{ "openapi": "3.0.1", "info": { "title": "Glassdoor + AI Employer Intelligence · No-Limit Reviews·Jobs", "description": "Glassdoor scraper that survives the anti-bot wall — no 200-review cap: full reviews with sub-ratings, pros/cons, employer replies, plus jobs, salaries & interviews. New AI Employer Intelligence: per-employer complaint themes, attrition-risk signals & quick wins from real reviews.", "version": "0.0", "x-build-id": "T0BUb7ffR69lWFEfD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~glassdoor-scraper-ppr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-glassdoor-scraper-ppr", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~glassdoor-scraper-ppr/runs": { "post": { "operationId": "runs-sync-memo23-glassdoor-scraper-ppr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~glassdoor-scraper-ppr/run-sync": { "post": { "operationId": "run-sync-memo23-glassdoor-scraper-ppr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URLs to start with. Glassdoor company-page URLs from any tab (Reviews, Jobs, Salaries, Interviews, Overview) and any country's Glassdoor domain, e.g. https://www.glassdoor.com/Reviews/Google-Reviews-E9079.htm. The 'command' field selects which dataset is scraped from them.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "command": { "title": "Choose which data to scrape reviews or interviews for the links(s) you provided", "enum": [ "reviews", "interviews", "locations", "salaries", "jobs", "overview", "benefits", "culture" ], "type": "string", "description": "Choose which data to scrape (reviews or interviews or locations or salaries or jobs) for the links(s) you provided. Also supports 'overview' (company profile), 'benefits' and 'culture' (diversity ratings). Default: reviews.", "default": "reviews" }, "searchJobsByKeyword": { "title": "Search jobs by keyword & filters", "type": "boolean", "description": "Turn this ON to run a keyword/location/filter job search using the fields below. When OFF, these fields are ignored and the actor uses the Start URLs / command above.", "default": false }, "searchKeyword": { "title": "Search keyword", "type": "string", "description": "Job title or keyword to search for (e.g. \"Software Developer\", \"Registered Nurse\"). Requires the toggle above to be ON." }, "searchLocation": { "title": "Search location", "type": "string", "description": "City, state, or country to search in (e.g. \"New York\", \"United States\", \"London\"). Optional — omit for a nationwide/global search." }, "sortBy": { "title": "Sort results by", "enum": [ "relevant_desc", "date_desc" ], "type": "string", "description": "Order of the returned jobs.", "default": "relevant_desc" }, "maxDaysOld": { "title": "Posted within (days)", "enum": [ "any", "1", "3", "7", "14", "30" ], "type": "string", "description": "Only return jobs posted within this many days.", "default": "any" }, "remoteWorkType": { "title": "Workplace type", "enum": [ "any", "1", "2", "3" ], "type": "string", "description": "Filter by remote / hybrid / on-site.", "default": "any" }, "applicationType": { "title": "Easy Apply only", "enum": [ "any", "1" ], "type": "string", "description": "Restrict to Glassdoor Easy Apply jobs.", "default": "any" }, "jobType": { "title": "Job type", "enum": [ "any", "CF3CP", "5QWDV", "75GKK", "NJXCK", "T9BXE", "VDTG7" ], "type": "string", "description": "Filter jobs by employment type.", "default": "any" }, "minSalary": { "title": "Minimum salary", "type": "string", "description": "Only return jobs with an estimated salary at or above this amount (e.g. \"80000\"). Annual, in the location's currency." }, "maxSalary": { "title": "Maximum salary", "type": "string", "description": "Only return jobs with an estimated salary at or below this amount (e.g. \"150000\")." }, "minRating": { "title": "Minimum company rating", "enum": [ "any", "1", "2", "3", "4" ], "type": "string", "description": "Only return jobs at companies with at least this Glassdoor rating.", "default": "any" }, "employerSize": { "title": "Company size", "enum": [ "any", "1", "2", "3", "4", "5" ], "type": "string", "description": "Filter jobs by employer size band.", "default": "any" }, "radius": { "title": "Search radius (miles)", "enum": [ "any", "10", "20", "30", "50", "100", "200" ], "type": "string", "description": "Distance around the search location to include.", "default": "any" }, "industryNid": { "title": "Industry", "enum": [ "any", "10002", "10019", "10010", "10012", "10026", "10013", "10014", "10006", "10015", "10016", "10024" ], "type": "string", "description": "Filter jobs by company industry.", "default": "any" }, "sgocId": { "title": "Job function", "enum": [ "any", "1003", "1004", "1007", "1011", "1016", "1017", "1018", "1019", "1022", "1023" ], "type": "string", "description": "Filter jobs by job function / department.", "default": "any" }, "resumeKeywords": { "title": "🎯 Profile match — your resume / CV skills", "type": "array", "description": "Optional. Paste your resume/CV skills to score every job against your profile. Each entry is {\"keyword\":\"Python\",\"aliases\":[\"py\"]} (aliases optional). Adds matchScore (0–100), matchedSkills and missingSkills to each job row. This does NOT change which jobs are returned — it's a triage aid so you can skip jobs you're not qualified for." }, "deepSearch": { "title": "Deep search (expand related keywords)", "type": "boolean", "description": "Go beyond Glassdoor's single-search depth cap: after the base search, the actor harvests the related job titles Glassdoor returned and re-runs the search for each, merging results and removing duplicates by job ID. Best for keyword searches expecting many results. Increases run time and result count; still bounded by Max items.", "default": false }, "expandKeywords": { "title": "Additional expansion keywords", "type": "array", "description": "Optional extra keywords to also search and merge in when Deep search is on (e.g. synonyms or adjacent roles). Each runs as its own search; duplicates across searches are removed.", "items": { "type": "string" } }, "saveOnlyUniqueItems": { "title": "Save only unique items", "type": "boolean", "description": "Remove duplicate rows before they are saved. Deduplicates by job ID (jobs) or review ID (reviews), falling back to full-content matching. Useful for job searches, which can return the same posting across multiple pages. On pay-per-result billing this also means you are not charged twice for the same item.", "default": false }, "includes": { "title": "Include only reviews containing specific keywords.", "type": "array", "description": "Only include reviews that contain at least one of the specified keywords. For now keywords are use only on 'Cons' property of the review.", "items": { "type": "string" } }, "includeCompanyReviewStats": { "title": "Include Company Review Stats", "type": "boolean", "description": "Include company review stats in the output.", "default": false }, "includeAllReviews": { "title": "Include All Reviews.", "type": "boolean", "description": "Include all possible reviews in the output from all available languages like: 'eng', 'fra', 'por', 'spa', 'ita', 'nld', 'deu'.", "default": false }, "monitoringModeForReviews": { "title": "Run in monitoring mode where only newly reviews compared to previous runs will be scraped", "type": "boolean", "description": "If checked, it will only scrape newly reviews compared to what has been scraped in previous runs. Please turn on or check 'Include posts' setting above in case you want this feature.", "default": false }, "sortReviewsBy": { "title": "Sort review by", "enum": [ "RELEVANCE", "DATE", "RATING", "RATING_ASC" ], "type": "string", "description": "Sort reviews by criteria", "default": "RELEVANCE" }, "reviewsStartDate": { "title": "Only scrape reviews newer than [date]", "type": "string", "description": "Format should be YYYY-MM-DD, e.g., 2025-02-20" }, "includeCompanyInterviewStats": { "title": "Include Company Interview Stats.", "type": "boolean", "description": "Include company interview stats in the output.", "default": false }, "interviewsStartDate": { "title": "Only scrape interviews newer than [date]", "type": "string", "description": "Format should be YYYY-MM-DD, e.g., 2025-02-20" }, "includeCompanyBenefitsStats": { "title": "Include Company Benefits Stats.", "type": "boolean", "description": "Include company benefits stats in the output.", "default": false }, "benefitsStartDate": { "title": "Only scrape benefits newer than [date]", "type": "string", "description": "Format should be YYYY-MM-DD, e.g., 2025-02-20" }, "includeAllSalaries": { "title": "Include All Salaries.", "type": "boolean", "description": "Include all possible salaries in the output from all available languages like: 'eng', 'fra', 'por', 'spa', 'ita', 'nld', 'deu'.", "default": false }, "enrichEmails": { "title": "Enrich with company contact emails (experimental, billed per email)", "type": "boolean", "description": "If enabled, reads the company's own website (shown on its Glassdoor profile) for contact emails (e.g. info@, press@), or discovers it from the company name. Adds contactEmail + contactWebsite columns plus a detailed emailEnrichment object to company/overview records. Best-effort, billed per contact email found; only charged when an email is returned, never for misses.", "default": false }, "qualifyByPayment": { "title": "💳 Qualify by payment (flag businesses that take money online)", "type": "boolean", "description": "Requires \"Enrich with contact emails\". Scans each business's website — reusing the pages already fetched for email discovery, so no extra cost or time — for payment processors and e-commerce platforms (Stripe, Shopify, PayPal, Paddle, Lemon Squeezy, WooCommerce, Square, Chargebee and more). Adds takesPayments (is this a real paying business?), paymentProcessors (which stack), stripeLiveKey (the public key if exposed) and paymentConfidence. Turn raw contacts into monetization-qualified leads. No extra charge — included with each enriched company.", "default": false }, "reviewInsights": { "title": "📊 Review insights — instant digest per employer (no AI, billed per employer)", "type": "boolean", "description": "Adds one `review_insights` row per employer: rating breakdown & sentiment split, the recurring workplace complaint themes (management, pay, work-life balance, culture, career growth, job security…), top negative-review terms, and advice-to-management snippets. Deterministic — instant, no AI credits or keys required. Billed per employer analyzed.", "default": false }, "painPointAnalysis": { "title": "Run AI pain-point analysis (one report per employer)", "type": "boolean", "description": "Adds a single `painPointAnalysis` row per employer alongside the reviews: top complaint themes (each with severity + how often it recurs), standout strengths, attrition-risk signals, quick wins, overall sentiment and a short summary — the 'what should this employer fix' teardown, straight from real Glassdoor employee reviews. Requires a paid Apify plan; billed per employer analyzed.", "default": false }, "maxItems": { "title": "Max number items per input URL (like reviews, salaries, interviews and etc)", "type": "integer", "description": "Maximum number of items (like reviews, salaries, interviews and etc) that will be scraped FROM EACH input URL independently. If you provide 3 URLs and set maxItems to 100, you can get up to 300 total items (100 from each URL).", "default": 20000 }, "maxConcurrency": { "title": "Max Concurrency", "type": "integer", "description": "Maximum number of pages that can be processed at the same time.", "default": 7 }, "minConcurrency": { "title": "Min Concurrency", "type": "integer", "description": "Minimum number of pages that will be processed at the same time.", "default": 1 }, "maxRequestRetries": { "title": "Max Request Retries", "type": "integer", "description": "Number of times the crawler will retry a failed request before giving up.", "default": 100 }, "proxy": { "title": "Proxy configuration (optional override)", "type": "object", "description": "Leave empty — the actor already routes all traffic through its own built-in residential proxy at no extra cost to you. Only set this if you want to use your own proxies." } } }, "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 } } } } } } } } } }