{ "openapi": "3.0.1", "info": { "title": "H1B Visa Sponsor & Salary Database Scraper", "description": "Search the US Department of Labor's public H1B LCA filing history by employer, job title, city, or year -- salary, worksite, and (optionally) full case detail including sponsoring attorney and employer contact. No account or API key needed.", "version": "0.0", "x-build-id": "wrTuFQYU5awlZ49Bl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zucchini_gopher_m2v~h1bdata-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zucchini_gopher_m2v-h1bdata-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zucchini_gopher_m2v~h1bdata-scraper/runs": { "post": { "operationId": "runs-sync-zucchini_gopher_m2v-h1bdata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zucchini_gopher_m2v~h1bdata-scraper/run-sync": { "post": { "operationId": "run-sync-zucchini_gopher_m2v-h1bdata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "caseDetail" ], "type": "string", "description": "\"search\" queries the H1B LCA filing database by employer / job title / city / year. \"caseDetail\" fetches the full case record (wage, worksite, attorney, employer contact) for specific case ID(s) directly.", "default": "search" }, "employer": { "title": "Employer name", "type": "string", "description": "\"search\" mode -- partial or full sponsor company name, e.g. \"Google\" or \"Tata Consultancy\". Case-insensitive substring match. At least one of employer / jobTitle / city is required." }, "jobTitle": { "title": "Job title", "type": "string", "description": "\"search\" mode -- partial or full job title as filed on the LCA, e.g. \"Data Scientist\". Note: filed job titles are often auto-generated and lightly mangled (spaces stripped, an internal code appended) -- a short, common substring works best." }, "city": { "title": "Worksite city", "type": "string", "description": "\"search\" mode -- worksite city, e.g. \"Mountain View\"." }, "year": { "title": "Fiscal year", "enum": [ "All Years", "2025", "2024", "2023", "2022", "2021", "2020", "2019", "2018", "2017", "2016", "2015", "2014", "2013", "2012" ], "type": "string", "description": "\"search\" mode -- LCA fiscal year to search, or \"All Years\" for the full 2012-present history (returns more rows, slower for large employers).", "default": "All Years" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 20000, "type": "integer", "description": "\"search\" mode -- maximum number of filing rows to return. h1bdata.info renders every matching row on one page (no pagination) -- large employers across \"All Years\" can match tens of thousands of rows, so this caps both the output size and (indirectly) how much HTML gets parsed.", "default": 200 }, "fetchCaseDetails": { "title": "Enrich with full case detail", "type": "boolean", "description": "\"search\" mode -- when true, each matched filing is additionally fetched for its full case record (prevailing wage, wage level, worksite address, employer point-of-contact name/email, sponsoring attorney/law-firm name/email). When false (default), only the lightweight search-result row (employer, job title, base salary, location, submit/start date) is returned -- much faster for large result sets.", "default": false }, "caseIds": { "title": "Case IDs", "type": "array", "description": "\"caseDetail\" mode -- LCA case numbers to fetch full detail for directly, e.g. \"I-200-21027-037298\" (the case ID shown in the Base Salary column link of search results, or in a previous run's \"caseId\" field).", "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrent workers", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many case-detail pages to fetch in parallel (\"search\" mode's enrichment pass, or \"caseDetail\" mode's case ID list).", "default": 4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Residential is on by default.", "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 } } } } } } } } } }