{ "openapi": "3.0.1", "info": { "title": "RSS & Atom Structured Feed Extractor", "description": "Point at ANY RSS or Atom feed (news, blogs, podcasts, GitHub releases, YouTube) and get clean structured rows. Auto-detects RSS 2.0 / RSS 1.0 / Atom and normalizes every entry to one schema: title, link, content, author, categories, ISO-8601 dates, enclosures. Pay per item.", "version": "0.1", "x-build-id": "WDFsSu9V7yfyHA0JQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~rss-structured-feed-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-rss-structured-feed-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~rss-structured-feed-extractor/runs": { "post": { "operationId": "runs-sync-datamule-rss-structured-feed-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~rss-structured-feed-extractor/run-sync": { "post": { "operationId": "run-sync-datamule-rss-structured-feed-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "feedUrl": { "title": "Feed URL", "type": "string", "description": "The URL of ANY RSS or Atom feed. One actor handles all of them — RSS 2.0, RSS 1.0 (RDF) and Atom 1.0 are auto-detected and normalized to one schema. Works on news feeds (https://feeds.bbci.co.uk/news/rss.xml), blogs, podcasts, GitHub releases (https://github.com/OWNER/REPO/releases.atom), status pages, YouTube channels (https://www.youtube.com/feeds/videos.xml?channel_id=...), journal tables-of-contents and more. Required unless you use \"Feed URLs\" below to harvest several at once." }, "feedUrls": { "title": "Feed URLs (harvest several at once)", "type": "array", "description": "Optional: harvest MULTIPLE feeds in one run — each output row is tagged with its _feedUrl. Use this OR the single \"Feed URL\" above (at least one is required). A feed that is unreachable, auth-gated, returns a non-feed HTML page, or is malformed XML is skipped with a warning and the batch continues.", "items": { "type": "string" } }, "maxItems": { "title": "Max items (global cap)", "minimum": 1, "type": "integer", "description": "A GLOBAL cap on the number of item rows emitted across ALL feeds (each row is one feed entry and one billable event). Reached mid-feed, the run stops deterministically. Leave empty to emit every entry in every feed." }, "fullContent": { "title": "Include full content", "type": "boolean", "description": "Include the full-text body of each entry (RSS content:encoded / Atom ) in the content field when the feed provides it. Turn OFF to keep only the short summary / description and produce smaller rows.", "default": true }, "userAgent": { "title": "User-Agent override", "type": "string", "description": "Optional override for the request User-Agent. A descriptive User-Agent is sent by default — some feeds return 403 to a blank or generic UA. Only override if a specific feed asks you to identify differently." }, "timeoutSecs": { "title": "Read timeout (seconds)", "minimum": 1, "maximum": 600, "type": "integer", "description": "How long to wait for a feed to answer (default 60). A dead connection fails fast regardless." }, "bearer": { "title": "Bearer token", "type": "string", "description": "Optional bearer token for an auth-gated feed (sent as Authorization: Bearer ...). NOT required for public feeds. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers as a JSON object, e.g. {\"X-Api-Key\": \"...\"} or a Cookie for a gated feed. Not required for public feeds. Header values are never logged." } } }, "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 } } } } } } } } } }