{ "openapi": "3.0.1", "info": { "title": "Glassdoor Jobs Scraper", "description": "Scrape job listings from Glassdoor across all Glassdoor country sites (US, UK, Canada, Australia, New Zealand, Ireland, India, Hong Kong, Singapore), including title, company, rating, location, salary, and posted date.", "version": "1.0", "x-build-id": "UlPx874nBU52W5Xb5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mrdoe~glassdoor-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mrdoe-glassdoor-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mrdoe~glassdoor-jobs-scraper/runs": { "post": { "operationId": "runs-sync-mrdoe-glassdoor-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mrdoe~glassdoor-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-mrdoe-glassdoor-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "maxPages" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Glassdoor job search result page URLs to start scraping from, on any Glassdoor country site (glassdoor.com, glassdoor.co.uk, glassdoor.ca, glassdoor.com.au, glassdoor.co.nz, glassdoor.ie, glassdoor.co.in, glassdoor.com.hk, glassdoor.sg). Takes priority over Keyword/Location/Country below when set.", "default": [ { "url": "https://www.glassdoor.com/Job/software-engineer-jobs-SRCH_KO0,17.htm" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keyword": { "title": "Keyword", "type": "string", "description": "Job title, skill, or keyword to search for. Used to build a search URL when Start URLs is empty." }, "location": { "title": "Location", "type": "string", "description": "Free-text location to search in (city, state, or region). Used to build a search URL when Start URLs is empty." }, "country": { "title": "Country (Glassdoor site)", "enum": [ "us", "uk", "ca", "au", "nz", "ie", "in", "hk", "sg" ], "type": "string", "description": "Which Glassdoor country site to search when building a URL from Keyword/Location. Ignored if Start URLs is set.", "default": "us" }, "maxItems": { "title": "Max jobs per start URL", "minimum": 1, "type": "integer", "description": "Maximum number of job listings to scrape for each start URL / search.", "default": 10 }, "maxPages": { "title": "Max search result pages per start URL", "minimum": 1, "type": "integer", "description": "Safety cap on how many search result pages to paginate through for each start URL / search. Since results are billed per item, this must be set explicitly so a single search can't run away into an unbounded number of pages.", "default": 5 }, "scrapeJobDetails": { "title": "Scrape full job descriptions", "type": "boolean", "description": "Visit each job's detail page for the untruncated description. Off by default: search-result pages already carry title, company, rating, location, salary, and a real (if truncated) description snippet for every job, reliably and without a proxy. Detail pages sit behind a much stricter Cloudflare challenge - turning this on adds one extra page load per job, and any job whose detail page is blocked still lands in the dataset using its snippet as a fallback.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Required - Glassdoor blocks a majority of unproxied/datacenter-IP requests (confirmed live), on both search pages and (if Scrape full job descriptions is on) job-detail pages. Defaults to Apify Proxy's Residential group.", "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 } } } } } } } } } }