{ "openapi": "3.0.1", "info": { "title": "Internet Archive Scraper — Wayback + Search + Metadata [$1.5💰]", "description": "Internet Archive all-in-one scraper — paste a URL or domain for Wayback snapshot history, a keyword for library search, or an item ID for full metadata + file lists. Date filters, availability checks, flat JSON rows. Pure HTTP via open APIs, no browser, no proxies. $1.50/1k rows.", "version": "0.1", "x-build-id": "wzRnfjXwcexnb21BD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~internet-archive-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-internet-archive-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/memo23~internet-archive-scraper/runs": { "post": { "operationId": "runs-sync-memo23-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/memo23~internet-archive-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "queries": { "title": "URLs, domains, search queries, item identifiers, or snapshotOf: lookups", "type": "array", "description": "One query per line. Examples: `example.com` (snapshot history of a domain), `https://example.com/page` (history of one URL), `nasa` (library search), `https://archive.org/details/InformationM` or `item:InformationM` (item metadata + files), `snapshotOf:example.com@20200601` (closest snapshot to a date).", "items": { "type": "string" } }, "archives": { "title": "Archives to query (for URL / domain snapshot history)", "type": "array", "description": "Which web archives to pull snapshot history from. **Wayback Machine** (archive.org) is the default and gives the richest metadata. **archive.today** is a separate mirror that often has pages Wayback missed. **Memento aggregator** (TimeTravel) returns snapshots from 20+ member archives at once. Multiple = merged, each row tagged with its `archive`. Applies to URL/domain queries only (library search & item lookups are archive.org). Tip: enable a proxy in the Proxy section for archive.today / Memento — those mirrors rate-limit per IP.", "items": { "type": "string", "enum": [ "waybackmachine", "archivetoday", "memento" ], "enumTitles": [ "Wayback Machine (archive.org)", "archive.today", "Memento aggregator (20+ archives)" ] }, "default": [ "waybackmachine" ] }, "from": { "title": "From date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Start of the date range. Applies to snapshot timestamps in CDX mode and to `publicdate` in search mode. Defaults to 1996-01-01 (the Wayback Machine's first crawls), i.e. no effective lower bound." }, "to": { "title": "To date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "End of the date range. Applies to snapshot timestamps in CDX mode and to `publicdate` in search mode. Also used as the default target date for `snapshotOf:` lookups without an explicit `@date`. Leave empty for 'up to now'." }, "mediatype": { "title": "Media type (search mode)", "enum": [ "texts", "movies", "audio", "image", "software", "data", "web", "collection", "etree" ], "type": "string", "description": "Restrict library-search results to one archive.org mediatype. Ignored in CDX / metadata / availability modes." }, "collapseSnapshots": { "title": "Collapse duplicate snapshots (CDX mode)", "type": "boolean", "description": "When enabled, consecutive Wayback snapshots with identical content (same digest) are collapsed into one row. Ignored in other modes.", "default": false }, "searchSort": { "title": "Sort order (search mode)", "enum": [ "downloads desc", "downloads asc", "publicdate desc", "publicdate asc", "date desc", "date asc", "titleSorter asc" ], "type": "string", "description": "Sort for library-search results. Default (empty) is relevance." }, "maxItems": { "title": "Maximum items", "minimum": 1, "type": "integer", "description": "Hard cap on total dataset rows across all queries. Always enforced — CDX requests carry an explicit limit so large domains stay fast.", "default": 100 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "How many queries are processed in parallel. archive.org is a nonprofit — keep this low (hard-capped at 5).", "default": 2 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy. Default off. When enabled, retries rotate a fresh IP to ride out per-IP rate limits from archive.org or aggressive archive mirrors. Apify Residential is recommended when you do enable it." } } }, "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 } } } } } } } } } }