{ "openapi": "3.0.1", "info": { "title": "IrishJobs.ie [$1.45/1K💰] Ireland Jobs Scraper + Salary", "description": "Search IrishJobs.ie by keyword, county & salary — or any URL. Structured salary bands, skills, employer + geo. Only-new-jobs mode for scheduled runs, Telegram/Slack/Discord/WhatsApp alerts, AI-agent compact output, optional contact-email enrichment. JSON/CSV out.", "version": "0.1", "x-build-id": "YJzfEy9mitC1l3Y3K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~irishjobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-irishjobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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~irishjobs-scraper/runs": { "post": { "operationId": "runs-sync-memo23-irishjobs-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~irishjobs-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-irishjobs-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": { "query": { "title": "🔍 Search keyword", "type": "string", "description": "Job title, skill, or keyword — e.g. `software engineer`, `accountant`, `nurse`. Leave empty to browse all jobs (optionally narrowed by location/county). Add more keywords in **Batch keywords** below to run several searches in one go." }, "queries": { "title": "Batch keywords (optional)", "type": "array", "description": "Extra keyword searches, one per line — each runs as its own search sharing the same location and filters, into one dataset. `maxItems` applies per search.", "items": { "type": "string" } }, "location": { "title": "📍 Location", "type": "string", "description": "City, town, or region in Ireland — e.g. `Dublin`, `Cork`, `Portlaoise`. Leave empty to search nationwide. Ignored when a County is selected below." }, "county": { "title": "🗺️ County", "enum": [ "dublin", "cork", "galway", "limerick", "waterford", "kilkenny", "wexford", "wicklow", "kildare", "meath", "louth", "kerry", "clare", "tipperary", "mayo", "sligo", "donegal", "cavan", "monaghan", "roscommon", "leitrim", "longford", "westmeath", "offaly", "laois", "carlow" ], "type": "string", "description": "Filter by Irish county — matches the site's own county pages. Overrides Location when set." }, "radius": { "title": "🧭 Radius (km)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Search radius in km around the Location (requires a location). The site honours values like 5, 10, 20, 30, 40, 50, 75, 100." }, "sort": { "title": "↕️ Sort by", "enum": [ "relevance", "date", "salary_high", "salary_low", "distance" ], "type": "string", "description": "Result order. `date` = newest first — the right choice for monitoring feeds.", "default": "relevance" }, "postedWithin": { "title": "🕐 Posted within (days)", "minimum": 0, "type": "integer", "description": "Only jobs posted in the last N days. The site supports windows of 1, 3, 7, or 14 — other values snap UP to the next window (5 → 7). Values above 14 disable the filter. For sharper recency (hours/minutes) use `maxAgeMinutes` in Filters." }, "minSalary": { "title": "💶 Minimum salary (EUR/year)", "minimum": 0, "type": "integer", "description": "Only jobs with an annual salary of at least this (the site's own \"at least\" facet — e.g. 40000). Jobs without a disclosed salary are excluded by the site when this is set." }, "companyType": { "title": "🏢 Company type", "enum": [ "employer", "agency" ], "type": "string", "description": "Only agency postings, or only direct employers. Leave empty for both." }, "startUrls": { "title": "📌 IrishJobs.ie URLs", "type": "array", "description": "Direct listing URLs (e.g. `https://www.irishjobs.ie/jobs/dublin`, `/jobs/software-engineer/in-cork`, `/jobs-at/{company}`) and/or job-detail URLs (`/job/{slug}/{company}-job{id}`). Every filter the IrishJobs web search supports works via the query string too. Scraped IN ADDITION to any keyword search above. Sister sites: for totaljobs.com use [TotalJobs Scraper](https://apify.com/memo23/totaljobs-scraper), for stepstone.de/at/fr use [StepStone Scraper](https://apify.com/memo23/stepstone-search-cheerio-ppr).", "items": { "type": "string" } }, "remoteOnly": { "title": "🏠 Remote only", "type": "boolean", "description": "Only fully remote positions (listing tagged \"Remote\" or TELECOMMUTE). Hybrid roles do NOT pass. Applied after fetch — IrishJobs has no server-side remote facet — so runs scan up to `maxItems` jobs and emit the remote subset.", "default": false }, "includeKeywords": { "title": "✅ Include keywords", "type": "object", "description": "Require at least one of these keywords in title/description/skills. Example: `{\"keywords\":[\"React\",\"Node.js\"],\"matchTitle\":true,\"matchDescription\":true,\"matchSkills\":true}` (the three match flags default to true)." }, "excludeKeywords": { "title": "🚫 Exclude keywords", "type": "object", "description": "Drop jobs containing any of these keywords. Same shape as Include keywords: `{\"keywords\":[\"PHP\",\"WordPress\"]}`." }, "fromDate": { "title": "📅 From date", "type": "string", "description": "Only jobs posted on or after this date — `YYYY-MM-DD` or full ISO-8601." }, "toDate": { "title": "📅 To date", "type": "string", "description": "Only jobs posted on or before this date — `YYYY-MM-DD` (inclusive through end of day) or ISO-8601." }, "maxAgeMinutes": { "title": "⏰ Max age (minutes)", "minimum": 0, "type": "integer", "description": "Only jobs posted within the last N minutes. 0 = off. Pair with an hourly schedule (e.g. 60) + `sort: date` for a real-time feed.", "default": 0 }, "customFilters": { "title": "🔧 Custom filters (advanced)", "type": "array", "description": "Rules on any output field, dot-notation supported. Each rule: `{\"field\":\"salary.min\",\"op\":\"gte\",\"value\":50000}`. Ops: includes, notIncludes, equals, notEquals, gt, gte, lt, lte. Example: `[{\"field\":\"location.locality\",\"op\":\"includes\",\"value\":\"Dublin\"},{\"field\":\"description\",\"op\":\"notIncludes\",\"value\":\"php\"}]`." }, "skipReposts": { "title": "♻️ Only new jobs (skip reposts)", "type": "boolean", "description": "Remember every job emitted and skip it on future runs (90-day window). Skipped jobs are dropped BEFORE the page fetch — never charged, and they don't consume `maxItems`, so scheduled runs keep digging until they find genuinely new postings. Perfect with a daily/hourly schedule + notifications.", "default": false }, "dedupStoreName": { "title": "Dedup store name", "type": "string", "description": "Named storage for the seen-jobs memory (default `irishjobs-seen-jobs`). Use different names to keep separate searches' memories apart, or the same name to share one memory across tasks." }, "telegramToken": { "title": "🤖 Telegram bot token", "type": "string", "description": "Bot token from @BotFather, e.g. `110201543:AAHdqTc…`. Requires Telegram chat ID below." }, "telegramChatId": { "title": "💬 Telegram chat ID", "type": "string", "description": "Chat or channel the bot posts to, e.g. `-1001234567890` (get yours from @userinfobot)." }, "discordWebhookUrl": { "title": "🎮 Discord webhook URL", "type": "string", "description": "Channel webhook from Server Settings → Integrations → Webhooks." }, "slackWebhookUrl": { "title": "💼 Slack webhook URL", "type": "string", "description": "Incoming webhook from api.slack.com/messaging/webhooks." }, "whatsappPhoneNumberId": { "title": "📱 WhatsApp phone number ID", "type": "string", "description": "Meta Cloud API phone number ID (the numeric ID next to your business number — NOT the phone number). Requires the access token and recipient below." }, "whatsappAccessToken": { "title": "🔐 WhatsApp access token", "type": "string", "description": "Meta Cloud API token with `whatsapp_business_messaging` scope." }, "whatsappTo": { "title": "📨 WhatsApp recipient", "type": "string", "description": "Recipient phone in international format, e.g. `+353861234567`. Meta only delivers free-form text within 24h of the recipient's last message to your business number." }, "webhookUrl": { "title": "🪝 Generic webhook URL", "type": "string", "description": "Any HTTPS endpoint — receives a JSON POST with counts, dataset link, and the newest items. The universal escape hatch for n8n / Make / Zapier / your own backend." }, "webhookHeaders": { "title": "Webhook headers", "type": "object", "description": "Optional extra HTTP headers for the generic webhook, e.g. `{\"Authorization\": \"Bearer abc123\"}`." }, "notificationLimit": { "title": "Items per notification", "minimum": 1, "maximum": 25, "type": "integer", "description": "Max jobs listed inside a notification message. Default 10, cap 25.", "default": 10 }, "notifyOnlyChanges": { "title": "Notify only on new results", "type": "boolean", "description": "Stay silent when a run found nothing (new). Disable to get a ping after every run.", "default": true }, "descriptionFormat": { "title": "📝 Description formats", "enum": [ "all", "text", "html", "markdown" ], "type": "string", "description": "Which derived description fields to add to each row: plain text, clean HTML, Markdown, or all three. The original `description` field is always kept.", "default": "all" }, "descriptionMaxLength": { "title": "✂️ Description max length", "minimum": 0, "type": "integer", "description": "Truncate every description field to this many characters ('...' appended). 0 = no truncation. Pairs well with compact mode for token budgets.", "default": 0 }, "compact": { "title": "📦 Compact output", "type": "boolean", "description": "Flat 15-field core rows — jobId, title, company, location, salary band, skills, dates, URLs, plain-text description. Built for AI-agent and MCP workflows where token budgets matter. Email-enrichment columns are kept when enabled.", "default": false }, "outputFields": { "title": "🎛️ Output fields", "type": "array", "description": "Keep only these fields, dot-notation supported — e.g. `title`, `salary.min`, `employer.name`, `location.locality`. Empty = all fields.", "items": { "type": "string" } }, "excludeEmptyFields": { "title": "Exclude empty fields", "type": "boolean", "description": "Drop null / empty-string / empty-array fields from each row — smaller payloads for agents and dashboards.", "default": false }, "enrichEmails": { "title": "📧 Enrich with contact emails (billed per email)", "type": "boolean", "description": "Finds a contact email for each hiring employer (discovered from the company name, then its website is scanned). Adds contactEmail + contactWebsite columns plus a detailed emailEnrichment object. 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, paymentProcessors, stripeLiveKey and paymentConfidence. No extra charge.", "default": false }, "maxItems": { "title": "Max jobs per search / listing URL", "minimum": 1, "type": "integer", "description": "Maximum job rows emitted **per search or listing URL**. 2 keywords with `maxItems: 100` → up to 200 total rows. Direct detail URLs always emit 1 row each. Each row is one paid dataset item. With `skipReposts` on, skipped known jobs do NOT count — the crawl digs until it finds this many NEW jobs (or the site runs out). Default 1000. Free-tier users are additionally capped at 100 total rows.", "default": 1000 }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel HTTP requests for detail-page fetches. Concurrency 3-6 is the sweet spot through the built-in residential proxy.", "default": 4 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Per-URL retry budget on network errors, proxy CONNECT failures, HTTP/2 stream resets, and transient 4xx responses. Each retry rotates the proxy session. Default 6.", "default": 6 }, "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 } } } } } } } } } }