{ "openapi": "3.0.1", "info": { "title": "Thumbtack Scraper - Local Service Pros Market Data", "description": "Scrape Thumbtack service pros by category and city: ratings, review counts, hires, years in business, Top Pro status. Business-level data, no personal contact details.", "version": "1.0", "x-build-id": "pRzN0Gpic2LBZCDA7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maydit~thumbtack-local-pros-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maydit-thumbtack-local-pros-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maydit~thumbtack-local-pros-scraper/runs": { "post": { "operationId": "runs-sync-maydit-thumbtack-local-pros-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maydit~thumbtack-local-pros-scraper/run-sync": { "post": { "operationId": "run-sync-maydit-thumbtack-local-pros-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "categories": { "title": "Service categories", "type": "array", "description": "Thumbtack service categories to scrape, one per line, written the way Thumbtack writes them (for example \"House Cleaning\", \"Plumbing\", \"Handyman\", \"Movers\"). Names are converted to Thumbtack's URL wording automatically. If a category returns HTTP 404 it does not exist under that name - open the category page on thumbtack.com and copy the wording from its URL.", "default": [ "House Cleaning" ], "items": { "type": "string" } }, "locations": { "title": "Locations (City, ST)", "type": "array", "description": "US markets to scrape, one per line, in \"City, ST\" format (for example \"Houston, TX\", \"Los Angeles, CA\"). Full state names also work. Every category is scraped in every location, so 3 categories and 4 cities means 12 browse pages.", "default": [ "Houston, TX" ], "items": { "type": "string" } }, "maxItems": { "title": "Maximum pros to return", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many pro records. Thumbtack's public browse page lists roughly 4-10 pros per category and city, so to collect more than that, add more categories and locations (or turn on nearby areas) rather than raising this number alone.", "default": 50 }, "maxRunSeconds": { "title": "Maximum run time (seconds)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Wall-clock budget for the crawl. When it runs out the Actor stops cleanly and keeps every row collected so far instead of failing. Raise this for large category and location lists.", "default": 240 }, "includeNearbyAreas": { "title": "Also scrape nearby areas", "type": "boolean", "description": "Follow Thumbtack's own \"In other nearby areas\" links to neighbouring city and neighbourhood browse pages for the same category. Nearby pages mostly list the SAME pros (in a measured Los Angeles run, 6 pages listed 47 cards but only 13 distinct businesses), so expect many more requests for a modest number of extra rows. Adding more separate metros to Locations grows a dataset faster. Leave off for a quick sample.", "default": false }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 250, "maximum": 10000, "type": "integer", "description": "Politeness delay between page requests. Requests are always serial, never parallel. Lower values are faster but less polite; the default is a deliberately unhurried pace.", "default": 1200 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }