{ "openapi": "3.0.1", "info": { "title": "SoundCloud Scraper · Tracks + Artists + Emails · $1.50/1k", "description": "Scrape SoundCloud tracks, artists, playlists, albums, and search results in one actor — with management/booking emails parsed directly from artist bios. Auto-classifies any SoundCloud URL. Uses the public v2 JSON API (no browser, no client_id setup). 30+ fields per row, JSON or CSV", "version": "0.0", "x-build-id": "aDFgBgOi0Q3UQAS6s" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~soundcloud-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-soundcloud-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/memo23~soundcloud-scraper/runs": { "post": { "operationId": "runs-sync-memo23-soundcloud-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/memo23~soundcloud-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-soundcloud-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": { "startUrls": { "title": "SoundCloud URLs", "type": "array", "description": "Full soundcloud.com URLs to scrape. Search URLs paginate automatically (cursor-based) until `Maximum items to scrape` is reached.", "items": { "type": "string" } }, "harvestArtistEmails": { "title": "Harvest contact emails from each artist's bio", "type": "boolean", "description": "When enabled (default), each artist's bio (`description` field) is scanned for emails (mailto: links + plain-text patterns, junk filtered). SoundCloud artists routinely put management/booking emails in their bio (e.g. Flume's bio starts with `Management: flume@threesixzero.com`). Disable for slightly cleaner raw output.", "default": true }, "paginateSearch": { "title": "Paginate through search/discover results", "type": "boolean", "description": "When enabled (default), search URLs follow cursor pagination (SC's `next_href` field) across multiple pages until `Maximum items to scrape` is reached. Disable to scrape only the first page of each search (~25 results).", "default": true }, "flatten": { "title": "Flatten nested fields for CSV-friendly output", "type": "boolean", "description": "When enabled (default), nested API objects (`user`, `media`, etc.) are flattened to underscore-separated top-level keys (e.g. `user_id`, `user_country_code`). Arrays-of-objects become JSON-stringified `*_json` fields. Disable to keep the raw nested JSON shape.", "default": true }, "includeRaw": { "title": "Include full v2 API response on every row", "type": "boolean", "description": "When enabled, the full v2 API response is attached as a `raw` field on every row — useful for accessing fields the actor doesn't surface explicitly. Off by default to keep rows small.", "default": false }, "hydratePlaylistTracks": { "title": "Hydrate playlist tracklist with full titles + metadata", "type": "boolean", "description": "SoundCloud's playlist endpoint returns the first few tracks fully populated and the rest as id-only stubs (titles come back as `null` in `tracks_json`). When enabled (default), the actor issues one extra `/tracks?ids=…` call per playlist to backfill titles, permalinks, and full track metadata. Disable to keep playlist rows to a single API call — titles for stub tracks will remain `null`.", "default": true }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on the number of rows emitted (tracks + artists + playlists combined). A single artist URL emits 1 row. A search URL fans out to ~25 rows per page × however many pages are available.", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of API calls processed in parallel. SoundCloud's API is forgiving; 6-10 is the sweet spot.", "default": 8 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Minimum number of API calls processed in parallel.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Number of retries before a failed API call is given up. 401/403 responses trigger an automatic client_id refresh + single retry; this counter covers other failures.", "default": 5 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Defaults to Apify Proxy. SoundCloud's v2 API doesn't require a proxy in our testing — impit's Chrome TLS fingerprint + the right Referer header is enough. Provide your own residential pool here only if you encounter rate-limits." } } }, "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 } } } } } } } } } }