{ "openapi": "3.0.1", "info": { "title": "Ximalaya Scraper 喜马拉雅: Podcasts & Comments", "description": "Scrape Ximalaya (喜马拉雅) album and episode metadata, host/creator profiles, play and subscriber counts, and paginated track comments from China's dominant podcast/audiobook platform. Direct play URLs for free tracks only - paid/VIP tracks are never bypassed.", "version": "0.1", "x-build-id": "Q1dCYoXHnfDn6Budf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/getascraper~ximalaya-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-getascraper-ximalaya-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/getascraper~ximalaya-scraper/runs": { "post": { "operationId": "runs-sync-getascraper-ximalaya-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/getascraper~ximalaya-scraper/run-sync": { "post": { "operationId": "run-sync-getascraper-ximalaya-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "albums": { "title": "Albums (ID or URL)", "type": "array", "description": "One entry per album: a numeric album ID (e.g. 61) or a full ximalaya.com album URL (e.g. https://www.ximalaya.com/album/61). Returns album metadata, host/creator profile, the paginated episode list, and (if enabled below) paginated comments per episode.", "default": [], "items": { "type": "string" } }, "tracks": { "title": "Tracks (ID or URL) - comments only", "type": "array", "description": "One entry per track/episode: a numeric track ID or a full ximalaya.com track URL (e.g. https://www.ximalaya.com/sound/93969607). Ximalaya has no standalone track-metadata endpoint, so a bare track only yields its comments (requires \"Include comments\" enabled below) - for full episode metadata, look up the parent album instead.", "default": [], "items": { "type": "string" } }, "maxEpisodes": { "title": "Max episodes per album", "minimum": 1, "type": "integer", "description": "Maximum number of episodes/tracks to fetch and output per album, paginated 20 at a time from the source API. Set high to fetch a whole catalog; set low for a quick sample.", "default": 10 }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch paginated comments for every episode processed from albums, and for any bare track entries above. Required for track-only entries - it's the only data obtainable for a track without its parent album.", "default": true }, "maxCommentPagesPerTrack": { "title": "Max comment pages per track", "minimum": 1, "type": "integer", "description": "Comment pages fetched per track (20 comments/page). Caps compute cost on popular tracks - one validated track alone had 106 pages of comments. Lower this for a lighter sample, raise it (or use incremental monitoring below) to go deeper over multiple runs.", "default": 2 }, "since": { "title": "Only comments after", "type": "string", "description": "Skip comments at or older than this date/time, and stop paginating a track's comments once older comments are reached. Leave blank to fetch the newest comments up to the page cap above on every run." }, "incrementalComments": { "title": "Incremental comment monitoring", "type": "boolean", "description": "Remember the newest comment timestamp seen per track (in this Actor's key-value store) and automatically resume from there on the next run - a \"since last run\" mode for recurring comment/sentiment monitoring. Combine with a schedule for ongoing monitoring.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Datacenter proxy is the default and expected to be sufficient. Switch to residential only if you observe blocking in production.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }