{ "openapi": "3.0.1", "info": { "title": "Yandex News Scraper", "description": "Scrapes news articles from Yandex Search news results. Extracts headline, summary, source, publication date, author, thumbnail, and more.", "version": "3.0", "x-build-id": "zRoDsWt7ZHHRTF9FY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/searchapi~yandex-news-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-searchapi-yandex-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/searchapi~yandex-news-scraper/runs": { "post": { "operationId": "runs-sync-searchapi-yandex-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/searchapi~yandex-news-scraper/run-sync": { "post": { "operationId": "run-sync-searchapi-yandex-news-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search query", "type": "string", "description": "News keywords to enter in Dzen/Yandex News search." }, "queries": { "title": "Multiple queries", "type": "array", "description": "Optional batch of up to 20 queries with fair result selection.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Maximum records", "minimum": 1, "maximum": 500, "type": "integer", "description": "Global maximum unique articles to store.", "default": 100 }, "maxItemsPerQuery": { "title": "Maximum per query", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum current search cards retained from each query.", "default": 50 }, "timeRange": { "title": "Publication time", "enum": [ "", "day", "week", "month" ], "type": "string", "description": "Filter normalized source publication labels locally.", "default": "" }, "startDate": { "title": "Published from", "type": "string", "description": "Optional inclusive YYYY-MM-DD date." }, "endDate": { "title": "Published through", "type": "string", "description": "Optional inclusive YYYY-MM-DD date." }, "includeDomains": { "title": "Include domains", "type": "array", "description": "Keep articles from at least one listed destination domain.", "default": [], "items": { "type": "string" } }, "excludeDomains": { "title": "Exclude domains", "type": "array", "description": "Remove articles from listed destination domains.", "default": [], "items": { "type": "string" } }, "includePublishers": { "title": "Include publishers", "type": "array", "description": "Keep publisher names containing at least one value.", "default": [], "items": { "type": "string" } }, "excludePublishers": { "title": "Exclude publishers", "type": "array", "description": "Remove publisher names containing any value.", "default": [], "items": { "type": "string" } }, "includeKeywords": { "title": "Required article keywords", "type": "array", "description": "Keep titles/snippets containing at least one value.", "default": [], "items": { "type": "string" } }, "excludeKeywords": { "title": "Excluded article keywords", "type": "array", "description": "Remove titles/snippets containing any value.", "default": [], "items": { "type": "string" } }, "sortBy": { "title": "Sort results", "enum": [ "relevance", "newest", "oldest", "publisher", "title" ], "type": "string", "description": "Sort within each query before fair global selection.", "default": "relevance" }, "regionCode": { "title": "Yandex region code", "type": "string", "description": "Optional numeric Yandex lr code such as 213 for Moscow or 84 for the USA." }, "language": { "title": "Language label", "type": "string", "description": "Output/search provenance label; the live interface may still localize metadata independently.", "default": "ru" }, "country": { "title": "Country label", "type": "string", "description": "Optional requested-market provenance label." }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 4, "type": "integer", "description": "Maximum query pages processed simultaneously.", "default": 2 }, "maxRequestRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Bounded retries for temporary network/server failures.", "default": 2 }, "navigationTimeoutSecs": { "title": "Navigation timeout", "minimum": 20, "maximum": 120, "type": "integer", "description": "Seconds allowed for public Dzen navigation and redirects.", "default": 45 }, "requestHandlerTimeoutSecs": { "title": "Handler timeout", "minimum": 30, "maximum": 180, "type": "integer", "description": "Seconds allowed for one query extraction task.", "default": 60 }, "blockResources": { "title": "Block heavy resources", "type": "boolean", "description": "Skip image, media, and font downloads while keeping article metadata.", "default": true }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Use Apify Proxy unless custom proxy URLs are supplied.", "default": true }, "proxyGroups": { "title": "Apify Proxy groups", "type": "array", "description": "Compatible groups such as RESIDENTIAL; GOOGLE_SERP is incompatible.", "default": [], "items": { "type": "string" } }, "proxyCountryCode": { "title": "Proxy country", "type": "string", "description": "Optional two-letter proxy country code." }, "proxyUrls": { "title": "Custom proxy URLs", "type": "array", "description": "Custom browser proxies take precedence over Apify Proxy settings.", "default": [], "items": { "type": "string" } } } }, "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 } } } } } } } } } }