{ "openapi": "3.0.1", "info": { "title": "104.com.tw Taiwan Jobs Scraper", "description": "Scrape jobs from Taiwan's 104.com.tw — salary, location, company and HR contact details. Provisional listing; final SEO copy set post-verification.", "version": "0.1", "x-build-id": "JvClNT2dpQJEKTi6u" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/corvuslab~taiwan104-jobs-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-corvuslab-taiwan104-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/corvuslab~taiwan104-jobs-scraper/runs": { "post": { "operationId": "runs-sync-corvuslab-taiwan104-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/corvuslab~taiwan104-jobs-scraper/run-sync": { "post": { "operationId": "run-sync-corvuslab-taiwan104-jobs-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "🔑 Search keywords", "type": "string", "description": "Keywords to search for (Chinese or English), e.g. 「工程師」 or \"python\". Separate multiple searches with commas — each runs as its own search and results are merged and de-duplicated. Leave empty to scrape the broadest listing." }, "startUrls": { "title": "📋 Start URLs", "type": "array", "description": "Paste 104.com.tw search URLs (…/jobs/search/…) or job-detail URLs (…/job/) to scrape directly.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxResults": { "title": "🔢 Max results", "minimum": 0, "type": "integer", "description": "Maximum number of jobs to return across all searches. Set 0 for unlimited (bounded by how many the search has).", "default": 25 }, "ignoreUrlFailures": { "title": "⏭️ Ignore URL failures", "type": "boolean", "description": "Skip URLs that cannot be interpreted instead of failing the whole run.", "default": true }, "area": { "title": "📍 Regions", "type": "array", "description": "Limit results to one or more Taiwan regions. Leave empty for nationwide.", "items": { "type": "string", "enum": [ "6001001000", "6001002000", "6001005000", "6001008000", "6001014000", "6001016000", "6001006000", "6001004000", "6001003000", "6001007000", "6001010000", "6001011000", "6001012000", "6001013000", "6001018000", "6001019000", "6001020000", "6001021000", "6001022000", "6001023000" ], "enumTitles": [ "台北市 Taipei City", "新北市 New Taipei City", "桃園市 Taoyuan City", "台中市 Taichung City", "台南市 Tainan City", "高雄市 Kaohsiung City", "新竹縣市 Hsinchu", "基隆市 Keelung City", "宜蘭縣 Yilan County", "苗栗縣 Miaoli County", "彰化縣 Changhua County", "南投縣 Nantou County", "雲林縣 Yunlin County", "嘉義縣市 Chiayi", "屏東縣 Pingtung County", "台東縣 Taitung County", "花蓮縣 Hualien County", "澎湖縣 Penghu County", "金門縣 Kinmen County", "連江縣 Lienchiang County" ] } }, "remoteWork": { "title": "🏠 Remote jobs only", "type": "boolean", "description": "Limit results to remote-friendly positions.", "default": false }, "datePosted": { "title": "🗓️ Posted within", "enum": [ "0", "3", "7", "14", "30" ], "type": "string", "description": "Keep only jobs published within this many days.", "default": "0" }, "minExperience": { "title": "🧑‍💼 Minimum experience", "enum": [ "0", "1", "3", "5", "10" ], "type": "string", "description": "Keep only jobs requiring at least this many years of experience.", "default": "0" }, "sortBy": { "title": "↕️ Sort by", "enum": [ "relevance", "date", "salary" ], "type": "string", "description": "Order in which 104 returns results.", "default": "relevance" }, "requireContact": { "title": "📇 Require contact details", "enum": [ "off", "email", "phone", "either", "both" ], "type": "string", "description": "Keep only jobs that include an HR contact. off = keep everything; email / phone = require that channel; either = at least one; both = email and phone. Screened at emit time, so it also trims what you're billed for. Requires detail fetching.", "default": "off" }, "includeApplicantInsights": { "title": "📊 Include applicant-demand signals", "type": "boolean", "description": "Add how many people have applied and the recruiter's response score — handy for spotting low-competition, fast-replying employers.", "default": true }, "includeDetails": { "title": "🔬 Fetch full details", "type": "boolean", "description": "Fetch each job's detail page for the full description, requirements, welfare benefits, close date and HR contact email/phone. Turn off for the fastest, cheapest runs.", "default": true }, "descriptionFormat": { "title": "📝 Description format", "enum": [ "all", "text", "html", "markdown" ], "type": "string", "description": "Which representation(s) of the job description to include.", "default": "all" }, "descriptionMaxLength": { "title": "✂️ Description max length", "minimum": 0, "type": "integer", "description": "Truncate each description to this many characters. Leave empty for full text." }, "compact": { "title": "📦 Compact records", "type": "boolean", "description": "Emit only the core fields (title, company, salary, location, applicant count). Ideal for AI agents and MCP clients.", "default": false }, "excludeEmptyFields": { "title": "🧹 Drop empty fields", "type": "boolean", "description": "Remove null, empty-string and empty-array fields from each record.", "default": false }, "incrementalMode": { "title": "♻️ Incremental mode", "type": "boolean", "description": "Track state between runs and tag every job with a changeType (NEW / UPDATED / UNCHANGED / EXPIRED).", "default": false }, "stateKey": { "title": "🗝️ State key", "type": "string", "description": "Stable name for the tracked search. Leave empty to derive one automatically from your search settings." }, "emitUnchanged": { "title": "🔁 Include unchanged jobs", "type": "boolean", "description": "Also emit jobs that have not changed since the previous run.", "default": false }, "emitExpired": { "title": "🗑️ Include expired jobs", "type": "boolean", "description": "Emit jobs that were present last run but are gone now.", "default": false }, "telegramToken": { "title": "💬 Telegram bot token", "type": "string", "description": "Bot token from @BotFather." }, "telegramChatId": { "title": "🆔 Telegram chat ID", "type": "string", "description": "Chat or channel ID, e.g. \"-100123456789\" or \"@yourchannel\"." }, "slackWebhookUrl": { "title": "💼 Slack webhook URL", "type": "string", "description": "Slack incoming-webhook URL." }, "discordWebhookUrl": { "title": "🎮 Discord webhook URL", "type": "string", "description": "Discord incoming-webhook URL." }, "webhookUrl": { "title": "🪝 Webhook URL", "type": "string", "description": "Any HTTPS endpoint. Receives a JSON POST with the matched jobs — works with n8n, Make and Zapier." }, "webhookHeaders": { "title": "🧾 Webhook headers", "type": "object", "description": "Extra headers for the webhook request, e.g. {\"Authorization\": \"Bearer xyz\"}." }, "notificationLimit": { "title": "🔢 Jobs per notification", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many jobs to include in each notification message.", "default": 5 }, "proxyConfiguration": { "title": "🌐 Proxy configuration", "type": "object", "description": "Optional. 104.com.tw is scraped over direct HTTP with no proxy — leave this off for the cheapest runs. Enable a proxy only if you hit rate limits at very high volume.", "default": { "useApifyProxy": false } }, "maxRequestRetries": { "title": "🔄 Max request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many times to retry a failed request before giving up on it.", "default": 3 } } }, "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 } } } } } } } } } }