{ "openapi": "3.0.1", "info": { "title": "H-1B LCA Disclosure Data Scraper", "description": "Scrape US Department of Labor (DOL) H-1B / H-1B1 / E-3 Labor Condition Application (LCA) disclosure data. Search by employer, job title, SOC code, wage, worksite state, visa class, and more, or look up exact case numbers.", "version": "1.0", "x-build-id": "3CIhkX2GN7LivKs6a" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~h1b-lca-disclosure-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-h1b-lca-disclosure-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~h1b-lca-disclosure-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-h1b-lca-disclosure-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~h1b-lca-disclosure-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-h1b-lca-disclosure-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode", "proxyConfiguration" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "byCaseNumbers" ], "type": "string", "description": "What to fetch.", "default": "search" }, "fiscalYear": { "title": "Fiscal year", "enum": [ "latest", "FY2025", "FY2024", "FY2023", "FY2022", "FY2021", "FY2020" ], "type": "string", "description": "Which DOL disclosure file to scan. `latest` auto-discovers the newest quarterly file for the current fiscal year (currently FY2026 Q2). Older fiscal years are closed/final (through Q4).", "default": "latest" }, "caseNumbers": { "title": "Case numbers (mode=byCaseNumbers)", "type": "array", "description": "Exact LCA case numbers to look up, e.g. `I-200-25181-143022`.", "default": [], "items": { "type": "string" } }, "employerName": { "title": "Employer name contains", "type": "string", "description": "Case-insensitive substring match against employer legal name OR trade name / DBA." }, "jobTitle": { "title": "Job title contains", "type": "string", "description": "Case-insensitive substring match against the job title." }, "socCode": { "title": "SOC code", "type": "string", "description": "Exact match or prefix match against the Standard Occupational Classification code, e.g. `19-2031` or `19-2031.00`." }, "caseStatus": { "title": "Case status", "enum": [ "", "Certified", "Certified - Withdrawn", "Denied", "Withdrawn" ], "type": "string", "description": "Filter to a specific case status.", "default": "" }, "visaClass": { "title": "Visa class", "enum": [ "", "H-1B", "H-1B1 Chile", "H-1B1 Singapore", "E-3 Australian" ], "type": "string", "description": "Filter to a specific visa classification.", "default": "" }, "worksiteState": { "title": "Worksite state", "enum": [ "", "AK", "AL", "AR", "AZ", "CA", "CO", "CT", "DC", "DE", "FL", "GA", "GU", "HI", "IA", "ID", "IL", "IN", "KS", "KY", "LA", "MA", "MD", "ME", "MI", "MN", "MO", "MP", "MS", "MT", "NC", "ND", "NE", "NH", "NJ", "NM", "NV", "NY", "OH", "OK", "OR", "PA", "PR", "RI", "SC", "SD", "TN", "TX", "UT", "VA", "VI", "VT", "WA", "WI", "WV", "WY" ], "type": "string", "description": "Filter to a specific US worksite state/territory.", "default": "" }, "worksiteCity": { "title": "Worksite city contains", "type": "string", "description": "Case-insensitive substring match against the worksite city." }, "naicsCode": { "title": "NAICS code", "type": "string", "description": "Exact match or prefix match against the employer's NAICS industry code, e.g. `611310` or `6113`." }, "socTitle": { "title": "SOC occupation title contains", "type": "string", "description": "Case-insensitive substring match against the SOC occupation category name (e.g. `Software Developers`), distinct from `jobTitle`. Useful when you don't know the exact SOC code." }, "lawfirmOrAttorneyName": { "title": "Attorney/law firm name contains", "type": "string", "description": "Case-insensitive substring match against the filing attorney's name OR the law firm/business name that represented the employer." }, "employerFein": { "title": "Employer FEIN (exact)", "type": "string", "description": "Exact match on the sponsoring employer's Federal Employer Identification Number (dashes/spaces ignored), e.g. `12-3456789`. Use this instead of employer name when you need to pin down one legal entity precisely." }, "fullTimePositionOnly": { "title": "Full-time positions only", "type": "boolean", "description": "Only emit full-time positions.", "default": false }, "totalWorkerPositionsMin": { "title": "Min total worker positions", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Drop records where the total number of worker positions requested on the LCA is below this value. Useful for finding bulk/high-volume filings." }, "totalWorkerPositionsMax": { "title": "Max total worker positions", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Drop records where the total number of worker positions requested on the LCA is above this value." }, "wageMin": { "title": "Min wage (rate of pay from)", "minimum": 0, "maximum": 100000000, "type": "integer", "description": "Drop records with `wageRateFrom` below this value (in the wage's own unit of pay)." }, "wageMax": { "title": "Max wage (rate of pay from)", "minimum": 0, "maximum": 100000000, "type": "integer", "description": "Drop records with `wageRateFrom` above this value (in the wage's own unit of pay)." }, "prevailingWageMin": { "title": "Min prevailing wage", "minimum": 0, "maximum": 100000000, "type": "integer", "description": "Drop records with `prevailingWage` below this value." }, "prevailingWageMax": { "title": "Max prevailing wage", "minimum": 0, "maximum": 100000000, "type": "integer", "description": "Drop records with `prevailingWage` above this value." }, "pwWageLevel": { "title": "Prevailing wage level", "enum": [ "", "I", "II", "III", "IV" ], "type": "string", "description": "Filter to a specific DOL prevailing wage level.", "default": "" }, "wageUnitOfPay": { "title": "Wage unit of pay", "enum": [ "", "Year", "Hour", "Week", "Bi-Weekly", "Month" ], "type": "string", "description": "Filter to a specific offered-wage pay period.", "default": "" }, "employerState": { "title": "Employer (sponsor) state", "enum": [ "", "AK", "AL", "AR", "AZ", "CA", "CO", "CT", "DC", "DE", "FL", "GA", "GU", "HI", "IA", "ID", "IL", "IN", "KS", "KY", "LA", "MA", "MD", "ME", "MI", "MN", "MO", "MP", "MS", "MT", "NC", "ND", "NE", "NH", "NJ", "NM", "NV", "NY", "OH", "OK", "OR", "PA", "PR", "RI", "SC", "SD", "TN", "TX", "UT", "VA", "VI", "VT", "WA", "WI", "WV", "WY" ], "type": "string", "description": "Filter to a specific US state/territory of the sponsoring employer's own address (distinct from the worksite state).", "default": "" }, "hasAgentOrAttorney": { "title": "Filed with agent/attorney", "enum": [ "", "yes", "no" ], "type": "string", "description": "Filter by whether an agent or attorney represented the employer on the filing.", "default": "" }, "h1bDependentOnly": { "title": "H-1B dependent employers only", "type": "boolean", "description": "Only emit records where the employer is classified as H-1B dependent.", "default": false }, "willfulViolatorOnly": { "title": "Willful violators only", "type": "boolean", "description": "Only emit records where the employer is listed as a willful violator.", "default": false }, "receivedDateFrom": { "title": "Received date from", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records received before this date." }, "receivedDateTo": { "title": "Received date to", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records received after this date." }, "decisionDateFrom": { "title": "Decision date from", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records decided before this date." }, "decisionDateTo": { "title": "Decision date to", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records decided after this date." }, "employmentBeginDateFrom": { "title": "Employment start date from", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records whose requested employment period starts before this date." }, "employmentBeginDateTo": { "title": "Employment start date to", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records whose requested employment period starts after this date." }, "employmentEndDateFrom": { "title": "Employment end date from", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records whose requested employment period ends before this date." }, "employmentEndDateTo": { "title": "Employment end date to", "type": "string", "description": "ISO date `YYYY-MM-DD`. Drop records whose requested employment period ends after this date." }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on emitted records. The DOL disclosure file has 600K-900K rows; a very high value combined with a restrictive filter may take several minutes since the whole file must be streamed once.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Required. dol.gov's Akamai edge blocks Apify's own egress IPs and the default Apify datacenter proxy pool with a 403 on the large XLSX disclosure files. The actor always tries a direct connection first (fast to fail) and falls back to this proxy — it must be a Residential group for the download to succeed reliably from Apify's cloud infrastructure.", "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 } } } } } } } } } }