{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper | Search, Files & Reviews", "description": "Search the Internet Archive and export public item metadata, reviews, ratings and file download links to CSV, Excel or JSON. Batch item URLs or identifiers. Browser-only collection.", "version": "1.0", "x-build-id": "uwYMLNidLUR64NfjG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thescrapelab~internet-archive-book-reviews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thescrapelab-internet-archive-book-reviews-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thescrapelab~internet-archive-book-reviews-scraper/runs": { "post": { "operationId": "runs-sync-thescrapelab-internet-archive-book-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thescrapelab~internet-archive-book-reviews-scraper/run-sync": { "post": { "operationId": "run-sync-thescrapelab-internet-archive-book-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "operation": { "title": "Operation", "enum": [ "search", "itemDetails", "reviews", "files" ], "type": "string", "description": "Choose Search catalogue, Get item details, Export reviews, or List files. Enter matching search queries or item URLs in the shared input below." }, "targets": { "title": "URLs, identifiers or search queries", "minItems": 1, "maxItems": 1000, "type": "array", "description": "For Search catalogue, enter keywords or Archive.org search expressions (up to 20 queries). For the other jobs, enter public Archive.org /details/ URLs or item identifiers. Replace the example with your inputs. ISBNs are not resolved automatically.", "items": { "type": "string", "minLength": 1, "maxLength": 2000 } }, "maxResults": { "title": "Maximum results", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum item, review or file rows to export, up to 1,000. Reviews are exported without text or star filters. Page, time and spending limits may return fewer rows; check the coverage summary.", "default": 1 }, "sources": { "title": "Item URLs or identifiers", "type": "array", "description": "For item details, reviews and files. Paste public Archive.org /details/ URLs or item identifiers. Ignored for Search catalogue. ISBNs are not resolved automatically.", "items": { "type": "string" }, "default": [ "https://archive.org/details/goodytwoshoes00newyiala" ] }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Search catalogue only. Use keywords or Archive.org expressions such as creator:(Charles Dickens), subject:astronomy, collection:librivoxaudio or mediatype:texts. Up to 20 queries; matching items are deduplicated.", "items": { "type": "string" }, "default": [] }, "maxPublicPages": { "title": "Maximum page loads (advanced)", "minimum": 1, "maximum": 100, "type": "integer", "description": "JSON/API override: maximum browser page loads including pagination, from 1 to 100. Shared-input requests size this automatically from Maximum results; requests without targets retain the runtime default of 3." }, "maxReviewsPerItem": { "title": "Maximum reviews per item", "minimum": 0, "maximum": 10000, "type": "integer", "description": "JSON/API override: maximum reviews per item. Shared-input requests default to Maximum results; requests without targets retain the runtime default of 10. Zero disables review collection." }, "minStars": { "title": "Minimum stars", "minimum": 0, "maximum": 5, "type": "number", "description": "Retired review filter. Accepted for existing API clients but ignored with a warning; export reviews first and filter the dataset afterwards.", "default": null }, "maxStars": { "title": "Maximum stars", "minimum": 0, "maximum": 5, "type": "number", "description": "Retired review filter. Accepted for existing API clients but ignored with a warning; export reviews first and filter the dataset afterwards.", "default": null }, "reviewTextContains": { "title": "Review text contains", "type": "string", "description": "Retired review filter. Accepted for existing API clients but ignored with a warning; export reviews first and filter the dataset afterwards.", "default": "" }, "analysisQuery": { "title": "Find a phrase in reviews", "type": "string", "description": "JSON/API only: optional literal phrase for the review summary. This never filters or reduces exported reviews." }, "providedRecords": { "title": "Your review records (JSON)", "type": "array", "description": "Paste review records you have permission to process. Validates and deduplicates them without fetching the original websites. Clear to [] for web collection.", "items": { "type": "object" } }, "providedDatasetId": { "title": "Your review dataset ID", "type": "string", "description": "Optional accessible Apify dataset ID. Use either JSON records or a dataset, not both. Supplied records remain marked as unverified." }, "maxItems": { "title": "Maximum supplied records / legacy items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Applies to supplied-record processing and API requests without operation. The new web operations use Maximum results.", "default": 1 }, "isbns": { "title": "ISBNs (legacy)", "type": "array", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "items": { "type": "string" }, "default": [] }, "creators": { "title": "Authors / creators (legacy)", "type": "array", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "items": { "type": "string" }, "default": [] }, "collections": { "title": "Collections (legacy)", "type": "array", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "items": { "type": "string" }, "default": [] }, "subjects": { "title": "Subjects (legacy)", "type": "array", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "items": { "type": "string" }, "default": [] }, "outputMode": { "title": "Output mode (legacy)", "type": "string", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": "reviews_flat" }, "onlyItemsWithReviews": { "title": "Only items with reviews (legacy)", "type": "boolean", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": true }, "includeFiles": { "title": "Include file metadata (legacy)", "type": "boolean", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": false }, "monitoringMode": { "title": "Monitoring mode (legacy)", "type": "string", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": "snapshot" }, "monitoringKey": { "title": "Monitoring key (legacy)", "maxLength": 120, "type": "string", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": "" }, "languageFilter": { "title": "Languages (legacy)", "type": "array", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "items": { "type": "string" }, "default": [] }, "startUrls": { "title": "Structured URLs", "type": "array", "description": "Optional public Internet Archive item URLs; these take precedence over sources.", "items": { "type": "string" }, "default": [] }, "identifiers": { "title": "Structured identifiers", "type": "array", "description": "Optional Internet Archive item identifiers when startUrls are absent.", "items": { "type": "string" }, "default": [] }, "mediatypes": { "title": "Mediatypes (legacy)", "type": "array", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "items": { "type": "string" }, "default": [ "texts" ] }, "includeMetadata": { "title": "Include metadata (legacy)", "type": "boolean", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": true }, "includeReviews": { "title": "Include reviews", "type": "boolean", "description": "Enable public review collection. Disabling it does not emit metadata placeholders.", "default": true }, "includeRawMetadata": { "title": "Include raw metadata (legacy)", "type": "boolean", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": false }, "includeRawReviews": { "title": "Include raw reviews (legacy)", "type": "boolean", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": false }, "searchPageSize": { "title": "Search page size (legacy)", "minimum": 100, "maximum": 1000, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 100 }, "metadataReviewsPageSize": { "title": "Review page size (legacy)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 100 }, "globalConcurrency": { "title": "Global concurrency (legacy)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 2 }, "perHostConcurrency": { "title": "Per-host concurrency (legacy)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 2 }, "requestDelayMs": { "title": "Request delay in milliseconds (legacy)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 250 }, "requestTimeoutSecs": { "title": "Request timeout in seconds (legacy)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 20 }, "maxRetries": { "title": "Maximum retries (legacy)", "minimum": 0, "maximum": 10, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 2 }, "internetArchiveAccessKey": { "title": "Internet Archive access key (optional) (legacy)", "type": "string", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records." }, "internetArchiveSecretKey": { "title": "Internet Archive secret key (optional) (legacy)", "type": "string", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records." }, "debug": { "title": "Debug logging (legacy)", "type": "boolean", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": false }, "batchSize": { "title": "Items per batch (legacy)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records.", "default": 0 }, "continuationToken": { "title": "Continuation token (legacy)", "type": "string", "description": "Inactive in this product workflow. Retained for existing API clients; it does not enable collection, source APIs or filtering of supplied records." } } }, "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 } } } } } } } } } }