{ "openapi": "3.0.1", "info": { "title": "All-in one Linkedin Scraper", "description": "LinkedIn scraper — 8 modes: Profiles, Companies, Jobs, Posts, Search, Search Profiles, Profile Complete, Company Employees. Premium residential proxy (~95% success rate) + email discovery (11 patterns + Hunter.io). From $1/1K — up to 75% cheaper. MCP-ready for AI agents.", "version": "0.1", "x-build-id": "BXyNnrcixY5ini7qy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/get-leads~linkedin-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-get-leads-linkedin-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/get-leads~linkedin-scraper/runs": { "post": { "operationId": "runs-sync-get-leads-linkedin-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/get-leads~linkedin-scraper/run-sync": { "post": { "operationId": "run-sync-get-leads-linkedin-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": "Scraping Mode", "enum": [ "profiles", "companies", "jobs", "posts", "search", "search_profiles", "profile_complete", "company_employees", "monitor" ], "type": "string", "description": "What to scrape. Companies/Jobs/Search work WITHOUT cookies. Profiles/Posts/Search Profiles/Profile Complete/Company Employees work best WITH a cookie. 'profiles' = profile data (15 fields). 'companies' = company pages (15 fields). 'jobs' = job search with filters (20 fields — salary field now populates on 50-70% of listings via description-text extraction). 'posts' = posts with engagement + hashtags, cookie required (14 fields). 'search' = find profiles by keywords (9 fields, 5-engine parallel SERP with cross-engine field union). 'search_profiles' = search by name + full enrichment (15 fields; returns all matching people with canonical-slug dedupe). 'profile_complete' = profile + about + posts + engagement score (19 fields). 'company_employees' = find people at a company (8 fields; three-path discovery returns 20-100+ employees per company when cookie provided). Smart proxy routing: DC for Companies/Jobs/Posts/Search, residential only for Profiles/Search Profiles/Profile Complete.", "default": "profiles" }, "urls": { "title": "LinkedIn URLs", "type": "array", "description": "LinkedIn URLs to scrape. REQUIRED for modes: profiles, companies, posts, profile_complete, company_employees. URL format by mode — Profiles / Profile Complete: /in/username · Companies / Company Employees: /company/name · Posts: profile OR company URLs. Not used by Jobs / Search / Search Profiles (use Search Query instead). Submitting an empty `urls` array to a URL-input mode fails fast with an example of the correct shape.", "items": { "type": "string" } }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Search keywords. REQUIRED for modes: jobs, search, search_profiles. Jobs: role keywords (e.g. 'software engineer'). Search: profile keywords (e.g. 'product manager'). Search Profiles: a person's full name (e.g. 'Sunny Savita') — the scraper finds every matching LinkedIn profile and enriches each. Submitting an empty `searchQuery` to a query-input mode fails fast with an example of the correct shape." }, "location": { "title": "Location", "type": "string", "description": "Location filter for Jobs and Search modes. Examples: 'San Francisco', 'United States', 'London, UK'." }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of results to return. Default: 25. Runs that exceed the per-mode soft cap (profile_complete: 100, profiles/search_profiles: 200, company_employees: 250, posts: 500) require `confirmLargeRun: true` to proceed — this prevents accidental multi-dollar bills from a mistyped input. Low-unit-price modes (jobs, search, companies) have no soft cap and accept values up to 1000 without confirmation.", "default": 25 }, "timePosted": { "title": "Time Posted", "enum": [ "24h", "week", "month" ], "type": "string", "description": "Filter jobs by when they were posted." }, "jobType": { "title": "Job Type", "enum": [ "full-time", "part-time", "contract", "temporary", "volunteer", "internship" ], "type": "string", "description": "Filter by job type." }, "experienceLevel": { "title": "Experience Level", "enum": [ "internship", "entry", "associate", "mid-senior", "director", "executive" ], "type": "string", "description": "Filter by experience level." }, "workType": { "title": "Work Type", "enum": [ "onsite", "remote", "hybrid" ], "type": "string", "description": "Filter by work arrangement." }, "startDate": { "title": "Start Date (Posts Mode)", "type": "string", "description": "Filter posts from this date onwards (YYYY-MM-DD format). Posts mode only. Requires li_at cookie. Example: '2025-01-01'." }, "endDate": { "title": "End Date (Posts Mode)", "type": "string", "description": "Filter posts up to this date (YYYY-MM-DD format). Posts mode only. Requires li_at cookie. Example: '2026-04-01'." }, "discoverEmails": { "title": "Discover Emails", "type": "boolean", "description": "Try to find email addresses for profiles by scraping employer websites and generating email patterns. Adds ~2-4 seconds per profile. Works for Profiles, Search Profiles, and Profile Complete modes. AUTOMATICALLY DISABLED for Company Employees mode regardless of this setting — email discovery per employee (~15-20s each) would exceed the default run timeout on 25+ employee batches. To enrich employee emails, run Profiles mode on the URLs returned by Company Employees in a follow-up call. The per-run summary log emits a source breakdown (`json-ld` / `company-website` / `search-engine` / `hunter` / `none`) so you can audit which discovery strategies are producing your emails and decide whether the optional Hunter.io key is worth adding.", "default": true }, "includePosts": { "title": "Include Posts (Profile Complete)", "type": "boolean", "description": "When `profile_complete` mode: include posts array + posts_count + total_engagement. Set to false to skip post retrieval (~5-15s + multiple Voyager calls saved per profile). Useful when you only need profile data without engagement metrics.", "default": true }, "includeEngagement": { "title": "Include Engagement Metrics (Profile Complete)", "type": "boolean", "description": "When `profile_complete` mode: include per-post engagement enrichment (likes/comments/shares). Set to false to skip the extra Voyager enrichment pass per post. `includePosts` must be true for this to matter. Saves ~1s + 1 Voyager call per post.", "default": true }, "includeAbout": { "title": "Include About Section (Profile Complete)", "type": "boolean", "description": "When `profile_complete` mode: include the `about` field. Set to false to skip the `ProfileTabInitialCards` Voyager call that fetches this.", "default": true }, "enrichEmployeeLocation": { "title": "Enrich Employee Location (Company Employees)", "type": "boolean", "description": "When `company_employees` mode: for employees whose location is missing from SERP snippets, do a direct LinkedIn HTML fetch to extract location. Adds ~1-2s + ~0.5MB residential proxy usage per enriched employee. Disabled by default because SERP discovery already delivers 20-100+ employees per company; enable only if downstream workflows require location for every employee. Expected lift: location 8% → 80-90% populated.", "default": false }, "filterRoles": { "title": "Filter Employee Roles (Company Employees)", "type": "array", "description": "When `company_employees` mode: only return employees whose headline/title contains one of these keywords (case-insensitive, AND logic with company filter). Examples: `['Engineer', 'Senior Engineer']` returns only people with Engineer in their title. Leave empty to return all employees.", "items": { "type": "string" } }, "streamDataset": { "title": "Stream Dataset Writes", "type": "boolean", "description": "When enabled, the scraper pushes each result to the dataset IMMEDIATELY as it's collected (one `Actor.pushData` per record). Default behavior batches all results at mode-end — the default is faster on small runs but on 100+ record runs it can delay first-row visibility by minutes. Streaming is recommended for large company_employees / jobs / search runs where you want progressive results.", "default": false }, "proxyCountry": { "title": "Proxy Country (Multi-Region)", "type": "string", "description": "Override the residential-proxy country. When set, overrides the Evomi endpoint's default country. Use if your `li_at` cookie was extracted from a specific country — best practice is to match proxy country to cookie origin to avoid LinkedIn's geolocation-mismatch burns. Supported values: `US`, `GB`, `DE`, `NL`, `CA`, `FR`, `AU`, `IN`, `MY`, or any ISO 3166 alpha-2 code supported by your Evomi plan. Leave empty to use the default (whichever country the `RESIDENTIAL_PROXY_URL` env var is configured for)." }, "validateSlugs": { "title": "Validate Slugs Before Scraping", "type": "boolean", "description": "When true (default), the scraper runs one Voyager search before the main scrape loop to verify each input slug. Genuinely unreachable slugs (empty, or zero search results) are flagged with `error: invalid_slug` so you can reconcile bad input. Ambiguous slugs (e.g. celebrity short-forms like `williamhgates` whose derived name doesn't round-trip through search) are NOT blocked — the scraper proceeds and the direct-fetch path handles them. Only runs when an li_at cookie is available (no-op in cookie-free mode). Turn off if you're 100% confident your input slugs are correct and want to save one Voyager search call per profile. Applies to Profiles and Profile Complete modes.", "default": true }, "forceRefresh": { "title": "Force Fresh Scrape (Bypass Cache)", "type": "boolean", "description": "When true, bypasses the 24-hour profile cache and forces a fresh scrape. Useful for testing, verifying recent changes, or re-running after fixing input errors. Default: false (use cache when available).", "default": false }, "confirmLargeRun": { "title": "Confirm Large Run", "type": "boolean", "description": "Opt-in confirmation for runs that would exceed per-mode soft caps (profiles/search_profiles: 200, profile_complete: 100, company_employees: 250, posts: 500). Soft caps exist so high-unit-price modes don't accidentally bill $5+ from a misconfigured `maxResults`. Low-unit-price modes (jobs, search, companies) have no soft cap and run up to 1000 results without confirmation. Set to true only after reviewing your intended spend.", "default": false }, "dryRun": { "title": "Dry Run (Validate + Estimate Cost, No Scraping)", "type": "boolean", "description": "When true, validates the input and pushes a single dry-run report row to the dataset with estimated event count, estimated cost (USD), and any warnings — then exits WITHOUT making any HTTP calls or billing events. Useful for previewing spend before launching large runs. Leave at `false` (default) to run the scraper for real.", "default": false }, "hunterApiKey": { "title": "Hunter.io API Key (Optional — Email Finder)", "type": "string", "description": "Optional Hunter.io API key for email enrichment. When provided, Hunter Email Finder is used as fallback after website scraping. Get your free API key at hunter.io/api-keys (25 free searches/month)." }, "proxyConfig": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings. Smart routing: residential proxy only for Profiles/Search Profiles/Profile Complete (direct LinkedIn access). All other modes use cheaper datacenter proxies automatically.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "minDelay": { "title": "Min Delay (ms)", "minimum": 500, "maximum": 30000, "type": "integer", "description": "Minimum delay between requests in milliseconds.", "default": 2000 }, "maxDelay": { "title": "Max Delay (ms)", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Maximum delay between requests in milliseconds.", "default": 5000 }, "urlsFileUrl": { "title": "URLs File (Batch Input)", "type": "string", "description": "URL to a text or CSV file containing LinkedIn URLs (one per line). Use this for batch runs with 100+ URLs instead of pasting them manually. Supports plain text (.txt) and CSV files. Lines starting with # are ignored." }, "alertEmail": { "title": "Alert Email (Monitor Mode)", "type": "string", "description": "Email address for health check alerts. Used in monitor mode — receives alerts when runs fail or return empty results. Leave blank to disable email alerts." }, "webhookUrl": { "title": "Webhook URL (Optional)", "type": "string", "description": "URL to receive a POST request when the scraper finishes. The webhook payload includes: mode, itemCount, datasetId, runId, status. Useful for large batch runs — get notified when results are ready instead of polling." } } }, "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 } } } } } } } } } }