{ "openapi": "3.0.1", "info": { "title": "Sitemap Scraper: Every URL on Any Site", "description": "Get every URL a website publishes, from a bare domain. Finds the sitemap through robots.txt or the usual paths, follows nested sitemap index files to any depth, unpacks .xml.gz, and returns each URL with lastmod, changefreq and priority. Filter by path regex or by what changed since a date.", "version": "0.1", "x-build-id": "domFWIh21p9V8gDkf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/glitchbound~sitemap-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-glitchbound-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/glitchbound~sitemap-scraper/runs": { "post": { "operationId": "runs-sync-glitchbound-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/glitchbound~sitemap-scraper/run-sync": { "post": { "operationId": "run-sync-glitchbound-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites", "uniqueItems": true, "type": "array", "description": "Sites to pull the sitemap from, one per line. A bare domain like apify.com is enough, since the sitemap is discovered from robots.txt or the usual paths. You can also paste a sitemap URL directly.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Stop after this many URLs per site. Nested sitemap index files are followed automatically until this cap is hit. The form is prefilled with 50 so a first run costs cents; the cap when this field is left out entirely is 5000.", "default": 5000 }, "includePattern": { "title": "Only paths matching", "type": "string", "description": "Regular expression tested against the URL path. Example: ^/blog/ keeps only blog posts." }, "excludePattern": { "title": "Skip paths matching", "type": "string", "description": "Regular expression tested against the URL path. Example: /(tag|author|page)/ drops paginated and taxonomy pages." }, "changedSince": { "title": "Changed since", "type": "string", "description": "Only URLs whose is on or after this date (YYYY-MM-DD). URLs with no lastmod are dropped. Use it to pull just what changed since your last crawl." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy settings.", "default": { "useApifyProxy": true } }, "maxItems": { "title": "Maximum results (whole run)", "minimum": 0, "type": "integer", "description": "A hard ceiling on rows for the entire run, across every target. The per-target limits above cap each one separately, so fifty targets at twenty each is still a thousand rows; this caps the total. The run stops cleanly when it is reached and nothing beyond that point is fetched or charged. Leave empty for no ceiling." } } }, "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 } } } } } } } } } }