{ "openapi": "3.0.1", "info": { "title": "Internet Archive & Wayback Machine Scraper", "description": "Search the Internet Archive's 40M+ items, pull full item metadata and file lists, and query the Wayback Machine for URL snapshots. Books, audio, video, software, and archived pages on official archive.org APIs. No API key.", "version": "0.0", "x-build-id": "YMABmhiY1lWVzifx0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mangudai~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mangudai-internet-archive-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mangudai~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-mangudai-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mangudai~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-mangudai-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "What to do", "enum": [ "search", "itemMetadata", "waybackCaptures", "waybackClosest" ], "type": "string", "description": "Pick the job. Search finds items; item metadata pulls the full record and file list; the two Wayback modes look up historical snapshots of a URL.", "default": "search" }, "searchQueries": { "title": "Search queries", "type": "array", "description": "One search per line. Used only in Search mode.", "items": { "type": "string" } }, "mediaType": { "title": "Media type", "enum": [ "all", "texts", "movies", "audio", "software", "image", "data", "web", "collection", "etree" ], "type": "string", "description": "Narrow a search to one media type.", "default": "all" }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "downloads desc", "date desc", "date asc", "titleSorter asc", "titleSorter desc" ], "type": "string", "description": "Order of search results.", "default": "relevance" }, "maxResults": { "title": "Max results per query or URL", "minimum": 1, "maximum": 500, "type": "integer", "description": "Caps items per search query, or snapshots per URL in Wayback captures mode.", "default": 50 }, "identifiers": { "title": "Item identifiers", "type": "array", "description": "Archive.org item identifiers, one per line (the last part of an archive.org/details/ URL). Used only in Item metadata mode.", "items": { "type": "string" } }, "urls": { "title": "URLs", "type": "array", "description": "Web addresses to look up in the Wayback Machine, one per line. Used by both Wayback modes.", "items": { "type": "string" } }, "waybackFrom": { "title": "Wayback from (YYYY or YYYYMMDD)", "type": "string", "description": "Only snapshots on or after this date. Wayback captures mode." }, "waybackTo": { "title": "Wayback to (YYYY or YYYYMMDD)", "type": "string", "description": "Only snapshots on or before this date. Wayback captures mode." }, "waybackTimestamp": { "title": "Closest to date (YYYYMMDD)", "type": "string", "description": "Find the snapshot nearest this date. Wayback closest snapshot mode. Leave empty for the most recent." } } }, "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 } } } } } } } } } }