{ "openapi": "3.0.1", "info": { "title": "H-1B Visa & LCA Sponsor Scraper - Employer Leads", "description": "Scrape US DOL H-1B / LCA visa data: sponsoring employers, salaries, job titles, worksites, FEIN & NAICS, HR contacts (email & phone) and immigration attorneys & law firms. Search by employer, job or city, build sponsor profiles, monitor new filings. No API key. Export JSON, CSV, Excel.", "version": "0.1", "x-build-id": "47ix4jyOyCCJTdjW7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~h1b-visa-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-h1b-visa-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~h1b-visa-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-h1b-visa-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~h1b-visa-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-h1b-visa-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "What to scrape", "enum": [ "search", "employerProfile", "caseDetails" ], "type": "string", "description": "search = individual H-1B/LCA filings (employer, job, salary, worksite, case #). employerProfile = one aggregated sponsor record per employer (filing volume, salary stats, top roles & locations + representative firmographics/contacts). caseDetails = full record for specific LCA case numbers.", "default": "search" }, "employers": { "title": "Employer names", "type": "array", "description": "Sponsoring employers to search, e.g. \"Google\", \"Amazon\", \"Anthropic PBC\". search mode: matched against the employer name. employerProfile mode: one sponsor record per employer. Combined with jobTitles/cities in search mode.", "items": { "type": "string" } }, "jobTitles": { "title": "Job titles (search)", "type": "array", "description": "search mode: filter filings by job title, e.g. \"Data Scientist\", \"Software Engineer\", \"Product Manager\". Combined with employers and cities (cartesian product, capped by Max search combinations).", "items": { "type": "string" } }, "cities": { "title": "Worksite cities (search)", "type": "array", "description": "search mode: filter filings by worksite city, e.g. \"New York\", \"San Francisco\", \"Austin, TX\" (the state part is ignored — h1bdata matches by city name).", "items": { "type": "string" } }, "year": { "title": "Filing year", "enum": [ "All", "2026", "2025", "2024", "2023", "2022", "2021", "2020", "2019", "2018", "2017", "2016", "2015", "2014", "2013", "2012" ], "type": "string", "description": "Disclosure year to search (DOL fiscal-year disclosure data). Use \"All\" to search across every year (large for big employers).", "default": "2025" }, "caseNumbers": { "title": "LCA case numbers (case details)", "type": "array", "description": "caseDetails mode: exact LCA case numbers to look up, e.g. \"I-200-24291-412570\". Each returns the complete disclosure record.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs (optional)", "type": "array", "description": "Paste h1bdata.info URLs to scrape directly: details.php?id= (a single case) or index.php?em=&job=&city=&year= (a search). Auto-routed.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "includeCaseDetails": { "title": "Include full case details (search)", "type": "boolean", "description": "search mode: for every filing, also fetch its detail page — adding employer phone/FEIN/NAICS/address, the HR point-of-contact (name, job title, email, phone), the immigration attorney & law firm (name, email, phone), worksite, prevailing wage & wage level and compliance flags. One extra request per filing (charged as case details). Turn off for fast, lightweight filing rows only.", "default": true }, "includeEmployerFirmographics": { "title": "Include firmographics & contacts (employer profile)", "type": "boolean", "description": "employerProfile mode: fetch one representative case per employer to attach firmographics (address, phone, FEIN, NAICS) and contacts (HR point-of-contact email/phone, immigration attorney & law firm). One extra request per employer.", "default": true }, "minSalary": { "title": "Minimum salary (USD/year)", "type": "integer", "description": "Only return records with an annualized wage at or above this amount — a fast way to surface senior/high-value sponsored roles." }, "certifiedOnly": { "title": "Certified filings only", "type": "boolean", "description": "Only keep filings with a Certified status (excludes Denied/Withdrawn). Applies when case details are fetched.", "default": false }, "withEmailOnly": { "title": "Only records with a contact email", "type": "boolean", "description": "Only keep records that carry at least one contact email (HR point-of-contact, attorney or preparer). Applies to case-detail and employer-profile records.", "default": false }, "maxSearchCombinations": { "title": "Max search combinations", "minimum": 1, "type": "integer", "description": "search mode: cap on the number of employer × job × city query combinations to run.", "default": 60 }, "maxResults": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Maximum number of records to return for this run.", "default": 100 }, "monitorMode": { "title": "Monitor mode (only new records)", "type": "boolean", "description": "Remember records seen in previous runs (in a named key-value store) and emit only records that are new since the last run — by case number for filings/case details, by employer+year for profiles. Ideal for a daily/weekly Schedule that watches an employer, job title or city for newly filed H-1B petitions. Does not conflict with Apify Schedules.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy for outbound requests. The default Apify Proxy is recommended — the actor rotates a fresh IP per request.", "default": { "useApifyProxy": true } }, "urlsFromFile": { "title": "Import URLs from a file", "type": "string", "description": "Paste a list of URLs (one per line), OR one link to a .txt/.csv file, Google Sheet or Google Drive file containing them. Lets you import many Start URLs at once instead of typing each. Google Sheet/Drive share links are handled automatically." } } }, "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 } } } } } } } } } }