Pricing

from $50.00 / 1,000 results

Try for free

Go to Apify Store

Universal AI Article Extractor for News & Research Websites

Try for free

Extract and structure articles from any news or research site using AI for clean text, metadata, and autogenerated summaries to feed AI models or content platforms.

Pricing

from $50.00 / 1,000 results

Rating

0.0

(0)

Developer

Taku Anan

Actor stats

Bookmarked

Total users

Monthly active users

a day ago

Last modified

How It Works

Takes array of URLs.
Fetches pages with HTTP timeout.
Parses HTML to extract clean article text and metadata (title, author, publish date, images).
Produces a short heuristic summary from the extracted content.
Pushes structured JSON dataset items conforming to schema.

Input

{
  "urls": ["https://www.nytimes.com/2024/06/10/technology/ai-chatgpt-openai.html"]
}

Output

Structured JSON with url, title, author, datePublished, images, content, and summary.

Installation

Build and run with Docker or use pip install -r requirements.txt.

Usage

$apify run

Pricing

Suggested price: $90 USD

For

Media monitoring firms, AI content enrichers, research aggregators requiring daily ingestion of AI-ready article content.

This Actor uses only open web endpoints and respects robots and access controls.

Article Scraper & News Scraper API

tugelbay/article-extractor

Article scraper API for clean text and metadata from URLs as Markdown, text, or HTML for RAG, AI agents, monitoring, and research. Guide: https://konabayev.com/tools/article-extractor/?utm_source=apify_info&utm_medium=referral&utm_campaign=article-extractor

Tugelbay Konabayev

Article Extractor & News Scraper

web.harvester/article-extractor-news-scraper

Extract articles from any news site, blog, or webpage. Get title, full text, author, date, images & metadata using 7 extraction engines (Newspaper4k, Trafilatura, Goose3). Anti-bot bypass, proxy rotation, automatic fallback. Perfect for news monitoring, NLP datasets & content aggregation.

Web Harvester

5.0

(2)

Any Website Listing Page Scraper

mrscrapercom/mrscraper-listing

Unblock pages and scrape listing page from any websites. It is stealth, reliable, and scalable. Every action uses the mrscraper.com engine to extract structured listing data.

MrScraper

Schema.Org Json Ld Extractor

sync-network/schema-org-json-ld-extractor

Extract Schema.org JSON-LD structured data from any website. Fast, lightweight HTTP-based scraper that pulls all JSON-LD scripts - perfect for SEO analysis, product data extraction, and AI/RAG pipelines. No browser overhead.

Alam

Website Content Crawler Pro

datascoutapi/website-content-crawler-pro

Crawl websites and extract clean, structured content in Markdown, JSON, or plain text for AI models, LLMs, vector DBs, or RAG pipelines. Fast, reliable, and stealthy, with bulk processing, advanced metadata extraction, and seamless integration with LangChain, LlamaIndex, and AI workflows.

halam

567

3.7

(3)

Scrape GPT - Universal AI Web Scraper Agent

paradox-analytics/scrape-gpt---universal-ai-web-scraper-agent

AI-powered universal web scraper that works on ANY website without configuration. Extract data from e-commerce, news sites, social media, and more using intelligent LLM-based field mapping. Features JSON-first extraction, automatic pagination, anti-bot bypass, and cost-effective caching.

Paradox Analytics

Universal Markdown Scraper for LLMs

botflowtech/universal-markdown-scraper-for-llms

Universal Markdown Scraper for LLMs

BotFlowTech

🧪High-Volume Website Content & Media Scraper

caring_dizi/blog-content-scraper-fixed

🧪Crawling Done Right! Let me now what you think, what or where or how i can improve my actor, and i am all for constructive criticism. So please message if you have any questions. Enjoy and have a good day.

Jeff Halverson

150

5.0

(2)

Universal RSS Feeds Scraper

parseforge/universal-rss-feeds-scraper

Scrapes RSS feed links from any webpage. Enter a URL and get every RSS, Atom, or JSON feed link on that page, with title and URL. Export to CSV, JSON, Excel, or XML.