{ "openapi": "3.0.1", "info": { "title": "Yandex News Story Clusters Across Russia & the CIS", "description": "Search or browse Yandex News and get story clusters with every linked article, topic tags, source names and publication dates across Russian and CIS editions.", "version": "2.0", "x-build-id": "bC913XMWUHe0Emsxm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vexaloom-labs~yandex-news-story-clusters-across-russia/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vexaloom-labs-yandex-news-story-clusters-across-russia", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vexaloom-labs~yandex-news-story-clusters-across-russia/runs": { "post": { "operationId": "runs-sync-vexaloom-labs-yandex-news-story-clusters-across-russia", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vexaloom-labs~yandex-news-story-clusters-across-russia/run-sync": { "post": { "operationId": "run-sync-vexaloom-labs-yandex-news-story-clusters-across-russia", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "searchNews", "browseCategory", "topStories", "byStoryUrls" ], "type": "string", "description": "What to scrape. `searchNews` searches keywords, `browseCategory` reads a rubric feed, `topStories` reads the homepage sections, and `byStoryUrls` resolves specific story clusters.", "default": "searchNews" }, "searchQueries": { "title": "Search queries", "type": "array", "description": "One or more keywords or phrases (mode=searchNews). Russian and English queries are supported. The daily-test prefill uses one query.", "items": { "type": "string" } }, "category": { "title": "Category", "enum": [ "all", "politics", "society", "svo", "business", "world", "sport", "incident", "culture", "computers", "science", "auto", "army", "showbusiness", "health", "moscow", "personal_feed" ], "type": "string", "description": "Rubric to browse (mode=browseCategory). `all` reads all 16 rubrics in one run.", "default": "politics" }, "storyUrls": { "title": "Story URLs or cluster IDs", "type": "array", "description": "Dzen News story or instory URLs, or bare cluster UUIDs (mode=byStoryUrls). A bare numeric persistent ID is not a valid cluster URL.", "items": { "type": "string" } }, "maxStories": { "title": "Maximum story clusters", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of story clusters to return across the whole run. Yandex search depth varies by query.", "default": 20 }, "sortOrder": { "title": "Sort order", "enum": [ "relevance", "newest", "oldest", "mostCovered" ], "type": "string", "description": "Order of the returned search clusters (mode=searchNews). Yandex search itself is relevance-ranked; these options sort the returned set.", "default": "newest" }, "timeRange": { "title": "Publication time", "enum": [ "any", "day", "week", "month" ], "type": "string", "description": "Keep clusters published in this window (mode=searchNews). Applied to the results Yandex returns. A custom date range overrides this field.", "default": "any" }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Inclusive start date in YYYY-MM-DD format (mode=searchNews). Leave blank for no lower bound." }, "publishedBefore": { "title": "Published before", "type": "string", "description": "Inclusive end date in YYYY-MM-DD format (mode=searchNews). Leave blank for no upper bound." }, "includeDomains": { "title": "Include source domains", "type": "array", "description": "Keep a cluster when at least one linked article is from one of these domains (for example `rbc.ru`).", "items": { "type": "string" }, "default": [] }, "excludeDomains": { "title": "Exclude source domains", "type": "array", "description": "Drop a cluster when any linked article is from one of these domains.", "items": { "type": "string" }, "default": [] }, "includePublishers": { "title": "Include publishers", "type": "array", "description": "Keep a cluster when any linked source name contains one of these values (case-insensitive).", "items": { "type": "string" }, "default": [] }, "excludePublishers": { "title": "Exclude publishers", "type": "array", "description": "Drop a cluster when any linked source name contains one of these values (case-insensitive).", "items": { "type": "string" }, "default": [] }, "includeKeywords": { "title": "Required keywords", "type": "array", "description": "Keep a cluster when its headline, summary or an article headline/summary contains at least one of these values.", "items": { "type": "string" }, "default": [] }, "excludeKeywords": { "title": "Excluded keywords", "type": "array", "description": "Drop a cluster when its headline, summary or an article headline/summary contains any of these values.", "items": { "type": "string" }, "default": [] }, "includeDetails": { "title": "Include story details", "type": "boolean", "description": "Fetch the cluster page for topic labels, source-reported counts, images, country/region, comments and likes.", "default": true }, "includeArticles": { "title": "Include article records", "type": "boolean", "description": "Emit one record per linked article in every cluster. Turn this off for a story-only dataset.", "default": true }, "maxArticlesPerStory": { "title": "Maximum articles per story", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum article records and article pages fetched per cluster. Yandex returns 100 articles per page.", "default": 100 } } }, "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 } } } } } } } } } }