{ "openapi": "3.0.1", "info": { "title": "Podcast RSS Feed Scraper — Episodes & Transcripts", "description": "Scrape podcast RSS feeds, Apple Podcasts URLs or search terms into show and episode records (title, pubDate, duration, audio URL, chapters, Podcasting 2.0 transcripts) with optional transcript text. Pay per episode ($0.0005), show ($0.001) and transcript ($0.005).", "version": "0.1", "x-build-id": "xeQ0MkGxaceAkzIMW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/owlabee~podcast-rss-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-owlabee-podcast-rss-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/owlabee~podcast-rss-scraper/runs": { "post": { "operationId": "runs-sync-owlabee-podcast-rss-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/owlabee~podcast-rss-scraper/run-sync": { "post": { "operationId": "run-sync-owlabee-podcast-rss-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", "required": [ "feeds" ], "properties": { "feeds": { "title": "Feeds", "minItems": 1, "type": "array", "description": "One entry per line. Accepts podcast RSS/Atom feed URLs, Apple Podcasts show URLs (https://podcasts.apple.com/…/id123456789, resolved through the public iTunes Lookup API), bare Apple IDs, and search terms written as `search:the daily` (resolved through the iTunes Search API; the top result is used and the other matches are recorded on the show record). A show's web page works too when it carries an RSS autodiscovery link. The prefilled feeds are the cheap, always-available examples used by Apify's daily automated test.", "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Max episodes per feed", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Newest-first cap on episode records per feed. The show record still reports the full `episodeCount`. With `onlyNewSinceLastRun`, new episodes beyond the cap are left for the next run.", "default": 100 }, "includeShowRecord": { "title": "Include show record", "type": "boolean", "description": "Write one `recordType: \"show\"` item per feed with the show-level metadata (title, description, author, categories, image, podcast GUID, funding, episode count). Turn off to get episode records only.", "default": true }, "fetchTranscripts": { "title": "Fetch transcripts", "type": "boolean", "description": "Download each episode's `` file (first available in order text, VTT, SRT, JSON, HTML; max 2 MB) and attach `transcriptText` (plain text, cue timestamps stripped) and `transcriptWords`. Charged per transcript on top of the episode event; episodes without a transcript tag are not charged for it.", "default": false }, "onlyNewSinceLastRun": { "title": "Only new episodes since the last run", "type": "boolean", "description": "Remember the episode GUIDs of each feed in the state store and return only episodes not seen before. The first run for a feed is a baseline and returns the newest episodes up to the cap. Ideal for scheduled monitoring and webhooks.", "default": false }, "stateStoreName": { "title": "State key-value store", "pattern": "^[a-zA-Z0-9-]{3,63}$", "type": "string", "description": "Named key-value store that keeps the seen-episode GUIDs per feed when `onlyNewSinceLastRun` is on. Use a different name for independent monitors (e.g. per client or schedule).", "default": "podcast-rss-scraper-state" }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel transcript downloads per feed. Requests to the same host are additionally spaced at least 500 ms apart (about 2 requests per second per host).", "default": 5 }, "webhookUrl": { "title": "Webhook URL (optional)", "pattern": "^https?://.+", "type": "string", "description": "If set, the Actor POSTs a JSON summary of the run (per-feed counts and, with `onlyNewSinceLastRun`, the list of new episodes) to this URL — 10 s timeout, 2 retries. Failures are logged, never fatal." } } }, "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 } } } } } } } } } }