{ "openapi": "3.0.1", "info": { "title": "Turkish News Scraper", "description": "Scrape Turkish news from Sozcu, Hurriyet, Haberturk, NTV and CNN Turk: titles, full text, dates, authors and categories. Fast HTTP scraper, no browser.", "version": "0.0", "x-build-id": "vt5tY1II3lzXtNCxk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dodoflix~news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dodoflix-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dodoflix~news-scraper/runs": { "post": { "operationId": "runs-sync-dodoflix-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dodoflix~news-scraper/run-sync": { "post": { "operationId": "run-sync-dodoflix-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "sources": { "title": "News outlets", "type": "array", "description": "Outlets to read. Their RSS feeds are fetched for the categories chosen below.", "items": { "type": "string", "enum": [ "sozcu", "hurriyet", "haberturk", "ntv", "cnnturk" ], "enumTitles": [ "Sözcü", "Hürriyet", "Habertürk", "NTV", "CNN Türk" ] }, "default": [ "sozcu", "hurriyet", "haberturk", "ntv", "cnnturk" ] }, "categories": { "title": "Categories", "type": "array", "description": "Latest is each outlet's front-page or breaking-news feed. An outlet without a feed for a category is skipped (for example NTV has no magazin feed).", "items": { "type": "string", "enum": [ "latest", "gundem", "ekonomi", "dunya", "spor", "magazin", "teknoloji", "saglik" ], "enumTitles": [ "Latest", "Gündem (national)", "Ekonomi", "Dünya (world)", "Spor", "Magazin", "Teknoloji", "Sağlık" ] }, "default": [ "latest" ] }, "startUrls": { "title": "Article or feed URLs", "type": "array", "description": "Optional. Article URLs from any news site that publishes schema.org NewsArticle data, or RSS and Atom feed URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "keywords": { "title": "Keywords", "type": "array", "description": "Keep only articles that contain at least one of these words. Ignores case and Turkish accents, so 'ekonomi' also matches 'EKONOMİ'. Sözcü, Habertürk and CNN Türk feeds carry only the title and a summary, so for them the word must appear there.", "items": { "type": "string" } }, "fullText": { "title": "Fetch full article text", "type": "boolean", "description": "Open each article page to get the complete text, author and keywords. Turn off for a faster run that returns only the feed title and summary.", "default": true }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Skip articles published before this date (YYYY-MM-DD or a full ISO timestamp)." }, "maxItems": { "title": "Max items in total", "minimum": 1, "type": "integer", "description": "Stop the whole run after this many articles. Leave empty for no limit." }, "maxItemsPerFeed": { "title": "Max items per feed", "minimum": 1, "type": "integer", "description": "Articles taken from each feed. Feeds hold the newest 20 to 100 articles, so higher values add nothing.", "default": 50 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 1, "type": "integer", "description": "Request speed. Lower it if you see 429 or 503 errors in the log.", "default": 300 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. The outlets answer plain requests, so no proxy is used by default.", "default": { "useApifyProxy": false } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }