Article Extractor — extract webpage content

Extract Article From Web API

What it does

Article Extractor pulls the main content and metadata from a webpage when you send it a URL. It returns the article body plus any available title, author, date, images, language, confidence scores, source URL, and word count.

Use it when you need clean article text without scraping the page yourself. The input is a single url in the request body, and the response gives you structured fields you can store, index, or pass into downstream analysis.

It is useful for content monitoring, news aggregation, research pipelines, and SEO workflows that need to compare published copy across pages. You can also use the confidence object to decide whether the extracted body, title, or author is reliable enough for automated processing.

Article Extractor keeps the output focused on the data the page actually exposes, so you can validate content, archive articles, or build text-processing features from a predictable schema.

{ "body": "Article text...", "date": "2024-01-15", "title": "Sample Article Title", "author": "Jane Doe", "images": ["https://example.com/image.jpg"], "language": "en", "confidence": { "body": 0.98, "title": 0.95, "author": 0.88 }, "source_url": "https://example.com/news/sample-article", "word_count": 742 }

About this endpoint

What it does

Extracts article content from a webpage URL and returns the parsed article fields in a JSON object. The request sends the target webpage URL, and the response may include the article body, metadata, detected language, confidence scores, source URL, and word count.

Request Body

Parameter	Type	Mandatory	Description
url	String	Yes	URL of the webpage to extract, audit, or validate content from. Must be a valid `http` or `https` URI.

Response

Returns a JSON object with top-level fields for the extracted article content and metadata: body (string), date (string in date format), title (string), author (string), images (string array of URI values), language (string), confidence (object), source_url (string in URI format), and word_count (integer). The confidence object contains body, title, and author number fields.

Parameter	Type	Mandatory	Description
body	String	No	Extracted article body text.
date	String	No	Article date in `YYYY-MM-DD` format.
title	String	No	Article title.
author	String	No	Article author.
images	String Array	No	Image URLs extracted from the article. Each item is a URI.
language	String	No	Detected language of the article.
confidence	Object	No	Confidence scores for extracted fields. Contains `body`, `title`, and `author` number fields.
source_url	String	No	Source URL of the extracted article content. Must be a valid URI.
word_count	Integer	No	Word count of the extracted article content.

Body

Name

Type

Description

bodyREQUIRED

object

—

Extract Article From Web API

What it does

QUICKSTART

Quickstart

What you'll get back

About this endpoint

What it does

Request Body

Response

Body

Errors any endpoint can return