{ "openapi": "3.0.1", "info": { "title": "OSHA Injury Data Scraper - US Employer & Workplace-Safety Leads", "description": "Scrape OSHA ITA Form 300A injury data: every US establishment that filed an annual injury summary — name, EIN, address, NAICS, employee count, injury counts, TRIR/DART rates & lead score. Filter by state, NAICS, size & injury rate. Firmographic B2B leads + monitoring, no browser.", "version": "0.1", "x-build-id": "ZKeuuc5rRIgq7VS7I" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~osha-injury-data-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-osha-injury-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~osha-injury-data-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-osha-injury-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~osha-injury-data-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-osha-injury-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "states": { "title": "States", "type": "array", "description": "Filter to one or more US states by 2-letter code (e.g. `TX`, `CA`, `OH`). Leave empty to scan the whole national file.", "items": { "type": "string" } }, "cities": { "title": "Cities", "type": "array", "description": "Filter by city name (case-insensitive, substring match).", "items": { "type": "string" } }, "zipCodes": { "title": "ZIP codes", "type": "array", "description": "Filter by ZIP code. A 5-digit value matches exactly; a shorter prefix (e.g. `770`) matches a region.", "items": { "type": "string" } }, "naicsCodes": { "title": "NAICS codes / prefixes", "type": "array", "description": "Filter by NAICS industry code. A prefix matches a whole branch — e.g. `23` = all construction, `2382` = building-equipment contractors, `311` = food manufacturing.", "items": { "type": "string" } }, "naicsSectors": { "title": "NAICS sectors (2-digit)", "type": "array", "description": "Quick filter by top-level NAICS sector. Examples: `23` Construction, `31`/`32`/`33` Manufacturing, `48`/`49` Transportation & Warehousing, `62` Health Care, `21` Mining/Oil & Gas, `22` Utilities.", "items": { "type": "string" } }, "industryQuery": { "title": "Industry contains", "type": "string", "description": "Free-text filter on the industry description (e.g. `roofing`, `nursing`, `warehousing`, `meat`)." }, "companyNameQuery": { "title": "Establishment / company name contains", "type": "string", "description": "Filter to establishments whose establishment name or company name contains this text (case-insensitive)." }, "establishmentTypes": { "title": "Establishment type", "type": "array", "description": "Keep only private, state-government or local-government establishments.", "items": { "type": "string", "enum": [ "private", "stateGovernment", "localGovernment" ], "enumTitles": [ "Private industry", "State government", "Local government" ] } }, "minEmployees": { "title": "Minimum employees", "minimum": 0, "type": "integer", "description": "Keep only establishments with at least this many annual-average employees. Great for targeting larger employers with bigger budgets." }, "maxEmployees": { "title": "Maximum employees", "minimum": 0, "type": "integer", "description": "Keep only establishments with at most this many annual-average employees." }, "minRecordableCases": { "title": "Minimum recordable cases", "minimum": 0, "type": "integer", "description": "Keep only establishments reporting at least this many total OSHA-recordable cases for the year." }, "minTrir": { "title": "Minimum TRIR", "minimum": 0, "type": "integer", "description": "Keep only establishments with a Total Recordable Incident Rate at or above this value (cases per 100 full-time workers). The US private-industry average is ~2.7 — set 4–8 to find high-injury sites." }, "hasInjuriesOnly": { "title": "Only establishments with recordable injuries", "type": "boolean", "description": "Keep only establishments that reported at least one recordable injury or illness.", "default": false }, "hasFatalitiesOnly": { "title": "Only establishments with a fatality", "type": "boolean", "description": "Keep only establishments that reported one or more work-related deaths.", "default": false }, "hasLostTimeOnly": { "title": "Only establishments with lost-time cases", "type": "boolean", "description": "Keep only establishments with days-away or job-transfer/restriction (DART) cases.", "default": false }, "withEinOnly": { "title": "Only establishments with an EIN", "type": "boolean", "description": "Keep only records that include the employer EIN (useful for B2B record matching).", "default": false }, "minLeadScore": { "title": "Minimum lead score", "minimum": 0, "maximum": 100, "type": "integer", "description": "Keep only establishments with a lead score (0–100) at or above this value." }, "yearFilingFor": { "title": "Filing year", "type": "integer", "description": "Which reporting year to scrape (the year the Form 300A summarizes). Leave empty for the latest year available. Years 2016–present are published by OSHA." }, "sortBy": { "title": "Sort by", "enum": [ "leadScore", "employeesHigh", "trirHigh", "recordableCasesHigh", "lostWorkdaysHigh", "fatalities", "name", "none" ], "type": "string", "description": "Order of returned records (the cap is applied after sorting).", "default": "leadScore" }, "maxResults": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Maximum number of establishment records to return. The full national file holds roughly 350,000+ establishments per year.", "default": 1000 }, "deduplicateResults": { "title": "Deduplicate", "type": "boolean", "description": "Drop duplicate establishments (by OSHA establishment ID) within a run, keeping the first seen.", "default": true }, "monitorMode": { "title": "Monitor mode (only new establishments)", "type": "boolean", "description": "Remember establishments seen in previous runs (per Monitor key) and only output NEW ones. Ideal with Apify Schedules for a fresh-leads feed as more employers file each year. Works independently of the platform scheduler.", "default": false }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Names the saved monitor state, so different filter sets keep separate memories. Use a distinct key per saved search.", "default": "default" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. The OSHA open-data files are public and download fine without a proxy (the default). If a run is blocked, enable Apify Proxy — the actor automatically escalates to US residential when needed.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }