{ "openapi": "3.0.1", "info": { "title": "News Website Crawler & Article Extractor", "description": "Extract clean Markdown or plain text from public websites for monitoring, RAG, publishing, and research. Discover through sitemaps and feeds, or use direct URL mode, while respecting robots.txt and host scope.", "version": "0.1", "x-build-id": "2DBLefpigMe6duhFD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xtech~news-source-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xtech-news-source-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/xtech~news-source-crawler/runs": { "post": { "operationId": "runs-sync-xtech-news-source-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/xtech~news-source-crawler/run-sync": { "post": { "operationId": "run-sync-xtech-news-source-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sourceUrls" ], "properties": { "sourceUrls": { "title": "Website or section URLs", "minItems": 1, "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Required. Add up to 20 public website or section URLs. Use a section URL when you only need content from that area of a site.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "sitemapUrls": { "title": "Sitemap URLs (optional)", "maxItems": 100, "uniqueItems": true, "type": "array", "description": "Add a sitemap when you know it. It must belong to one of the website hosts above. The crawler also looks for the website’s published sitemap and feed links automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "discoveryMode": { "title": "Page discovery mode", "enum": [ "discover", "direct" ], "type": "string", "description": "Choose site discovery for broad coverage, or direct URL mode when sourceUrls already contain the exact pages you need. Direct URL mode skips robots sitemap/feed/home-page discovery and is faster and cheaper for known pages.", "default": "discover" }, "maxPages": { "title": "Maximum content pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of clean content pages to save in this run.", "default": 100 }, "includePaths": { "title": "Include paths (optional)", "maxItems": 100, "type": "array", "description": "Only save pages below these website paths, for example /news or /guides. Leave empty to include all paths on each supplied host.", "items": { "type": "string" } }, "excludePaths": { "title": "Exclude paths (optional)", "maxItems": 100, "type": "array", "description": "Skip pages below these website paths, for example /tags or /archive.", "items": { "type": "string" } }, "contentFormat": { "title": "Content format", "enum": [ "markdown", "text" ], "type": "string", "description": "Choose clean Markdown for publishing and AI workflows, or plain text for simple analysis and search.", "default": "markdown" }, "maxConcurrency": { "title": "Maximum concurrent pages", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages to review at once. Use a lower number for a gentler run across several websites.", "default": 4 } } }, "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 } } } } } } } } } }