{ "openapi": "3.0.1", "info": { "title": "OpenLibrary Books Scraper", "description": "Book catalogue data from the Internet Archive's OpenLibrary: full-text search, subject/genre browsing, and rich work detail (description, subjects, linked authors), with identifiers, ratings and ebook availability via its own public API.", "version": "0.1", "x-build-id": "64xGo4T0zz7wix8IF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~openlibrary-books-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-openlibrary-books-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~openlibrary-books-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-openlibrary-books-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~openlibrary-books-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-openlibrary-books-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Search queries (free text)", "type": "array", "description": "Full-text catalogue search, e.g. 'dune frank herbert'. Each query gets its own SEARCH_SUMMARY + BOOK rows. Pagination is REAL on this endpoint (verified: no overlap between pages), so this actor pages through results up to 'maxItemsPerQuery' rather than a single fetch. A nonsense query returns an honest empty result (numFound: 0), never a silently-widened catalogue.", "default": [], "items": { "type": "string" } }, "subjectQueries": { "title": "Subject/genre slugs to browse", "type": "array", "description": "Browse works tagged with a subject, e.g. 'science_fiction', 'fantasy', 'poetry'. Slugs are OpenLibrary's own (lowercase, spaces as underscores) -- browse https://openlibrary.org/subjects to find one. Each entry gets its own SEARCH_SUMMARY + BOOK rows, paged the same way as search. An unrecognised slug returns an honest work_count: 0, not a fallback to a different subject.", "default": [], "items": { "type": "string" } }, "workLookups": { "title": "Work lookups (OpenLibrary work id)", "type": "array", "description": "Full detail for one work by its OpenLibrary id (e.g. 'OL893414W', with or without a '/works/' prefix or '.json' suffix -- all accepted). Adds a full description, complete subject list, and linked author keys beyond what search/subject rows carry. A bad id is reported as a clean not_found ERROR row. Some ids are stale/merged and redirect to a canonical id -- followed automatically once, noted via '_redirectedFrom'.", "default": [], "items": { "type": "string" } }, "searchFields": { "title": "Search result fields (advanced, optional)", "type": "array", "description": "Override which fields the search API returns per BOOK row (only affects 'searchQueries', not 'subjectQueries' or 'workLookups'). Leave empty for this actor's curated default field set (identifiers, ratings, ebook availability -- see README). Pass ['*'] for upstream's full raw field set, which additionally includes ~50 hour-of-day/day-of-week trending-score columns.", "default": [], "items": { "type": "string" } }, "maxItemsPerQuery": { "title": "Max rows per query", "minimum": 0, "type": "integer", "description": "Caps rows per search/subject query, paging as needed to reach it (up to 100 rows per request, OpenLibrary's own practical per-request cap). 0 = no explicit cap (still bounded by a 50-page safety net). Does not apply to 'workLookups' (always exactly one row per id).", "default": 50 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 15, "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": 30, "type": "number", "description": "The actual speed control: the shortest gap between two requests, across all workers. openlibrary.org's own robots.txt sets a 10-second crawl-delay specifically for the ClaudeBot/anthropic-ai groups (not a technical WAF limit -- no WAF was observed); this default of 10 honors that policy signal directly rather than just the minimum a rate-limiter would force.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy on the shared datacenter pool. This is the default because it is included in your plan at no extra cost and this target works through it. If you start seeing blocks, challenges or empty results, switch the group here to Residential -- it uses real consumer IPs and gets through more, but Apify bills residential traffic per gigabyte, so leave it off unless you need it.", "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 } } } } } } } } } }