{ "openapi": "3.0.1", "info": { "title": "WordPress Content Scraper", "description": "Scrapes any self-hosted WordPress site via its public REST API — posts, pages, media, categories, tags, comments, users, even custom post types. No login. Raw JSON passthrough, honest pagination, and a clear error row for sites that disable their REST API.", "version": "0.1", "x-build-id": "XDZNIgsZ353TnYx0H" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~wordpress-content-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-wordpress-content-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~wordpress-content-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-wordpress-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~wordpress-content-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-wordpress-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Base URL of each self-hosted WordPress site to scrape, e.g. `https://example.com` or `example.com/blog`. Every site is queried through its own public `/wp-json/wp/v2/` REST API -- the same one WordPress core exposes by default, with no login. A site that has disabled its REST API, or is not WordPress at all, gets a single ERROR row explaining why rather than stopping the whole run.", "default": [], "items": { "type": "string" } }, "resources": { "title": "Content types to fetch", "type": "array", "description": "Which built-in WordPress collections to pull from each site, in the SAME run -- these are independent resources sharing one client, not exclusive modes, so picking several is normal (e.g. posts + categories + tags together). Each gets its own SEARCH_SUMMARY row per site.", "items": { "type": "string", "enum": [ "posts", "pages", "media", "comments", "categories", "tags", "users" ], "enumTitles": [ "Posts", "Pages", "Media (images/files)", "Comments", "Categories", "Tags", "Users/authors" ] }, "default": [ "posts" ] }, "customPostTypes": { "title": "Custom post type REST slugs", "type": "array", "description": "Extra REST base slugs for non-core content this site's theme/plugins registered with `show_in_rest` (e.g. a WooCommerce `product`, a portfolio `project`). Fetched exactly like the built-in resources above, under a `CUSTOM_` record type. A slug that is not actually registered on the site fails with a clear `not_found` ERROR row for just that resource, not the whole site -- check the site's `/wp-json/` route index first if unsure.", "default": [], "items": { "type": "string" } }, "search": { "title": "Search query", "type": "string", "description": "Full-text search applied to every selected resource on every site, using WordPress's own `search` parameter. Leave empty to fetch each resource's full listing (newest first) instead.", "default": "" }, "after": { "title": "Published after", "type": "string", "description": "ISO 8601 datetime, e.g. `2026-01-01T00:00:00`. Only applies to date-bearing resources (posts, pages, media, comments, custom post types) -- silently skipped for categories/tags/users, which have no date field. Leave empty for no lower bound.", "default": "" }, "before": { "title": "Published before", "type": "string", "description": "ISO 8601 datetime. Same scope as 'Published after'. Leave empty for no upper bound.", "default": "" }, "embed": { "title": "Embed related objects (_embed)", "type": "boolean", "description": "Adds WordPress's own `_embed=true` flag, which inlines the author, featured image and taxonomy terms directly into each post/page/media/comment row under `_embedded` -- avoiding a separate request per related object. On by default; turn off only to shrink payload size.", "default": true }, "perPage": { "title": "Items per request", "minimum": 1, "maximum": 100, "type": "integer", "description": "WordPress's own `per_page` parameter. Hard-capped at 100 by the API -- any higher value fails that resource's fetch with a 400.", "default": 100 }, "maxItemsPerResource": { "title": "Max items per (site, resource) pair", "minimum": 0, "type": "integer", "description": "Stop paging one resource on one site after this many items. Set to 0 for unlimited (walks every page WordPress reports via X-WP-TotalPages). With multiple sites/resources selected, this cap applies separately to each pair.", "default": 200 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Upper bound on requests in flight at once, across every site and resource this run touches.", "default": 5 }, "minRequestInterval": { "title": "Min seconds between request starts, per site", "minimum": 0, "type": "number", "description": "Pacing floor applied separately to each site (not shared globally across different sites), independent of 'Max concurrent requests'. No rate-limit or WAF gate was observed on any site tested, but inputs here are arbitrary user-supplied installs -- some may be small blogs on modest shared hosting, unlike this portfolio's usual large fixed targets. Set to 0 to disable.", "default": 0.5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "The WordPress REST API is public by design and no bot-mitigation gate was observed on any site tested, including ones behind Cloudflare. Apify's automatic proxy is the cloud default; residential is not forced since this actor targets arbitrary sites worldwide rather than one region.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }