{ "openapi": "3.0.1", "info": { "title": "WordPress Posts Scraper - Extract Articles & Metadata", "description": "Extract posts, articles, and metadata from any WordPress site using REST API. 20+ filters: date ranges, categories, tags, 0authors, search keywords. Get title, content, author bio, featured images & more. No WordPress account needed.\nFast, reliable data extraction for content aggregation & research.", "version": "0.0", "x-build-id": "p93FcRPNh1u9bjcrd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/devnaz~wordpress-posts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-devnaz-wordpress-posts-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/devnaz~wordpress-posts-scraper/runs": { "post": { "operationId": "runs-sync-devnaz-wordpress-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/devnaz~wordpress-posts-scraper/run-sync": { "post": { "operationId": "run-sync-devnaz-wordpress-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "WordPress Site URLs", "type": "array", "description": "List of WordPress sites to scrape posts from (e.g., https://techcrunch.com)", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPosts": { "title": "Maximum Posts", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum total number of posts to extract per site (default: 5)", "default": 5 }, "perPage": { "title": "Posts Per Request (Advanced)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of posts to fetch per API request (default: 50, max: 100). Higher values = fewer requests = lower cost, but may timeout on large sites. Reduce to 10-20 if you experience timeouts.", "default": 50 }, "searchKeyword": { "title": "Search Keyword (Optional)", "type": "string", "description": "Filter posts by keyword search (leave empty to get all posts)" }, "after": { "title": "Published After Date (Optional)", "type": "string", "description": "Limit to posts published after this date (ISO8601 format: 2025-01-01T00:00:00)" }, "before": { "title": "Published Before Date (Optional)", "type": "string", "description": "Limit to posts published before this date (ISO8601 format: 2025-12-31T23:59:59)" }, "modifiedAfter": { "title": "Modified After Date (Optional)", "type": "string", "description": "Limit to posts modified after this date (ISO8601 format)" }, "modifiedBefore": { "title": "Modified Before Date (Optional)", "type": "string", "description": "Limit to posts modified before this date (ISO8601 format)" }, "categories": { "title": "Category IDs (Optional)", "type": "array", "description": "Filter by category IDs (comma-separated, e.g., [1, 5, 12])", "items": { "type": "string" } }, "categoriesExclude": { "title": "Exclude Category IDs (Optional)", "type": "array", "description": "Exclude posts from specific category IDs", "items": { "type": "string" } }, "tags": { "title": "Tag IDs (Optional)", "type": "array", "description": "Filter by tag IDs (comma-separated)", "items": { "type": "string" } }, "tagsExclude": { "title": "Exclude Tag IDs (Optional)", "type": "array", "description": "Exclude posts with specific tag IDs", "items": { "type": "string" } }, "author": { "title": "Author IDs (Optional)", "type": "array", "description": "Filter by author IDs (comma-separated)", "items": { "type": "string" } }, "authorExclude": { "title": "Exclude Author IDs (Optional)", "type": "array", "description": "Exclude posts by specific author IDs", "items": { "type": "string" } }, "status": { "title": "Post Status", "enum": [ "publish", "draft", "pending", "private", "future" ], "type": "string", "description": "Filter by post status", "default": "publish" }, "orderBy": { "title": "Order By", "enum": [ "date", "modified", "title", "author", "id", "relevance" ], "type": "string", "description": "Sort posts by field", "default": "date" }, "order": { "title": "Order Direction", "enum": [ "asc", "desc" ], "type": "string", "description": "Sort order (ascending or descending)", "default": "desc" }, "sticky": { "title": "Sticky Posts Only", "type": "boolean", "description": "Include only sticky posts (pinned posts)", "default": false }, "slug": { "title": "Post Slug (Optional)", "type": "string", "description": "Filter by specific post slug" }, "offset": { "title": "Offset (Optional)", "minimum": 0, "type": "integer", "description": "Skip a specific number of posts (for pagination)", "default": 0 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings (optional - not needed for most WordPress sites)" } } }, "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 } } } } } } } } } }