Article Content Extractor — Clean Text for RAG & LLM
Pricing
from $8.00 / 1,000 useful article rows
Go to Apify Store
Article Content Extractor — Clean Text for RAG & LLM
Try Input: 1 URL ≈ USD 0.008. From USD 8/1k useful rows. Paste URL and Start.
Article Content Extractor — Clean Text for RAG & LLM
Pricing
from $8.00 / 1,000 useful article rows
Try Input: 1 URL ≈ USD 0.008. From USD 8/1k useful rows. Paste URL and Start.
You can access the Article Content Extractor — Clean Text for RAG & LLM programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "AhBBWSly8OcxxZ9QM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/taroyamada~article-content-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-taroyamada-article-content-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/taroyamada~article-content-extractor/runs": { "post": { "operationId": "runs-sync-taroyamada-article-content-extractor", "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/taroyamada~article-content-extractor/run-sync": { "post": { "operationId": "run-sync-taroyamada-article-content-extractor", "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": [ "urls" ], "properties": { "urls": { "title": "Article URLs", "type": "array", "description": "Paste 1–10 public article/news/blog URLs. First proof: leave other fields default and Start.", "items": { "type": "string" } }, "outputFormat": { "title": "Output Format", "enum": [ "text", "markdown" ], "type": "string", "description": "Content output format. Markdown is recommended for first-run proof and LLM ingestion.", "default": "markdown" }, "includeImages": { "title": "Include Images", "type": "boolean", "description": "Include the inline images array in the result. The heroImage field can still be returned separately when available.", "default": false }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel article requests (1-10).", "default": 5 }, "timeoutMs": { "title": "Timeout (ms)", "minimum": 1000, "maximum": 30000, "type": "integer", "description": "Request timeout per article in milliseconds.", "default": 15000 }, "maxResponseBytes": { "title": "Maximum response bytes", "minimum": 32768, "maximum": 10485760, "type": "integer", "description": "Reject HTML responses larger than this limit before parsing.", "default": 5242880 }, "maxRedirects": { "title": "Maximum redirects", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum public HTTP redirects followed per article.", "default": 3 }, "delivery": { "title": "Delivery", "enum": [ "dataset", "webhook" ], "type": "string", "description": "Select dataset-only output or webhook handoff. Non-dry-run always writes canonical dataset rows first; webhook delivery runs only after dataset/PPE output succeeds.", "default": "dataset" }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "URL to POST article payloads when delivery=webhook. The webhook is sent after canonical dataset rows and PPE output succeed, and is skipped on dryRun." }, "generateReport": { "title": "Generate content audit report", "type": "boolean", "description": "Optional. Leave false for first proof (~$0.008 useful row). true charges one article-content-audit-report.", "default": false }, "emitExport": { "title": "Generate batch export event", "type": "boolean", "description": "Optional. Leave false for first proof (~$0.008 useful row). true charges one article-batch-export.", "default": false }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Validate input and write only local output. When true, dataset writes and webhook delivery are disabled.", "default": false } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Article Content Extractor — Clean Text for RAG & LLM from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: