Any Website URL to Article Summarizer
Pricing
from $4.99 / 1,000 results
Any Website URL to Article Summarizer
Extract and summarize articles from any website URL. Returns title, author, publish date, word count, reading time, full text, and a concise AI-style summary using extractive summarization.
Pricing
from $4.99 / 1,000 results
Rating
0.0
(0)
Developer
Coding Frontned
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
20 days ago
Last modified
Categories
Share
Extract article content and create deterministic extractive summaries from one to twenty public web pages. Each dataset row is a real article entity with its title, source URL and domain, optional author and publication metadata, summary, key points, word count, estimated reading time, and collection provenance.
The Actor uses bounded HTTP requests and Cheerio rather than a browser. It supports direct access or an Apify/custom proxy, fresh-session retries, up to five validated redirects, a 5 MB response ceiling, and configurable request timeouts. Input and every redirect are rejected if they use credentials, a non-HTTP protocol, or resolve to a private or reserved network address.
Input
urls: one to twenty public HTTP(S) article URLs.summaryLength:short(3 sentences),medium(5), orlong(8).includeFullText: include the extracted source text when true.maxItems: process at most 1–20 supplied URLs.timeoutMs: 5,000–120,000 milliseconds per request.requestDelayMs: 0–5,000 milliseconds before each attempt.maxRetries: zero to two retries per URL.proxyConfiguration: optional Apify or custom proxy settings.
Output
The dataset contains only validated article-summary rows. Request failures, blocks, and pages without enough article content are kept in the OUTPUT key-value-store record and never inserted as fake article rows. A run fails when it cannot publish any article; mixed results are reported as partial.
Summaries are source-extractive: sentences are selected from the fetched public article using term relevance, title relevance, source position, and repetition filtering. They are not generative AI claims and can only be as accurate as the public page text.
Notes
Sites may block automated traffic, require client-side rendering, or expose content that is not article-shaped. Use a suitable proxy where permitted. Dynamic sites and unusual markup may provide fewer optional fields.
