{ "openapi": "3.0.1", "info": { "title": "Instahyre Jobs Scraper — India Tech Jobs & Hiring Monitor", "description": "Search and monitor India tech jobs on Instahyre — title, skills, city, apply URL and the full hiring-company profile (headcount, founded year, tagline) on every row. Track only-new postings, filter by skill, city, company or size, and add employer emails. JSON, CSV or Excel.", "version": "1.0", "x-build-id": "XkWkANonMl4N6tOp9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~instahyre-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-instahyre-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~instahyre-jobs-scraper/runs": { "post": { "operationId": "runs-sync-memo23-instahyre-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~instahyre-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-instahyre-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Skills or keywords", "type": "array", "description": "One search walk per entry — e.g. `python`, `react`, `data science`. Leave empty (with no URLs) to walk the whole board, newest first.", "items": { "type": "string" } }, "jobFunctions": { "title": "Job functions", "type": "array", "description": "Search by job function — e.g. \"product manager\", \"sales\", \"devops\", \"data science\". Each runs one search walk, exactly like Skills/keywords, and the two lists are merged. Use this to pull a whole function across companies. For Instahyre's own function slugs (server-side), use Job function slugs below.", "items": { "type": "string" } }, "jobFunctionSlugs": { "title": "Job function slugs", "type": "array", "description": "Instahyre's own function slugs, bound server-side — e.g. `backend-development`, `full-stack-development`, `data-science-machine-learning`, `frontend-development`, `product-management`. Resolved against Instahyre's live /api/v1/job_function/ list; unknown slugs are skipped with a warning, never guessed. Numeric ids are also accepted. Leave empty to not filter by function id. Default: none.", "items": { "type": "string" } }, "city": { "title": "City", "type": "string", "description": "Optional city filter shared by every search — e.g. `bangalore`, `gurgaon`, `hyderabad`, `mumbai`." }, "cities": { "title": "Cities (multiple)", "type": "array", "description": "Filter to several cities at once — a job in ANY of them passes (e.g. [\"bangalore\", \"pune\", \"gurgaon\"]). Merged with the single City field above. Instahyre ignores location server-side, so rows are filtered here and non-matches are never billed. API alias: `locations` is accepted and merged into this list (the `cities` key is unchanged).", "items": { "type": "string" } }, "remoteOnly": { "title": "Remote only", "type": "boolean", "description": "Only roles listed under Work From Home.", "default": false }, "skills": { "title": "Skills", "type": "array", "description": "Keep only jobs whose skill tags match, e.g. `react`, `python`, `sql`. Case-insensitive, partial match.", "default": [], "items": { "type": "string" } }, "skillMatch": { "title": "Skill matching", "enum": [ "any", "all" ], "type": "string", "description": "`Any` keeps a job when one listed skill matches; `All` requires every listed skill.", "default": "any" }, "keywords": { "title": "Title / keyword filter", "type": "array", "description": "Keep only jobs matching these terms across title, skills, company and location. Case-insensitive.", "default": [], "items": { "type": "string" } }, "keywordMatch": { "title": "Keyword matching", "enum": [ "any", "all" ], "type": "string", "description": "`Any` keeps a job when one keyword matches; `All` requires every keyword.", "default": "any" }, "companyNames": { "title": "Companies to include", "type": "array", "description": "Allowlist of employer names. Each name is tried first as Instahyre's exact `companies` token (one request; case-insensitive). A recognised name binds server-side so the walk never pages the rest of the board. An unrecognised name falls back to a case-insensitive partial match across the scanned pages. Dropped rows are never billed. Leave empty to keep all companies.", "default": [], "items": { "type": "string" } }, "trackCompanies": { "title": "Track companies (hiring tracker mode)", "type": "array", "description": "Exact Instahyre company names to track as a hiring profile instead of listing jobs. When this is non-empty the actor switches to tracker mode: one billed row per company with open-role count, location mix, skill mix, and (from the second scheduled run onward) new/closed job ids. Use the name Instahyre shows — e.g. from MARKET_SNAPSHOT topCompanies. Unknown names are skipped with a warning and are not billed. All other search filters are ignored in this mode.", "default": [], "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Skip any job containing one of these terms in its title, skills, company or location.", "default": [], "items": { "type": "string" } }, "diversityEmployersOnly": { "title": "Diversity employers only", "type": "boolean", "description": "Keep only jobs from employers Instahyre flags with a diversity-hiring badge (`isDiversityEmployer: true` on the list payload). Dropped rows are never billed. Default: false.", "default": false }, "companySize": { "title": "Company size", "enum": [ "any", "small", "medium", "large" ], "type": "string", "description": "Filter by employer headcount band.", "default": "any" }, "jobType": { "title": "Job type", "enum": [ "any", "full_time", "internship" ], "type": "string", "description": "Filter by employment type. Job type only appears on the detail page, so this turns on 'Fetch job details' automatically (those detail fetches are billed).", "default": "any" }, "startUrls": { "title": "Instahyre URLs (optional — override the search fields)", "type": "array", "description": "Listing pages (`instahyre.com/python-jobs-in-bangalore/`) or job detail pages (`/job-{id}-…/`). When present, the search fields above are ignored.", "default": [], "items": { "type": "string" } }, "enrichEmails": { "title": "Find employer emails (billed as additional data)", "type": "boolean", "description": "Discover the hiring company's website and harvest a contact email from it. Billed per row with a found email — see the pricing tab.", "default": false }, "includeDetails": { "title": "Fetch job details (description, employment type, dates)", "type": "boolean", "description": "Fetch each job's public page and add the full description, employment type, exact location and posting dates. One extra request per job.", "default": false }, "monitoringMode": { "title": "Monitoring mode (only return jobs not seen on previous runs)", "type": "boolean", "description": "When enabled, jobs whose Instahyre ID has already been delivered to you are skipped unless their public fields changed (`changeType` = `updated`) or you turn on Include unchanged. The first run after enabling monitoring returns every match and builds your baseline; every later run returns new and updated postings. Combine with Apify's scheduler for a 'jobs posted since last run' feed.", "default": false }, "resetMonitoringState": { "title": "Reset monitoring state (one-shot)", "type": "boolean", "description": "One-shot: clear the saved 'jobs already seen' record at the start of this run. Use after changing the search, to rebuild the baseline, or to recover from a missed delivery. No effect when monitoring mode is off.", "default": false }, "monitorStateName": { "title": "Monitor state name (independent watches)", "type": "string", "description": "Name this monitor so one account can run several independent 'only-new' watches without their seen-job history colliding — e.g. \"bangalore-eng\" for one schedule and \"remote-sales\" for another. Leave empty for a single default baseline. Only used when Monitoring mode is on. API alias: `stateName`." }, "emitBaseline": { "title": "Emit baseline on first monitoring run", "type": "boolean", "description": "Only used with Monitoring mode. ON (default): the first run returns every current match and remembers them. OFF: the first run silently records what exists now and emits nothing, so every later run returns only jobs that appeared after it — no baseline flood, no first-run billing.", "default": true }, "includeUnchanged": { "title": "Include unchanged jobs (monitoring)", "type": "boolean", "description": "Only used with Monitoring mode. OFF (default): return only new and updated postings. ON: also re-emit jobs already seen whose public fields did not change, tagged `changeType` = `unchanged`, so every run is a full snapshot. Re-emitted rows are billed like any other.", "default": false }, "includeRemoved": { "title": "Include removed jobs (monitoring)", "type": "boolean", "description": "Only used with Monitoring mode. OFF (default) so existing only-new schedules are not surprise-billed. ON: after a completed (uncapped) scan, emit a stub row with `changeType` = `removed` for each job id that was present on the last complete scan and is missing now. A run that hits Max results or Max pages never marks jobs as removed. Each removed stub is billed as a job. Default: false.", "default": false }, "maxItems": { "title": "Maximum results", "minimum": 1, "type": "integer", "description": "Hard cap on billed rows for the run — your spend guard. API alias: `maxJobs`.", "default": 1000 }, "maxPages": { "title": "Max pages per search", "minimum": 1, "type": "integer", "description": "Cap the crawl at this many result pages per search term (~35 jobs each). Optional — Max results still limits billed rows; this bounds how deep the walk goes regardless of matches." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Parallel fetches (the API pages at 35 rows per request, so most runs need very few).", "default": 10 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Retries per request before it is skipped.", "default": 5 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "The site answers a direct connection (the built-in retry ladder adds a residential fallback automatically). Configure a proxy only if you want all traffic through it. API alias: `proxyConfiguration`." } } }, "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 } } } } } } } } } }