{ "openapi": "3.0.1", "info": { "title": "Internet Archive & Wayback Machine Scraper - Snapshots & Search", "description": "List Wayback Machine snapshots of any URL or site with date, status and change filters and optional page text, or search archive.org item metadata. Official APIs, no key, $0.50 per 1,000 rows.", "version": "0.1", "x-build-id": "ouR6THYCHIhldYYHJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/skillmerc~internet-archive-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-skillmerc-internet-archive-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/skillmerc~internet-archive-search-scraper/runs": { "post": { "operationId": "runs-sync-skillmerc-internet-archive-search-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/skillmerc~internet-archive-search-scraper/run-sync": { "post": { "operationId": "run-sync-skillmerc-internet-archive-search-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": "Mode", "enum": [ "search", "wayback" ], "type": "string", "description": "\"search\" exports archive.org item metadata (books, audio, video, software). \"wayback\" lists Wayback Machine snapshots of the URLs or sites you enter below.", "default": "search" }, "query": { "title": "Search Query", "type": "string", "description": "Archive.org search query (Lucene syntax). Examples: \"subject:jazz AND mediatype:audio\", \"creator:tolkien\", \"collection:librivoxaudio\"", "default": "mediatype:texts AND subject:python" }, "mediatype": { "title": "Media Type Filter", "type": "string", "description": "Narrow results to a specific media type: texts, audio, movies, software, image, web, data. Leave blank to search all types.", "default": "" }, "sort": { "title": "Sort Order", "type": "string", "description": "Sort results. Examples: \"downloads desc\", \"date desc\", \"titleSorter asc\"", "default": "downloads desc" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of items to return. Hard cap at 10,000.", "default": 100 }, "includeFiles": { "title": "Include File List", "type": "boolean", "description": "Fetch the file manifest for each item. Makes one extra API request per item, so large result sets run much slower.", "default": false }, "urls": { "title": "URLs or domains", "type": "array", "description": "Pages or sites to look up in the Wayback Machine, for example \"example.com\" or \"https://www.python.org/about/\". Used in wayback mode only.", "items": { "type": "string" } }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "exact: only this URL. prefix: every archived URL that starts with it (a folder). host: every page on this host. domain: every page on the domain and its subdomains.", "default": "exact" }, "from": { "title": "From date", "type": "string", "description": "Earliest capture to include, as YYYY, YYYY-MM or YYYY-MM-DD. Leave empty for no limit." }, "to": { "title": "To date", "type": "string", "description": "Latest capture to include, as YYYY, YYYY-MM or YYYY-MM-DD. Leave empty for no limit." }, "collapse": { "title": "Collapse", "enum": [ "none", "day", "month", "year", "digest" ], "type": "string", "description": "Thin out the results. day, month or year: at most one capture per URL per period. digest: changes only, skipping captures whose content is identical to the one before.", "default": "none" }, "statusFilter": { "title": "HTTP status filter", "type": "string", "description": "Only captures with this status code. Accepts a regular expression, for example 200 or 3.. for redirects. Leave empty for all." }, "mimeFilter": { "title": "MIME type filter", "type": "string", "description": "Only captures of this type, for example text/html or application/pdf. Accepts a regular expression. Leave empty for all." }, "maxSnapshotsPerUrl": { "title": "Max snapshots per URL", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many snapshots for each URL or domain.", "default": 100 }, "fetchContent": { "title": "Download page text", "type": "boolean", "description": "Download each archived page and add its title and cleaned text. One extra request per snapshot, about 1.5 seconds each, so use it with a small limit or a collapse setting.", "default": false }, "maxContentChars": { "title": "Max text characters", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Cut the downloaded text to this many characters (0 means no cut). The full length is still reported in text_length.", "default": 20000 } } }, "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 } } } } } } } } } }