{ "openapi": "3.0.1", "info": { "title": "SRU Catalog Harvester", "description": "Point at ANY SRU/SRW library catalog (DNB, Library of Congress, K10plus and thousands more — one LoC standard) and get flat bibliographic rows from a CQL query: title, creator, publisher, date, subject, ISBN and more, plus lossless raw XML. Discovery mode lists a server's indexes. Pay per record.", "version": "0.1", "x-build-id": "9KjAU4aoIBQSg8bs0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~sru-catalog-harvester/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-sru-catalog-harvester", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~sru-catalog-harvester/runs": { "post": { "operationId": "runs-sync-datamule-sru-catalog-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~sru-catalog-harvester/run-sync": { "post": { "operationId": "run-sync-datamule-sru-catalog-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "base_url" ], "properties": { "base_url": { "title": "SRU/SRW endpoint URL", "type": "string", "description": "The base URL of any SRU (Search/Retrieve via URL) or SRW server — the Library of Congress standard protocol spoken by most national, university and union library catalogs. Examples: https://services.dnb.de/sru/dnb (German National Library), http://lx2.loc.gov:210/lcdb (Library of Congress), https://sru.k10plus.de/gvk (K10plus/GBV union catalog). One actor works against thousands of these." }, "query": { "title": "CQL query", "type": "string", "description": "A CQL (Contextual Query Language) search expression, e.g. dc.title=climate, dc.creator=goethe, or a bare keyword. The exact indexes a server supports vary — run this actor once with operation=explain to list them. Required for a searchRetrieve; ignored for explain." }, "operation": { "title": "Operation", "enum": [ "searchRetrieve", "explain" ], "type": "string", "description": "searchRetrieve (default) runs the query and returns bibliographic records. explain fetches the server's self-description and lists its searchable indexes and available record schemas — a cheap way to discover a server before querying it.", "default": "searchRetrieve" }, "recordSchema": { "title": "Record schema", "type": "string", "description": "The metadata schema to request per record. oai_dc / dc (Dublin Core) flattens to clean columns; MARC21-xml / marcxml is decoded from standard MARC tags. Any other schema still yields a structured fields map + the lossless raw XML. Leave empty to use the server's default. Common values: oai_dc, dc, marcxml, MARC21-xml, mods." }, "maximumRecords": { "title": "Records per page", "minimum": 1, "type": "integer", "description": "How many records to request per SRU page (the server's maximumRecords parameter). Most servers cap this at 100. Default 50.", "default": 50 }, "maxRecords": { "title": "Max records (global cap)", "minimum": 1, "type": "integer", "description": "A GLOBAL cap on the total number of records to harvest across all pages (each emitted record is one billable event). Leave empty to fetch a single page (equal to Records per page) — a cost-safe default. Set higher to auto-paginate through a large result set." }, "startRecord": { "title": "Start record", "minimum": 1, "type": "integer", "description": "The 1-based position of the first record to return (SRU is 1-indexed). Use to resume or skip into a result set. Default 1.", "default": 1 }, "sruVersion": { "title": "SRU version", "enum": [ "1.1", "1.2", "2.0" ], "type": "string", "description": "The SRU protocol version to send. Most servers accept 1.1; some require 1.2 or 2.0. The response is parsed the same way regardless. Default 1.1.", "default": "1.1" }, "bearer": { "title": "Bearer token", "type": "string", "description": "Optional bearer token for gated SRU deployments (sent as Authorization: Bearer ***). Not required for public library catalogs. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers as a JSON object, e.g. {\"x-api-key\": \"...\"} for gated servers. Not required for public servers. Header values are never logged." } } }, "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 } } } } } } } } } }