{ "openapi": "3.0.1", "info": { "title": "RSS & Atom Feed Scraper — Any Feed to Clean JSON (Bulk)", "description": "Turn any RSS, Atom or JSON Feed (or a website URL, feed auto-discovered) into clean JSON: title, link, summary, content, author, date, categories, images. Bulk feeds, whole-word keyword include/exclude, date window, dedupe, sort, only-new monitoring, optional full article text. No API key.", "version": "0.1", "x-build-id": "hsCjlkYzjaCqqUy9A" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yadroo~rss-to-json/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yadroo-rss-to-json", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yadroo~rss-to-json/runs": { "post": { "operationId": "runs-sync-yadroo-rss-to-json", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yadroo~rss-to-json/run-sync": { "post": { "operationId": "run-sync-yadroo-rss-to-json", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Feed or site URLs", "type": "array", "description": "RSS 2.0, RSS 1.0 (RDF), Atom or JSON Feed URLs — or plain website URLs: the feed is auto-discovered from and common paths (/feed, /rss.xml, /atom.xml…). Up to a few hundred URLs per run; fetched 4 at a time.", "items": { "type": "string" } }, "discoverFeeds": { "title": "Auto-discover feed from website URLs", "type": "boolean", "description": "If a URL returns an HTML page, look for its feed. Off = HTML pages are reported as errors.", "default": true }, "includeKeywords": { "title": "Include keywords", "type": "array", "description": "Keep only items mentioning these words/phrases (case-insensitive, whole words: \"ai\" does not match \"StarCraft\"). Add a trailing * for prefixes: \"invest*\". Matched words are returned in keywordsMatched.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Drop items mentioning any of these words/phrases (same matching rules).", "items": { "type": "string" } }, "keywordMatch": { "title": "Include keywords: match", "enum": [ "any", "all" ], "type": "string", "description": "Whether an item needs one or all of the include keywords.", "default": "any" }, "matchIn": { "title": "Search keywords in", "enum": [ "title", "titleSummary", "all" ], "type": "string", "description": "Which item text the keyword filters look at. Full article text (fetchFullContent) is fetched after filtering and is not searched.", "default": "titleSummary" }, "query": { "title": "Keyword filter (legacy)", "type": "string", "description": "Space-separated words that must ALL appear in title/summary. Ignored when includeKeywords is set." }, "since": { "title": "Published since", "type": "string", "description": "ISO date/datetime (2026-09-01, 2026-09-01T12:00:00Z) or relative span back from now: 30m, 24h, 7d, 2w. Items without a parseable date are dropped when set." }, "until": { "title": "Published until", "type": "string", "description": "ISO date/datetime or relative span. A date-only value includes that whole day (UTC)." }, "sinceHours": { "title": "Since N hours (legacy)", "minimum": 0, "type": "integer", "description": "Only items from the last N hours (0 = no limit). If both are set, the later of since / sinceHours wins.", "default": 0 }, "onlyNew": { "title": "Only items not seen in previous runs", "type": "boolean", "description": "Monitoring mode: remembers item ids in the named key-value store \"rss-to-json-state\" and outputs only new items on each scheduled run (last 20 000 ids kept).", "default": false }, "stateKey": { "title": "Monitor name", "type": "string", "description": "Name of the seen-items memory for onlyNew. Default is derived from the URL list; set it explicitly to keep state when you edit the list. Letters, digits, dot, dash, underscore." }, "limitPerFeed": { "title": "Max items per feed", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap per feed, applied after filters and sorting (so with publishedDesc you get each feed's newest N matches).", "default": 50 }, "maxItems": { "title": "Max items total", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Overall cap after merging feeds (keeps the first N in the chosen sort order).", "default": 1000 }, "sortBy": { "title": "Sort", "enum": [ "publishedDesc", "publishedAsc", "feedOrder" ], "type": "string", "description": "Order of the merged output. Undated items go last.", "default": "publishedDesc" }, "dedupeBy": { "title": "Deduplicate by", "enum": [ "url", "id", "title", "none" ], "type": "string", "description": "Removes the same story appearing in several feeds or twice in one feed.", "default": "url" }, "fetchFullContent": { "title": "Fetch full article text", "type": "boolean", "description": "Open each output item's link and extract the main article text (plus word count, reading time, canonical URL, og:image/author/date when missing). One extra request per item; paywalled or bot-protected sites return fullContentError.", "default": false }, "maxFullContentChars": { "title": "Max article characters", "minimum": 500, "maximum": 200000, "type": "integer", "description": "Truncate fullContent to this length.", "default": 20000 }, "fullContentConcurrency": { "title": "Article fetch concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel article requests. Keep low for single-site feeds to stay polite.", "default": 3 }, "summaryMaxChars": { "title": "Max summary characters", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Plain-text summary length (0 = no limit).", "default": 1000 }, "contentMaxChars": { "title": "Max feed content characters", "minimum": 0, "maximum": 200000, "type": "integer", "description": "Plain-text length of the content embedded in the feed (content:encoded / Atom content). 0 = no limit.", "default": 5000 }, "includeContentHtml": { "title": "Include raw content HTML", "type": "boolean", "description": "Add contentHtml with the feed's original HTML (not truncated).", "default": false }, "includeErrors": { "title": "Output a row per failed feed", "type": "boolean", "description": "Off (default): feeds that could not be fetched/parsed are listed free of charge in the SUMMARY record (errors, feeds) and the run's status message. On: also push a {feedUrl, httpStatus, error} row per failed feed — such rows are dataset rows and are charged like items.", "default": false }, "fields": { "title": "Output fields", "type": "array", "description": "Keep only these fields, e.g. [\"publishedAt\",\"feedTitle\",\"title\",\"url\"]. Empty = all.", "items": { "type": "string" } }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Override the User-Agent header (some feeds serve 403 to unknown bots)." } } }, "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 } } } } } } } } } }