{ "openapi": "3.0.1", "info": { "title": "Ultimate URL Harvester — All Site URLs from 6 Archives", "description": "Get every known URL of any domain from Wayback Machine, Common Crawl, AlienVault OTX, URLScan, crt.sh and sitemap — merged & deduped. Block-proof, no API key.", "version": "1.0", "x-build-id": "B5Lhw6e2mXTlXlYfp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/inexhaustible_glass~url-harvester/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-inexhaustible_glass-url-harvester", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/inexhaustible_glass~url-harvester/runs": { "post": { "operationId": "runs-sync-inexhaustible_glass-url-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/inexhaustible_glass~url-harvester/run-sync": { "post": { "operationId": "run-sync-inexhaustible_glass-url-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "domain" ], "properties": { "domain": { "title": "Domain", "type": "string", "description": "The domain to harvest URLs for, e.g. example.com (no http://)." }, "sources": { "title": "Sources", "type": "array", "description": "Which public archives to query. All are free and need no API key.", "items": { "type": "string", "enum": [ "wayback", "commoncrawl", "otx", "urlscan", "crtsh", "certspotter", "sitemap", "livecrawl" ], "enumTitles": [ "Wayback Machine", "Common Crawl", "AlienVault OTX", "URLScan.io", "crt.sh (CT logs)", "CertSpotter (CT logs)", "sitemap.xml", "Live crawl (hits site)" ] }, "default": [ "wayback", "commoncrawl", "otx", "urlscan", "crtsh", "certspotter", "sitemap" ] }, "ccIndexes": { "title": "Common Crawl indexes to query", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many Common Crawl monthly indexes to search (more = far more URLs, a bit slower). 125 available.", "default": 5 }, "liveCrawl": { "title": "Also live-crawl the site (freshest pages)", "type": "boolean", "description": "Crawl the live website too, to catch brand-new pages not yet in any archive. Note: this DOES hit the target site (not block-proof).", "default": false }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Also collect URLs from subdomains (blog.example.com, etc.).", "default": true }, "maxUrls": { "title": "Max URLs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of URLs to return.", "default": 10000 }, "extensions": { "title": "Filter by file extension", "type": "array", "description": "Only keep URLs with these extensions, e.g. pdf, js, json. Empty = all.", "default": [], "items": { "type": "string" } }, "keyword": { "title": "Filter by keyword", "type": "string", "description": "Only keep URLs containing this text. Empty = all.", "default": "" }, "declutter": { "title": "Declutter (remove near-duplicate URLs)", "type": "boolean", "description": "Collapse URLs that differ only by numbers/parameter values.", "default": true }, "fetchContent": { "title": "Fetch archived content (block-proof)", "type": "boolean", "description": "Also fetch each URL's saved HTML from Wayback (slower, never hits the live site).", "default": 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 } } }, "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 } } } } } } } } } }