{ "openapi": "3.0.1", "info": { "title": "Goodreads Scraper [$1.00/1K💰] | Books + Reviews", "description": "Extract Goodreads books and review text from the official Goodreads API used by Amazon - ISBN, ratings, genres, editions plus reviewer, rating, date and full text. Books and reviews in one run.", "version": "0.2", "x-build-id": "rgKnTShHAynMdldlK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahmed_jasarevic~goodreads-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahmed_jasarevic-goodreads-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ahmed_jasarevic~goodreads-scraper/runs": { "post": { "operationId": "runs-sync-ahmed_jasarevic-goodreads-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/ahmed_jasarevic~goodreads-scraper/run-sync": { "post": { "operationId": "run-sync-ahmed_jasarevic-goodreads-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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Public Goodreads URLs. Supported: a book page (/book/show/3), a genre (/genres/art), a shelf (/shelf/show/...), a list (/list/show/...), an author's book list (/author/list/...), an ISBN page (/book/isbn/9780441013593) or a search URL (/search?q=dune). Genre, shelf, list and ISBN pages contribute up to 'max books per source' books, each with its own reviews.", "items": { "type": "string" }, "default": [ "https://www.goodreads.com/book/show/3" ] }, "bookIds": { "title": "Book IDs", "type": "array", "description": "Goodreads book legacy IDs (the number in /book/show/). Used when you do not want to build full URLs.", "items": { "type": "string" }, "default": [] }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Title/author search terms, resolved to book IDs. Each term returns only a handful of matches, so this is best-effort - prefer startUrls with a search URL, genre or list page for full coverage.", "items": { "type": "string" }, "default": [] }, "maxItems": { "title": "Maximum items", "type": "integer", "description": "Total number of books to scrape. This is the only size limit: it is shared by all start URLs, book IDs and search terms, and it is split evenly between them, so no single URL can use up the whole run.", "default": 100 }, "includeReviews": { "title": "Include reviews", "type": "boolean", "description": "Fetch individual review rows (text, rating, date, reviewer). Reviews go to their own separate dataset; books always go to the books dataset.", "default": true }, "maxReviewsPerBook": { "title": "Maximum reviews per book", "type": "integer", "description": "Maximum number of reviews to pull per book. Reviews are paged through with cursor pagination.", "default": 20 }, "reviewSort": { "title": "Review sort order", "enum": [ "DEFAULT", "NEWEST", "OLDEST" ], "type": "string", "description": "How to order reviews.", "default": "DEFAULT" }, "reviewMinRating": { "title": "Minimum review rating", "minimum": 1, "maximum": 5, "type": "integer", "description": "Only return reviews with at least this star rating (1-5). Leave empty for all ratings." }, "reviewMaxRating": { "title": "Maximum review rating", "minimum": 1, "maximum": 5, "type": "integer", "description": "Only return reviews with at most this star rating (1-5). Leave empty for all ratings." }, "includeEditions": { "title": "Include other editions", "type": "boolean", "description": "Also resolve sibling editions of the same work (different ISBNs / formats of the same title).", "default": false }, "stripHtmlFromReviews": { "title": "Strip HTML from review text", "type": "boolean", "description": "Convert review text from Goodreads' HTML format to plain text. When false, the original HTML is kept in reviewTextHtml.", "default": true }, "maxRequestsPerCrawl": { "title": "Maximum API requests", "type": "integer", "description": "Hard safety cap on total network requests made by this run. Set to 0 for unlimited.", "default": 5000 }, "maxConcurrency": { "title": "Max concurrency", "type": "integer", "description": "Number of books processed in parallel. 5-10 is comfortable; keep it modest out of courtesy.", "default": 5 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Select proxies to be used by your crawler." } } }, "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 } } } } } } } } } }