{
"openapi": "3.0.1",
"info": {
"title": "RSS Feed Scraper",
"description": "RSS Feed Scraper SD - RSS Feed Scraper is a feed reader tool that extracts every item of RSS 2.0, RSS 1.0 (RDF), Atom and JSON feeds: title, link, author, dates, categories, summary, full content, images, podcast enclosures, plus feed details. Follows paged feeds, finds feeds on websites.",
"version": "1.0",
"x-build-id": "fs45GHlHwwO76lADB"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/neuro-scraper~rss-feed-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-neuro-scraper-rss-feed-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/neuro-scraper~rss-feed-scraper/runs": {
"post": {
"operationId": "runs-sync-neuro-scraper-rss-feed-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/neuro-scraper~rss-feed-scraper/run-sync": {
"post": {
"operationId": "run-sync-neuro-scraper-rss-feed-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"feedUrls": {
"title": "Feed URLs",
"type": "array",
"description": "RSS, Atom, RDF or JSON Feed URLs, one per line, e.g. https://feeds.bbci.co.uk/news/rss.xml. A website or blog URL (e.g. https://wordpress.org/news/) also works when 'Discover feeds from websites' is on: the feed linked in the page's is used.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"maxItemsPerFeed": {
"title": "Max items per feed",
"minimum": 0,
"maximum": 100000,
"type": "integer",
"description": "How many items to save from each feed. When the feed is paged (Atom/RSS rel=\"next\" link such as Blogger, WordPress ?paged=N, JSON Feed next_url) the next pages are followed until this number or the feed's last page. 0 = every page of the feed.",
"default": 50
},
"maxItems": {
"title": "Max items in total",
"minimum": 0,
"maximum": 1000000,
"type": "integer",
"description": "Optional cap for the whole run across all feeds. 0 = no total cap (only Max items per feed applies).",
"default": 0
},
"followPagination": {
"title": "Follow feed pages",
"type": "boolean",
"description": "Follow the feed's own next-page link (rel=\"next\", WordPress ?paged=N, JSON Feed next_url) to reach older items. Off = only the document at the feed URL.",
"default": true
},
"publishedAfter": {
"title": "Published after",
"type": "string",
"description": "Only items published on or after this date (YYYY-MM-DD or a full ISO date-time, UTC). Applied to each item's date; paging stops once a whole page is older. Items without a date are kept. Example: 2026-01-01."
},
"includeContent": {
"title": "Include full content",
"type": "boolean",
"description": "Add the item's full body from the feed (content:encoded, Atom content, JSON content_html) as plain text ('content') and HTML ('contentHtml'). Off = only the short description.",
"default": true
},
"extractContent": {
"title": "Extract full article text",
"type": "boolean",
"description": "Also open each item's link and extract the article's main text into 'fullText' (one extra request per item, slower; useful for feeds that publish only a snippet).",
"default": false
},
"discoverFeeds": {
"title": "Discover feeds from websites",
"type": "boolean",
"description": "When a URL is a web page instead of a feed, use the feed it links in (comment feeds last), or the common paths /feed/, /rss.xml, /atom.xml, /index.xml, /feed.xml.",
"default": true
},
"deduplicateItems": {
"title": "Deduplicate items across feeds",
"type": "boolean",
"description": "Save each item (by GUID / id, else link) only once when several feeds in the run carry it.",
"default": true
},
"outputErrorRows": {
"title": "Save a row for feeds that failed",
"type": "boolean",
"description": "Write one row with type 'error' and the 'error' message for each feed that could not be read (each row counts as a result). Off = failed feeds are only named in the log and the run status.",
"default": false
},
"fetchTimeoutSeconds": {
"title": "Fetch timeout (seconds)",
"minimum": 5,
"maximum": 180,
"type": "integer",
"description": "Time limit for each HTTP request. Example: 30.",
"default": 30
},
"userAgent": {
"title": "User-Agent override",
"type": "string",
"description": "Optional User-Agent header for feed requests (some feeds serve only known readers). Empty = a normal desktop Chrome browser."
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Apify Proxy settings. RESIDENTIAL (default) gets through feeds behind bot protection; most public feeds also work with the proxy turned off.",
"default": {
"useApifyProxy": true,
"apifyProxyGroups": [
"RESIDENTIAL"
]
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}