{ "openapi": "3.0.1", "info": { "title": "Detik News AI Scraper", "description": "Scrapes news articles from Detik.com, including headline, author, publish date, category, images and full article text. Additionally use AI to paraphrase, summarize and get sentiment analysis value.", "version": "1.0", "x-build-id": "C6DJzfg6FEhO0XLOq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/confidential_gnat~detik-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-confidential_gnat-detik-news-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/confidential_gnat~detik-news-scraper/runs": { "post": { "operationId": "runs-sync-confidential_gnat-detik-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/confidential_gnat~detik-news-scraper/run-sync": { "post": { "operationId": "run-sync-confidential_gnat-detik-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Detik listing URLs (channel front pages, /indeks pages or search results) or direct article URLs. The type of each URL is detected automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max items per start URL", "type": "integer", "description": "Maximum number of articles to scrape for each start URL.", "default": 5 }, "scrapeWholeSite": { "title": "Scrape the whole site", "type": "boolean", "description": "Ignore Start URLs and crawl the index pages of every major Detik channel instead.", "default": false }, "cacheProjectName": { "title": "Cache project name", "type": "string", "description": "Optional. When set, articles already scraped under this project name in a previous run are skipped instead of being scraped again." }, "aiEnabled": { "title": "Enable AI enrichment", "type": "boolean", "description": "Use an AI model to paraphrase each article, summarize it, and analyse its sentiment. Enrichment runs on this Actor's own AI credits and is billed as part of the run.", "default": false }, "aiModels": { "title": "AI models", "type": "array", "description": "Models tried in order — the first one that returns a usable result is used, so the ones below it act as fallbacks. More models means more resilience, never extra cost on the happy path.", "items": { "type": "string", "enum": [ "openai/gpt-4o-mini", "anthropic/claude-3.5-haiku", "google/gemini-2.0-flash-001", "meta-llama/llama-3.1-8b-instruct", "mistralai/mistral-small" ] }, "default": [ "openai/gpt-4o-mini" ] }, "aiFeatures": { "title": "AI features", "type": "array", "description": "Which enrichments to request. All selected features come back from a single model call per article.", "items": { "type": "string", "enum": [ "summarize", "paraphrase", "sentiment", "keywords", "custom" ], "enumTitles": [ "Summary", "Paraphrase (list of sections, in order)", "Sentiment analysis", "Keywords", "Custom instructions" ] }, "default": [ "summarize", "paraphrase", "sentiment" ] }, "aiCustomInstructions": { "title": "Custom AI instructions", "type": "string", "description": "Only used when \"Custom instructions\" is among the selected AI features. Describe the extra analysis you want under the \"custom\" field." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Detik responds fine without a proxy. Enable datacenter proxies first if you start seeing blocks, and residential only if datacenter still fails.", "default": { "useApifyProxy": 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 } } } } } } } } } }