{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper: Search, Metadata, Wayback CDX", "description": "Internet Archive scraper using only official APIs: search archive.org items, get item metadata with file lists and download links, or list Wayback Machine snapshots (CDX). Metadata and links only, no file downloads. Polite rate limit, retries.", "version": "0.1", "x-build-id": "yebvfwVICstZEV9sn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/firebrick_zamia~internet-archive-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-firebrick_zamia-internet-archive-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/firebrick_zamia~internet-archive-search/runs": { "post": { "operationId": "runs-sync-firebrick_zamia-internet-archive-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/firebrick_zamia~internet-archive-search/run-sync": { "post": { "operationId": "run-sync-firebrick_zamia-internet-archive-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "details", "snapshots" ], "type": "string", "description": "search: find archive.org items. details: metadata and file list for known identifiers. snapshots: list Wayback Machine captures of URLs.", "default": "search" }, "query": { "title": "Search query", "type": "string", "description": "Search mode: archive.org search query (Lucene syntax is accepted, e.g. creator:nasa AND subject:moon). Leave empty if you set a media type, collection or date filter." }, "mediatype": { "title": "Media type", "enum": [ "", "texts", "movies", "audio", "software", "image", "data", "web", "collection", "etree", "education" ], "type": "string", "description": "Search mode: restrict to one media type. Empty means any.", "default": "" }, "collection": { "title": "Collection", "type": "string", "description": "Search mode: restrict to one collection identifier, for example nasa or prelinger. Empty means any." }, "dateFrom": { "title": "Date from", "type": "string", "description": "Search mode: earliest item date, YYYY or YYYY-MM-DD. Snapshots mode: earliest capture date, YYYY, YYYY-MM or YYYY-MM-DD." }, "dateTo": { "title": "Date to", "type": "string", "description": "Search mode: latest item date, YYYY or YYYY-MM-DD. Snapshots mode: latest capture date, YYYY, YYYY-MM or YYYY-MM-DD." }, "sort": { "title": "Sort order", "enum": [ "", "downloads desc", "date desc", "date asc", "publicdate desc", "addeddate desc" ], "type": "string", "description": "Search mode: sort order of results. Relevance is the default of archive.org.", "default": "" }, "maxItems": { "title": "Maximum items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Search mode: maximum number of items to return (1 to 10,000). Each item is one billed result.", "default": 50 }, "identifiers": { "title": "Item identifiers", "type": "array", "description": "Details mode: archive.org identifiers or item URLs (https://archive.org/details/...), one per line, up to 500.", "items": { "type": "string" } }, "includeFiles": { "title": "Include file list", "type": "boolean", "description": "Details mode: add the list of files with sizes, checksums and download URLs. Files are never downloaded, only linked.", "default": true }, "includeDerivatives": { "title": "Include derivative files", "type": "boolean", "description": "Details mode: also list files generated by archive.org (thumbnails, OCR text, conversions). Off lists only original uploads.", "default": false }, "urls": { "title": "URLs to look up", "type": "array", "description": "Snapshots mode: URLs, domains or URL prefixes to list Wayback Machine captures for, one per line, up to 100.", "items": { "type": "string" } }, "matchType": { "title": "URL match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Snapshots mode: exact matches the URL only, prefix matches everything below the path, host matches one host, domain includes subdomains.", "default": "exact" }, "collapseByDigest": { "title": "Collapse identical captures", "type": "boolean", "description": "Snapshots mode: skip a capture when its content is identical to the previous one (same digest), so you only see changes.", "default": true }, "statusCodeFilter": { "title": "HTTP status filter", "type": "string", "description": "Snapshots mode: keep only captures with this HTTP status code, for example 200. Empty means any.", "default": "200" }, "mimeTypeFilter": { "title": "MIME type filter", "type": "string", "description": "Snapshots mode: keep only captures with this MIME type, for example text/html. Empty means any." }, "maxSnapshots": { "title": "Maximum snapshots per URL", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Snapshots mode: maximum captures returned for each URL (1 to 10,000). Each snapshot is one billed result.", "default": 100 } } }, "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 } } } } } } } } } }