{ "openapi": "3.0.1", "info": { "title": "Indeed Jobs Scraper", "description": "Extract public Indeed job listings into clean Apify datasets for recruiting intelligence, talent pipeline building, competitor monitoring, and hiring analytics.", "version": "0.1", "x-build-id": "7xEgCbgmsyrUX6hoJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kmiloaguilar~indeed-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kmiloaguilar-indeed-jobs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kmiloaguilar~indeed-jobs-scraper/runs": { "post": { "operationId": "runs-sync-kmiloaguilar-indeed-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kmiloaguilar~indeed-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-kmiloaguilar-indeed-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Indeed search result URLs or /viewjob detail URLs to scrape.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "query": { "title": "Job keywords", "type": "string", "description": "Search keywords, used when startUrls is empty.", "default": "data analyst" }, "location": { "title": "Location", "type": "string", "description": "City, region, country, or postal code for Indeed search.", "default": "New York, NY" }, "country": { "title": "Country site", "enum": [ "us", "ca", "uk", "gb", "au", "de", "fr", "es", "www.indeed.com", "ca.indeed.com", "uk.indeed.com", "au.indeed.com", "de.indeed.com", "fr.indeed.com", "es.indeed.com" ], "type": "string", "description": "Indeed host to scrape.", "default": "www.indeed.com" }, "maxItems": { "title": "Maximum jobs", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum unique job records to save.", "default": 100 }, "startPage": { "title": "Start page", "minimum": 1, "type": "integer", "description": "First Indeed search-results page to scrape, using 1-indexed page numbers.", "default": 1 }, "endPage": { "title": "End page", "minimum": 1, "type": "integer", "description": "Last Indeed search-results page to scrape, inclusive. Leave empty to continue until maxItems is reached." }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 50, "type": "integer", "description": "Expected jobs per Indeed search-results page, used for pagination offsets and stopping logic.", "default": 15 }, "queryVariants": { "title": "Query variants", "type": "array", "description": "Optional extra keyword searches for segmented large-result runs. The main query is always tried first.", "items": { "type": "string" } }, "locationVariants": { "title": "Location variants", "type": "array", "description": "Optional extra locations for segmented large-result runs. The main location is always tried first.", "items": { "type": "string" } }, "postedWithinDaysSegments": { "title": "Posted date segments", "type": "array", "description": "Optional extra Indeed fromage values to fan out large searches, for example 1, 3, 7, and 14.", "items": { "type": "string" } }, "radiusKmSegments": { "title": "Radius segments in km", "type": "array", "description": "Optional extra radius values to fan out large searches while deduplicating jobs across segments.", "items": { "type": "string" } }, "maxSearchSegments": { "title": "Maximum search segments", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum generated search URLs when query, location, date, or radius segments are provided.", "default": 20 }, "postedWithinDays": { "title": "Posted within days", "minimum": 0, "maximum": 30, "type": "integer", "description": "Indeed date filter. Common values are 1, 3, 7, and 14.", "default": 7 }, "radiusKm": { "title": "Search radius in km", "minimum": 0, "maximum": 100, "type": "integer", "description": "Radius around location, converted to Indeed radius parameter.", "default": 25 }, "jobType": { "title": "Job type", "enum": [ "any", "full-time", "part-time", "contract", "internship", "temporary" ], "type": "string", "description": "Indeed job type filter.", "default": "any" }, "remoteWorkType": { "title": "Remote work type", "enum": [ "any", "remote", "hybrid", "on-site" ], "type": "string", "description": "Remote work filter. Remote maps to Indeed's remote-only URL filter; hybrid and on-site are accepted for compatibility but not forced unless Indeed exposes them in the result page.", "default": "any" }, "sort": { "title": "Sort order", "enum": [ "relevance", "date" ], "type": "string", "description": "Sort Indeed results by relevance or date.", "default": "relevance" }, "experienceLevel": { "title": "Experience level", "enum": [ "any", "entry-level", "mid-level", "senior-level" ], "type": "string", "description": "Indeed experience-level filter where supported by the selected country site.", "default": "any" }, "excludeEmployers": { "title": "Exclude employers", "type": "array", "description": "Employer names or substrings to exclude after extraction.", "items": { "type": "string" } }, "excludeSalaryTypes": { "title": "Exclude salary types", "type": "array", "description": "Salary cadence labels to exclude after extraction, for example hourly jobs.", "items": { "type": "string" } }, "dedupeJobs": { "title": "Deduplicate jobs", "type": "boolean", "description": "Skip duplicate jobs across pages and segmented searches.", "default": true }, "scrapeDetailPages": { "title": "Scrape detail pages", "type": "boolean", "description": "Fetch each job page for description and richer apply/company data.", "default": true }, "maxConcurrency": { "title": "Maximum concurrent requests", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many Indeed pages to fetch in parallel.", "default": 20 }, "requestDelayMillis": { "title": "Request delay in milliseconds", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Optional delay after each successful request while holding a concurrency slot. Keep 0 for speed; raise it if Indeed starts rate limiting.", "default": 0 }, "proxyUrl": { "title": "Custom proxy URL", "type": "string", "description": "Optional proxy URL. Leave empty to use DEFAULT_PROXY_URL when configured, or Apify Proxy through proxyConfiguration." }, "proxyConfiguration": { "title": "Apify proxy configuration", "type": "object", "description": "Optional Apify proxy configuration. Defaults to Apify Proxy when no proxyUrl or DEFAULT_PROXY_URL is set.", "default": { "useApifyProxy": true } }, "requestRetries": { "title": "Request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retry count for failed requests.", "default": 2 }, "retryDelayMillis": { "title": "Retry delay in milliseconds", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Delay between retry attempts after a failed request.", "default": 1000 }, "requestTimeoutSecs": { "title": "Request timeout in seconds", "minimum": 1, "maximum": 120, "type": "integer", "description": "HTTP timeout per request.", "default": 30 } } }, "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 } } } } } } } } } }