{ "openapi": "3.0.1", "info": { "title": "JobStreet Scraper โ€” MY, SG, ID & PH Job Listings", "description": "Scrape JobStreet Malaysia, Singapore, Indonesia & the Philippines (SEEK platform). Salary, full descriptions, company intelligence (logo, reviews, perks), and optional applicant-demand signals to find low-competition roles. Incremental mode emits only new and changed listings.", "version": "0.3", "x-build-id": "zjZhqgJdZ1MQrtAzk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blackfalcondata~jobstreet-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blackfalcondata-jobstreet-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blackfalcondata~jobstreet-scraper/runs": { "post": { "operationId": "runs-sync-blackfalcondata-jobstreet-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blackfalcondata~jobstreet-scraper/run-sync": { "post": { "operationId": "run-sync-blackfalcondata-jobstreet-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "๐Ÿ” Search Term(s)", "type": "string", "description": "Job search keywords. For a single term: `software engineer`. For multiple terms (OR โ€” runs each as a separate search and merges results, deduplicated by job ID), use a JSON array, for example: `[\"ERP Implementation\", \"ERP Initiatives\"]`." }, "country": { "title": "๐ŸŒ Country", "enum": [ "MY", "SG", "ID", "PH" ], "type": "string", "description": "Which JobStreet market to search.", "default": "MY" }, "location": { "title": "๐Ÿ“ Location", "type": "string", "description": "City, state, or region. For a single location: `Kuala Lumpur`. For multiple locations, use a JSON array, for example: `[\"Kuala Lumpur\", \"Selangor\", \"Jakarta\"]`." }, "startUrls": { "title": "๐Ÿ”— Start URLs", "type": "array", "description": "Direct JobStreet search or job-detail URLs. โœ… Valid shapes: `https://my.jobstreet.com/jobs` (all jobs), `https://my.jobstreet.com/jobs-in-information-technology` (category), `https://sg.jobstreet.com/job/12345` (single job). โŒ The bare homepage (`https://my.jobstreet.com`) is **not** accepted โ€” use a `/jobs` or `/job/` path. Added on top of any query/location search (not a replacement) โ€” each URL becomes an additional source in the same run. Detail URLs (`/job/`) skip SERP entirely; search URLs paginate like a query. The market is derived from the URL host (`sg.` โ†’ SG, `id.` โ†’ ID, `ph.` โ†’ PH, otherwise MY). For search URLs, `searchQuery` is derived from `keywords` or `/jobs/`; filter-only URLs without keywords return `searchQuery: \"\"`.", "items": { "type": "string" } }, "maxResults": { "title": "๐Ÿ’ฏ Max Results", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum total job listings to emit to the dataset. 0 = unlimited. Applied after post-filters โ€” if you use `includeKeywords` / `excludeKeywords` / `customFilters` / date filters, set this to your final cap, not your collection cap. Cost control: Apify charges per emitted record, so this is your primary knob. If both maxResults and maxPages are set, the lower cap wins.", "default": 25 }, "maxPages": { "title": "๐Ÿ“„ Max Pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum SERP pages to scrape per search source. Each page has ~22-32 jobs depending on market. In incremental mode this also defines the tracked search universe โ€” set high enough to cover every listing you want monitored; jobs beyond this page window fall outside the state and won't be marked EXPIRED. This is a defensive safety bound โ€” use maxResults for cost control. If both maxResults and maxPages are set, the lower cap wins.", "default": 5 }, "sortMode": { "title": "Sort By", "enum": [ "relevance", "date" ], "type": "string", "description": "Sort search results by relevance or date.", "default": "relevance" }, "dateRange": { "title": "Date Range", "enum": [ "", "1", "3", "7", "14", "31" ], "type": "string", "description": "Filter by posting date (JobStreet date range code, e.g. \"1\" = last 24h, \"3\" = last 3 days, \"7\" = last 7 days, \"14\" = last 14 days, \"31\" = last 31 days)." }, "workType": { "title": "Work Type", "enum": [ "", "242", "243", "244", "245" ], "type": "string", "description": "Filter by employment type code." }, "workArrangement": { "title": "Work Arrangement", "enum": [ "", "1", "2", "3" ], "type": "string", "description": "Filter by work arrangement code." }, "classification": { "title": "Classification", "type": "string", "description": "JobStreet job classification ID (e.g. \"6281\" = Information & Communication Technology, \"1203\" = Accounting, \"6043\" = Healthcare & Medical). Find IDs in JobStreet category URLs." }, "subClassification": { "title": "Sub-Classification", "type": "string", "description": "JobStreet job sub-classification ID (e.g. \"6287\" = Developers/Programmers under ICT). Requires a parent classification to work." }, "salaryMin": { "title": "๐Ÿ’ฐ Minimum Salary", "minimum": 0, "type": "integer", "description": "JobStreet's own salary-bracket filter โ€” minimum value in the listing's local currency (MYR for MY, SGD for SG, IDR for ID, PHP for PH). Applied server-side by JobStreet; matched listings may still hide their actual salary text. Combine with `salaryMax` for a range." }, "salaryMax": { "title": "๐Ÿ’ฐ Maximum Salary", "minimum": 0, "type": "integer", "description": "JobStreet's own salary-bracket filter โ€” maximum value in the listing's local currency (MYR for MY, SGD for SG, IDR for ID, PHP for PH). Applied server-side by JobStreet; matched listings may still hide their actual salary text. Combine with `salaryMin` for a range." }, "includeKeywords": { "title": "Include Keywords", "type": "array", "description": "Only keep jobs that contain at least one of these keywords anywhere in the listing โ€” title, company, location, category, sub-category, work type, work arrangement, salary text, teaser, bullets, or description. Broad match by design โ€” use exclude keywords below to narrow.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude Keywords", "type": "array", "description": "Drop jobs that contain any of these keywords in title, company, teaser, bullets, or description. Narrow scope by design โ€” does NOT check location, salary text, or employment type, so \"remote\" won't drop jobs with \"remote work allowance\" in salary or \"not remote\" in location.", "items": { "type": "string" } }, "keywordMatchTitle": { "title": "๐ŸŽฏ Match Job Title", "type": "boolean", "description": "When any keyword match toggle is set, include/exclude keyword filters match only toggled fields, for both include and exclude. Leave all toggles empty to use default broad keyword matching. Use customFilters for location, employmentType, workArrangement, or salaryText." }, "keywordMatchCompany": { "title": "๐Ÿข Match Company", "type": "boolean", "description": "Include company name in include/exclude keyword matching when keyword match toggles are used." }, "keywordMatchDescription": { "title": "๐Ÿ“„ Match Description", "type": "boolean", "description": "Include teaser and full description in include/exclude keyword matching when keyword match toggles are used." }, "keywordMatchCategory": { "title": "๐Ÿ—‚๏ธ Match Category", "type": "boolean", "description": "Include category and sub-category in include/exclude keyword matching when keyword match toggles are used." }, "keywordMatchBulletPoints": { "title": "โ€ข Match Bullet Points", "type": "boolean", "description": "Include listing bullet points in include/exclude keyword matching when keyword match toggles are used." }, "customFilters": { "title": "๐Ÿ”ง Custom Filters", "type": "array", "description": "Advanced post-filter rules applied to output fields after collection. Each rule is {\"field\":\"salaryMin\",\"op\":\"gte\",\"value\":120000}. Supported ops: includes, notIncludes, equals, notEquals, gt, gte, lt, lte. equals/notEquals are intended for scalar fields; use includes/notIncludes for arrays such as bulletPoints or extractedUrls. Invalid fields or operators fail fast.", "items": { "type": "object" } }, "fromDate": { "title": "From Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}(T\\d{2}:\\d{2}(:\\d{2})?(\\.\\d{3})?(Z|[+-]\\d{2}:?\\d{2})?)?$", "type": "string", "description": "Only keep jobs posted at or after this date/time. Use ISO date or datetime (e.g. \"2026-05-01\" or \"2026-05-01T00:00:00Z\")." }, "toDate": { "title": "To Date", "pattern": "^\\d{4}-\\d{2}-\\d{2}(T\\d{2}:\\d{2}(:\\d{2})?(\\.\\d{3})?(Z|[+-]\\d{2}:?\\d{2})?)?$", "type": "string", "description": "Only keep jobs posted at or before this date/time. Use ISO date or datetime." }, "maxAgeMinutes": { "title": "Max Age Minutes", "minimum": 0, "type": "integer", "description": "Only keep jobs posted within this many minutes from the scrape timestamp." }, "includeDetails": { "title": "๐Ÿ“‹ Include Full Details", "type": "boolean", "description": "Fetch each job's detail page for full description, structured location, salary data, company profile, and more.", "default": true }, "includeApplicantInsights": { "title": "๐Ÿ‘ฅ Include Applicant Demand", "type": "boolean", "description": "Add applicant-demand fields to each job: `applicantCount` (number of applicants), `applicantVolumeLabel` (e.g. \"High application volume\"), and `coverLetterPercentage`. Useful for spotting low-competition roles and gauging hiring demand. Adds one extra request per job, so it is slightly slower. Coverage is partial โ€” only standard-apply listings expose this data; jobs that apply on an external site return `null` for these fields.", "default": false }, "descriptionMaxLength": { "title": "โœ‚๏ธ Description Max Length", "minimum": 0, "type": "integer", "description": "Truncate job description to N characters. 0 = no truncation.", "default": 0 }, "compact": { "title": "๐Ÿ“ฆ Compact Output", "type": "boolean", "description": "Output only core fields (jobId, title, company, location, salary, score, category, URL, dates). Ideal for AI-agent and MCP workflows.", "default": false }, "descriptionFormat": { "title": "Description format", "enum": [ "all", "text", "html", "markdown" ], "type": "string", "description": "Pick a single description representation. `all` keeps every variant; `text` / `html` / `markdown` drop the others.", "default": "all" }, "excludeEmptyFields": { "title": "Exclude empty fields from output", "type": "boolean", "description": "Drop null, empty-string, and empty-array fields from each record before push. Smaller payloads for AI agents and dashboards.", "default": false }, "incrementalMode": { "title": "โ™ป๏ธ Incremental Mode", "type": "boolean", "description": "Track changes between runs. Each record carries a `changeType` of NEW / UPDATED / UNCHANGED / REAPPEARED / EXPIRED. Default emits NEW + UPDATED + REAPPEARED only; use `emitUnchanged` / `emitExpired` to opt into the others. `stateKey` is optional โ€” when empty, a stable key is auto-derived from your search inputs so different query/filter combinations get isolated state.", "default": false }, "stateKey": { "title": "๐Ÿ”‘ State Key", "type": "string", "description": "Optional stable identifier for the tracked search universe. Leave empty to auto-derive a stable identifier from your search inputs โ€” different keyword/location/filter combinations get isolated state automatically." }, "emitUnchanged": { "title": "โ™ป๏ธ Emit Unchanged Records", "type": "boolean", "description": "When incremental, also emit records that haven't changed since last run.", "default": false }, "emitExpired": { "title": "โšฐ๏ธ Emit Expired Records", "type": "boolean", "description": "When incremental, also emit records no longer found in search results.", "default": false }, "skipReposts": { "title": "๐Ÿšซ Skip Reposts", "type": "boolean", "description": "When incremental, skip jobs that are reposts of previously seen (now expired) jobs.", "default": false }, "telegramToken": { "title": "๐Ÿค– Telegram Bot Token", "type": "string", "description": "Telegram bot token from @BotFather. Required for Telegram notifications." }, "telegramChatId": { "title": "๐Ÿ’ฌ Telegram Chat ID", "type": "string", "description": "Telegram chat or channel ID where alerts are sent (e.g. \"-100123456789\" for a private group, or \"@yourchannel\")." }, "discordWebhookUrl": { "title": "๐ŸŽฎ Discord Webhook URL", "type": "string", "description": "Discord incoming webhook URL. Get one from Server Settings โ†’ Integrations โ†’ Webhooks." }, "slackWebhookUrl": { "title": "๐Ÿ’ผ Slack Webhook URL", "type": "string", "description": "Slack incoming webhook URL. Create at api.slack.com/messaging/webhooks." }, "whatsappPhoneNumberId": { "title": "๐Ÿ“ฑ WhatsApp Phone Number ID", "type": "string", "description": "WhatsApp Business phone number ID from Meta Business Manager (NOT the phone number itself โ€” the numeric ID shown next to your business number). Free service-conversation messages within 24 hours of last user-initiated contact." }, "whatsappAccessToken": { "title": "๐Ÿ” WhatsApp Access Token", "type": "string", "description": "Meta Cloud API access token with `whatsapp_business_messaging` scope. Get a permanent token from a system user in Meta Business Manager." }, "whatsappTo": { "title": "๐Ÿ“จ WhatsApp Recipient", "type": "string", "description": "Recipient phone in E.164 format (e.g. +60123456789). Recipient must have messaged your business number within the last 24 hours โ€” outside that window, free-form text is rejected by Meta." }, "webhookUrl": { "title": "๐Ÿช Generic Webhook URL", "type": "string", "description": "Universal escape hatch for n8n / Make / Zapier / custom HTTP backends. Receives a JSON POST `{ metadata, items }` per run. Single attempt, 15 s timeout." }, "webhookHeaders": { "title": "๐Ÿช Webhook Headers (optional)", "type": "object", "description": "Additional HTTP headers sent with the generic webhook POST (e.g. `{\"Authorization\":\"Bearer ...\"}`). Body is JSON; default `Content-Type: application/json` is set unless you override it here." }, "notificationLimit": { "title": "๐Ÿ“Š Max Jobs Per Notification", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of jobs included in each notification message (1โ€“20). Excess jobs are still in the dataset; notifications get a summary line.", "default": 5 }, "notifyOnlyChanges": { "title": "๐Ÿ”„ Notify Only New/Updated", "type": "boolean", "description": "When Incremental Mode is on, only send notifications for jobs with `changeType` NEW or UPDATED. REAPPEARED, UNCHANGED, and EXPIRED records are dropped from notifications but still go to the dataset. No effect outside incremental mode.", "default": false }, "includeRunSummary": { "title": "Include Run Summary", "type": "boolean", "description": "Prepend a one-line summary to each notification message: search label (`JobStreet: ยท `), total emitted record count, and run timestamp. Disable to send raw job items only.", "default": true } } }, "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 } } } } } } } } } }