{ "openapi": "3.0.1", "info": { "title": "HathiTrust Digital Library Scraper - Books, Editions & Rights", "description": "$0.5/1K 🔥 HathiTrust scraper! 18M+ digitized books — editions, rights & holding libraries by ISBN or OCLC. No key. JSON, CSV, Excel or API in seconds. Power library & book research ⚡", "version": "0.1", "x-build-id": "0GxyOAOXcBvwjSgsP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ninhothedev~hathitrust-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ninhothedev-hathitrust-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ninhothedev~hathitrust-scraper/runs": { "post": { "operationId": "runs-sync-ninhothedev-hathitrust-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/ninhothedev~hathitrust-scraper/run-sync": { "post": { "operationId": "run-sync-ninhothedev-hathitrust-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": [ "ids" ], "properties": { "mode": { "title": "Mode", "enum": [ "lookup" ], "type": "string", "description": "Scraping mode. 'lookup' resolves a list of bibliographic identifiers into HathiTrust volume records (title, editions, holdings and rights).", "default": "lookup" }, "idType": { "title": "Identifier type", "enum": [ "isbn", "oclc", "lccn", "issn", "htid", "recordnumber" ], "type": "string", "description": "Which kind of identifier the 'Identifiers' list contains. All values in that list must be of this same type. ISBN and OCLC give the widest coverage; HTID targets a single digitized item; record number targets a HathiTrust catalog record directly.", "default": "isbn" }, "ids": { "title": "Identifiers", "type": "array", "description": "The identifiers to look up, all of the type chosen above. Up to 20 are packed into each API request. Identifiers with no HathiTrust holdings are skipped and reported in the log. Older / academic / public-domain titles have far better coverage than recent trade paperbacks.", "default": [ "9780195079630", "0226458075", "0195079639" ], "items": { "type": "string" } }, "useFullRecords": { "title": "Fetch full records (with MARC-XML)", "type": "boolean", "description": "Use the API's 'full' level instead of 'brief'. Full records add the complete MARC-XML bibliographic record (authors, subjects, publisher, physical description) to the 'marc_xml' field. Slower and much larger payloads — leave off unless you need MARC data.", "default": false }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Hard cap on how many volume records are written to the dataset. Use it to bound cost and runtime on long identifier lists.", "default": 200 } } }, "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 } } } } } } } } } }