{ "openapi": "3.0.1", "info": { "title": "Discogs Search Scraper", "description": "Searches Discogs across releases, master releases, artists and labels. Returns full tracklist, catalog number, community rating, and live marketplace price range for individual releases.", "version": "0.1", "x-build-id": "ZQn1fDcIr491ogYmM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~discogs-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-discogs-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~discogs-search-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-discogs-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~discogs-search-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-discogs-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Search terms", "type": "array", "description": "Free-text searches — one crawl per entry, each with its own SEARCH_SUMMARY row. Leave empty and set at least one filter below to browse by filter alone (e.g. every Reggae release with no search term at all).", "default": [], "items": { "type": "string" } }, "entityType": { "title": "Entity type", "enum": [ "release", "master", "artist", "label" ], "type": "string", "description": "Which of Discogs' four indexed types to search. Each returns a genuinely different result shape (verified) — a specific pressing, the canonical work across all its pressings, an artist, or a record label.", "default": "release" }, "format": { "title": "Format", "type": "string", "description": "Exact format facet, e.g. 'Vinyl', 'CD', 'Cassette'. Must match Discogs' own facet text exactly (case and spacing matter). A bogus value genuinely narrows to zero results here rather than silently returning everything, so a typo is safe — just empty.", "default": "" }, "genre": { "title": "Genre", "type": "string", "description": "Exact genre facet, e.g. 'Rock', 'Electronic', 'Hip Hop', 'Jazz'. Same exact-match behaviour as Format.", "default": "" }, "style": { "title": "Style", "type": "string", "description": "Exact style facet — a finer-grained tag than genre, e.g. 'Trip Hop', 'Alternative Rock', 'Downtempo'. Same exact-match behaviour as Format.", "default": "" }, "country": { "title": "Country", "type": "string", "description": "Country of release, e.g. 'US', 'UK', 'Germany'.", "default": "" }, "year": { "title": "Year", "type": "string", "description": "Exact release year, e.g. '1997'.", "default": "" }, "decade": { "title": "Decade", "type": "string", "description": "Decade, e.g. '1990' for the 1990s.", "default": "" }, "maxItems": { "title": "Max results per query", "minimum": 0, "type": "integer", "description": "Stop after this many results per query. Set to 0 for unlimited — Discogs' pagination is genuinely honest here (25 results/page, past the real last page it returns an empty array rather than clamping back to page 1), so an unlimited crawl terminates correctly.", "default": 50 }, "includeReleaseDetails": { "title": "Fetch full release details", "type": "boolean", "description": "For entityType='release' only: fetch each release's detail page for the full tracklist, catalog number, community rating, and live marketplace price range (offer count, low/high price). Ignored (with a log warning) for master/artist/label searches, which this actor does not have a detail parser for.", "default": true }, "surface": { "title": "Data surface", "enum": [ "auto", "web", "api" ], "type": "string", "description": "Where to read from. 'auto' (default) tries the website first (fast, Discogs' own GraphQL result objects with `__typename`, JSON-LD marketplace price range on release pages) and falls back to the official API (api.discogs.com) for any query or release the website's Cloudflare challenge blocks. 'api' skips the website entirely: deterministic, but rate-limited to 25 requests/min without a token (60/min with one) and rows carry the API's field names instead. 'web' never falls back. Every row says which surface produced it in `_source`.", "default": "auto" }, "discogsToken": { "title": "Discogs personal access token (optional)", "type": "string", "description": "Optional. Generate one at discogs.com/settings/developers. Only used for API calls (the fallback surface, or all calls with surface='api'); it raises the API rate limit from 25 to 60 requests/min. Never logged and never sent to the website." }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many requests may be in flight at once. This absorbs latency variance; it is NOT the throttle — the crawl rate is set by 'Minimum interval between requests' below.", "default": 5 }, "minRequestInterval": { "title": "Minimum interval between requests (seconds)", "minimum": 0.05, "maximum": 10, "type": "number", "description": "The actual speed control: the shortest gap between two requests to Discogs, across all workers.", "default": 0.4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "www.discogs.com sits behind a Cloudflare challenge that is probabilistic per request from cloud egress; the actor rotates exit IP + browser fingerprint and falls back to the official Discogs API (api.discogs.com, never challenged in our measurements) when the web surface is blocked. Apify datacenter proxy is the default: measured identically to residential here, at a fraction of the cost. Leaving this empty runs on the container's own IP.", "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 }, "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 } } } } } } } } } }