Ultimate Articles Extractor
Pricing
$25.00/month + usage
Go to Store
Ultimate Articles Extractor
A powerful and modular web scraping tool designed to extract content from any webpage, article, or news site. Get clean, structured data from any website with optimized extraction algorithms, anti-bot detection avoidance, and proxy support.
5.0 (2)
Pricing
$25.00/month + usage
3
Total users
4
Monthly users
4
Runs succeeded
>99%
Last modified
2 months ago
You can access the Ultimate Articles Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "w6opE8crz4txDcDSt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/web.harvester~ultimate-articles-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-web.harvester-ultimate-articles-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/web.harvester~ultimate-articles-extractor/runs": { "post": { "operationId": "runs-sync-web.harvester-ultimate-articles-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/web.harvester~ultimate-articles-extractor/run-sync": { "post": { "operationId": "run-sync-web.harvester-ultimate-articles-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": [ "startUrls", "extractorEngine" ], "properties": { "startUrls": { "title": "Article URLs", "type": "array", "description": "Enter URLs of articles you want to extract content from. The extractor will parse the content and extract title, main text, author information, publication date, and other metadata.", "items": { "type": "string" } }, "extractorEngine": { "title": "Extraction Engine", "enum": [ "newspaper4k", "trafilatura", "boilerpy3", "news-please", "goose3", "article-parser", "justext" ], "type": "string", "description": "Choose which extraction engine to use. Each has unique strengths: Newspaper4k (best all-around), Trafilatura (best for news), Boilerpy3 (fastest), News-Please (rich metadata), Goose3 (good with images), Article Parser (HTML/markdown output), JusText (boilerplate removal).", "default": "newspaper4k" }, "saveHtml": { "title": "Save Full Page HTML", "type": "boolean", "description": "Enable this option to save the complete HTML of each webpage alongside the extracted content.", "default": false }, "saveArticleHtml": { "title": "Save Article HTML (not for all methods)", "type": "boolean", "description": "When enabled, preserves the cleaned article HTML from Newspaper4k and Article Parser extractors in the output. This includes only the article content (not the full page) with its formatting, links, and embedded media intact. Only works when using the Newspaper4k or Article Parser extraction methods.", "default": false }, "maxRetries": { "title": "Maximum Retries", "minimum": 1, "type": "integer", "description": "How many times to retry if a page fails to load. More retries means better chance of success but may take longer. Default (25) works well for most sites.", "default": 15 }, "useHeaderGenerator": { "title": "Use Smart Header Generator (recommended)", "type": "boolean", "description": "Automatically generate realistic browser headers for each request to help bypass anti-bot measures.", "default": true }, "headerGeneratorOptions": { "title": "Header Generator Options", "type": "object", "description": "Configure which devices and browsers to emulate when generating headers. Only applies when Smart Header Generator is enabled." }, "customHeaders": { "title": "Custom Headers", "type": "object", "description": "Add specific HTTP headers to your requests. Useful for accessing sites that require certain headers or for mimicking specific browsers." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxies to avoid IP blocking and access region-restricted content.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } }}Ultimate Article Extractor OpenAPI definition
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 Ultimate Articles Extractor 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:
