{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor & URL Change Monitor", "description": "Sitemap extractor API for complete XML, gzip, text and nested sitemap inventories. Export normalized URLs or monitor new, publisher-lastmod-changed and conservatively confirmed removed URLs. Failed or partial trees never manufacture mass removals.", "version": "0.1", "x-build-id": "EWGfcV12eKxI64ZlJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automa-flow~sitemap-extractor-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automa-flow-sitemap-extractor-monitor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automa-flow~sitemap-extractor-monitor/runs": { "post": { "operationId": "runs-sync-automa-flow-sitemap-extractor-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automa-flow~sitemap-extractor-monitor/run-sync": { "post": { "operationId": "run-sync-automa-flow-sitemap-extractor-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sites" ], "properties": { "sites": { "title": "Websites or sitemaps", "minItems": 1, "maxItems": 100, "type": "array", "description": "One to 100 root websites, robots.txt URLs, direct sitemap files, sitemap indexes, .xml.gz files, or text sitemaps. externalId is echoed for downstream joins.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "title": "Website, robots.txt, or sitemap URL", "type": "string", "description": "Public HTTP(S) target. Embedded credentials, private networks and non-web ports are rejected.", "editor": "textfield", "maxLength": 2048 }, "externalId": { "title": "Your external ID", "type": "string", "description": "Optional client, competitor, migration or pipeline identifier.", "editor": "textfield", "maxLength": 200 } } } }, "mode": { "title": "Mode", "enum": [ "snapshot", "monitor" ], "type": "string", "description": "snapshot extracts the current inventory without state. monitor compares only complete successful inventories in Apify KVS.", "default": "snapshot" }, "outputMode": { "title": "Output mode", "enum": [ "changesOnly", "all" ], "type": "string", "description": "changesOnly emits URL rows only for real changes; the first baseline and unchanged runs still return one site_summary. Snapshot mode always returns extracted URLs.", "default": "all" }, "discoverFromRobots": { "title": "Discover from robots.txt", "type": "boolean", "description": "For root websites, read every Sitemap: declaration first. If none exist, try /sitemap.xml. Direct sitemap and robots.txt inputs are always respected.", "default": true }, "checkPageStatus": { "title": "Check emitted page status", "type": "boolean", "description": "Optional lightweight checks for emitted current URL rows only. Disabled by default: extracting a million URLs must not make a million page requests.", "default": false }, "includePatterns": { "title": "Include URL glob patterns", "maxItems": 100, "type": "array", "description": "Optional case-sensitive glob patterns such as *://*/blog/* or *product*. Empty means include every sitemap URL. Pattern changes use a separate monitor state namespace.", "items": { "type": "string", "maxLength": 500 }, "default": [] }, "excludePatterns": { "title": "Exclude URL glob patterns", "maxItems": 100, "type": "array", "description": "Optional case-sensitive glob patterns such as */tag/* or *?preview=*. Exclusions run after includes.", "items": { "type": "string", "maxLength": 500 }, "default": [] } } }, "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 } } } } } } } } } }