{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper — Archive.org Snapshots & URL History", "description": "Every Wayback Machine (archive.org) capture of a URL, folder, host or domain: timestamp, status, MIME type, digest and archive links. Unique versions, daily/yearly sampling, unique URLs, per-site summaries, optional archived page Markdown. $2 per 1,000 snapshots.", "version": "0.1", "x-build-id": "7SP4Zt5lupMh3qzMF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~wayback-snapshots/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-wayback-snapshots", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~wayback-snapshots/runs": { "post": { "operationId": "runs-sync-actor-forge-wayback-snapshots", "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/actor-forge~wayback-snapshots/run-sync": { "post": { "operationId": "run-sync-actor-forge-wayback-snapshots", "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", "required": [ "urls" ], "properties": { "urls": { "title": "URLs or domains", "type": "array", "description": "Pages, folders or domains to look up in the Wayback Machine, e.g. example.com, https://example.com/pricing. Shortcuts: example.com/blog/* = everything under that path, *.example.com = the whole domain with subdomains.", "items": { "type": "string" } }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Exact: that one URL. Prefix: every URL starting with it (a folder). Host: every URL on that host name. Domain: the host and all its subdomains. Prefix/host/domain queries are slow on archive.org's side (20–40 s per index page).", "default": "exact" }, "outputMode": { "title": "Output", "enum": [ "snapshots", "summary" ], "type": "string", "description": "Snapshots: one row per archived capture. Summary: one row per input — first and last capture, total captures, captures per year, missing years (charged per summary, not per capture).", "default": "snapshots" }, "collapse": { "title": "Collapse captures", "enum": [ "digest", "none", "hourly", "daily", "monthly", "yearly", "unique-urls" ], "type": "string", "description": "Busy pages are captured thousands of times with identical content. Unique versions (default) keeps a capture only when the content changed. Hourly/daily/monthly/yearly keep the first capture of each period. Unique URLs keeps one row per distinct URL (best with prefix/host/domain to list every archived page of a site). None returns every capture.", "default": "digest" }, "from": { "title": "From date", "type": "string", "description": "Only captures on or after this date: 2015, 201505, 20150501 or 2015-05-01." }, "to": { "title": "To date", "type": "string", "description": "Only captures on or before this date (the whole period is included: 2018 means up to 31 Dec 2018)." }, "statusFilter": { "title": "HTTP status filter", "type": "string", "description": "Only captures with these HTTP status codes, comma-separated: 200, 2xx, 200,301 — or exclude with !404, !5xx. Empty = all (includes redirects and errors)." }, "mimeFilter": { "title": "MIME type filter", "type": "string", "description": "Only captures of these content types: text/html, application/pdf, image/* — or exclude with !image/*. Empty = all." }, "newestFirst": { "title": "Newest first", "type": "boolean", "description": "Exact URLs only: return the most recent captures (up to the max per URL) newest first, instead of the oldest first.", "default": false }, "maxSnapshotsPerUrl": { "title": "Max snapshots per URL", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many snapshot rows for each input. Each row is charged, so this is also your cost cap per URL.", "default": 1000 }, "fetchContent": { "title": "Fetch archived page content", "type": "boolean", "description": "Download the archived HTML of snapshots and add the page title and main content as Markdown/text (charged per page, see pricing). Only HTML captures with status 200 are fetched.", "default": false }, "maxContentPages": { "title": "Max pages with content", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Fetch content for at most this many snapshots in the run (the first ones delivered). Failed fetches don't count.", "default": 10 }, "contentFormat": { "title": "Content format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "What to include when fetching content.", "default": "markdown" }, "maxIndexPagesPerUrl": { "title": "Max index pages per URL (prefix/host/domain)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Prefix, host and domain queries walk archive.org's index page by page (each ~3,000–7,000 captures, 20–40 s). Stop after this many pages per input, even if fewer snapshots than the max were found (e.g. with tight filters on a huge site).", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed normally — archive.org's CDX API is public. Turn on Apify Proxy only if your runs keep hitting rate limits.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }