cap on suppliers collected per search term. ThomasNet server-renders at most 25 per term (deeper pages require browser-side JS), so values above 25 have no effect unless 'Max pages per term' is raised.", "default": 25 }, "maxPagesPerTerm": { "title": "Max pages per term (advanced)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pagination safety cap. Left at 1 by default because ThomasNet only server-renders page 1 (25 results); pages 2+ return empty over HTTP. The actor stops automatically on the first empty page.", "default": 1 }, "enrichProfiles": { "title": "Enrich with profile pages", "type": "boolean", "description": "Fetch each supplier's profile page for richer data (key personnel, certification counts by type, company-authored description, geo-coordinates). Slower and uses more requests/proxy traffic.", "default": false }, "enrichmentConcurrency": { "title": "Enrichment concurrency", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many profile pages to fetch in parallel when enrichment is on. Keep low (2-4) to stay under DataDome rate limits.", "default": 3 }, "cacheBuster": { "title": "Cache buster", "type": "boolean", "description": "Append a unique query param per request to defeat ThomasNet's flaky edge cache (which can occasionally return a previous term's results). Recommended on.", "default": true }, "logLevel": { "title": "Log level", "enum": [ "INFO", "DEBUG" ], "type": "string", "description": "Set DEBUG to surface more detail in the run log while troubleshooting.", "default": "INFO" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential proxy is strongly recommended for reliable results at scale. Light runs may work without a proxy.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }