{ "openapi": "3.0.1", "info": { "title": "Linkedin Company Jobs Scraper", "description": "Bulk scrape public job listings from lists of LinkedIn Company pages. Bypasses guest limits and data obfuscation (*****) to retrieve hundreds of clean results per company. Features smart proxy rotation and automated batch processing to scale your data collection.", "version": "1.2", "x-build-id": "6Utk3NdYE9SYwFxG7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gtgyani206~linkedin-company-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gtgyani206-linkedin-company-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gtgyani206~linkedin-company-scraper/runs": { "post": { "operationId": "runs-sync-gtgyani206-linkedin-company-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gtgyani206~linkedin-company-scraper/run-sync": { "post": { "operationId": "run-sync-gtgyani206-linkedin-company-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "companyUrls" ], "properties": { "companyUrls": { "title": "LinkedIn company page URLs", "minItems": 1, "maxItems": 100, "uniqueItems": true, "type": "array", "description": "Enter full company URLs such as `https://www.linkedin.com/company/google`. Job URLs, profile URLs, and search URLs are not accepted.", "items": { "type": "string", "pattern": "^https://www\\.linkedin\\.com/company/[^/?#]+/?(?:[?#].*)?$" } }, "runProfile": { "title": "Run profile", "enum": [ "fast", "balanced", "enriched", "custom" ], "type": "string", "description": "**Fast** minimizes requests. **Balanced** is the recommended default. **Enriched** fetches each job detail page. **Custom** starts from balanced defaults.", "default": "balanced" }, "maxJobs": { "title": "Maximum matching jobs per company", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stops after this many jobs pass all filters for each company. Profile default: 50." }, "maxTotalJobs": { "title": "Maximum jobs for the entire run", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Hard run-wide output cap across all companies. The profile default is 1,000 and prevents unexpectedly large result charges when many company URLs are supplied." }, "scrapeDescription": { "title": "Fetch descriptions and detail fields", "type": "boolean", "description": "Fetch each job detail endpoint to collect descriptions, employment type, seniority, workplace type, applicant text, and apply URL. This increases runtime and proxy traffic." }, "postedWithinDays": { "title": "Posted within", "minimum": 0, "maximum": 3650, "type": "integer", "description": "Keep jobs posted within the last N days. Use 0 for any posting date.", "default": 0 }, "includeJobsWithUnknownDate": { "title": "Keep jobs with missing dates", "type": "boolean", "description": "When a date filter is active, keep jobs for which LinkedIn does not provide a valid posting date.", "default": true }, "keywordInclude": { "title": "Include keywords", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Keep jobs whose title or location contains the configured terms. Matching is case-insensitive.", "items": { "type": "string", "minLength": 1, "maxLength": 100 }, "default": [] }, "keywordMatchMode": { "title": "Include keyword logic", "enum": [ "any", "all" ], "type": "string", "description": "Choose whether a job must match any included keyword or every included keyword.", "default": "any" }, "keywordExclude": { "title": "Exclude keywords", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Reject jobs whose title or location contains any configured term.", "items": { "type": "string", "minLength": 1, "maxLength": 100 }, "default": [] }, "locationInclude": { "title": "Include locations", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Keep jobs whose raw LinkedIn location contains at least one configured value, such as `Austin`, `Germany`, or `Remote`.", "items": { "type": "string", "minLength": 1, "maxLength": 100 }, "default": [] }, "locationExclude": { "title": "Exclude locations", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Reject jobs whose raw LinkedIn location contains any configured value.", "items": { "type": "string", "minLength": 1, "maxLength": 100 }, "default": [] }, "remoteFilter": { "title": "Remote status", "enum": [ "all", "remote", "nonRemote" ], "type": "string", "description": "Keep all jobs, remote jobs only, or non-remote jobs only. A non-default choice requires detail requests for better classification.", "default": "all" }, "workplaceTypes": { "title": "Workplace types", "uniqueItems": true, "type": "array", "description": "Optional exact-match filter. Enabling it requires job detail requests.", "items": { "type": "string", "enum": [ "Remote", "Hybrid", "On-site" ], "enumTitles": [ "Remote", "Hybrid", "On-site" ] }, "default": [] }, "employmentTypes": { "title": "Employment types", "uniqueItems": true, "type": "array", "description": "Optional exact-match filter. Values depend on what LinkedIn publishes for each job.", "items": { "type": "string", "enum": [ "Full-time", "Part-time", "Contract", "Temporary", "Volunteer", "Internship", "Other" ] }, "default": [] }, "seniorityLevels": { "title": "Seniority levels", "uniqueItems": true, "type": "array", "description": "Optional exact-match filter. Enabling it requires job detail requests.", "items": { "type": "string", "enum": [ "Internship", "Entry level", "Associate", "Mid-Senior level", "Director", "Executive", "Not Applicable" ] }, "default": [] }, "includeJobsWithUnknownMetadata": { "title": "Keep jobs with missing detail metadata", "type": "boolean", "description": "When employment, seniority, or workplace filters are active, keep jobs whose detail page omits the filtered field.", "default": true }, "newJobsOnly": { "title": "Only emit newly discovered jobs", "type": "boolean", "description": "Skip matching jobs already stored for the same company and monitoring namespace.", "default": false }, "monitoringStoreId": { "title": "Monitoring key-value store", "type": "string", "description": "Optional persistent store for monitoring history. When omitted, the Actor uses or creates the named store `linkedin-company-scraper-monitoring`." }, "monitoringNamespace": { "title": "Monitoring namespace", "pattern": "^[a-zA-Z0-9_-]{1,80}$", "type": "string", "description": "Separates independent schedules or filter sets that share a monitoring store.", "default": "default" }, "monitoringFirstRunPolicy": { "title": "First monitoring run", "enum": [ "emit", "storeOnly" ], "type": "string", "description": "Emit the initial baseline, or store it silently so future runs emit only jobs discovered later.", "default": "emit" }, "resetMonitoring": { "title": "Reset this namespace before running", "type": "boolean", "description": "Delete saved state for the requested companies in this namespace before collecting jobs. The reset applies only to this run.", "default": false }, "maxPagesPerCompany": { "title": "Maximum listing pages per company", "minimum": 1, "maximum": 100, "type": "integer", "description": "Each page contains up to about 25 cards. When omitted, the profile automatically allows enough pages for `maxJobs`, up to 100." }, "maxRequestsPerRun": { "title": "Maximum HTTP attempts per run", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Hard cost guard covering company pages, listing pages, detail pages, and retries. Profile defaults range from 100 to 500 attempts." }, "maxRunTimeSeconds": { "title": "Whole-run time budget", "minimum": 60, "maximum": 86400, "type": "integer", "description": "The Actor stops gracefully before this budget, keeps already saved jobs, and writes a partial `RUN_SUMMARY`." }, "requestTimeoutSeconds": { "title": "Per-request timeout", "minimum": 5, "maximum": 180, "type": "integer", "description": "Maximum wait for one LinkedIn HTTP request." }, "maxRequestRetries": { "title": "Retries per failed request", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retry transient request failures with bounded exponential backoff." }, "retryDelaySeconds": { "title": "Initial retry delay", "minimum": 0, "maximum": 60, "type": "integer", "description": "Base delay before the first retry. Later retries use exponential backoff with jitter." }, "requestDelayMillis": { "title": "Delay between requests", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Polite randomized pacing applied before requests. Use 0 only when you understand the blocking risk." }, "detailConcurrency": { "title": "Concurrent detail requests", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum parallel job-detail requests. Low values are more conservative and predictable." }, "failurePolicy": { "title": "When one company fails", "enum": [ "continue", "failFast" ], "type": "string", "description": "Continue with the remaining companies or stop immediately.", "default": "continue" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Configure Apify Proxy or your own proxy URLs. Disable proxy usage for local testing only if direct access works from your network.", "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 } } } } } } } } } }