AI Article Extractor
Pricing
from $1.50 / 1,000 results
Go to Apify Store
AI Article Extractor
Turn article URLs, sitemaps and RSS/Atom feeds into clean Markdown/text/HTML with metadata and optional RAG chunks. Browser-free HTTP extraction.
AI Article Extractor
Pricing
from $1.50 / 1,000 results
Turn article URLs, sitemaps and RSS/Atom feeds into clean Markdown/text/HTML with metadata and optional RAG chunks. Browser-free HTTP extraction.
url
Optional
Requested article URL.
canonicalUrl
Optional
Canonical URL declared by the page (rel=canonical or og:url), otherwise the requested URL.
title
Optional
Article title.
publishedAt
Optional
Publish date, normalized to ISO 8601 when parseable.
siteName
Optional
Site name from og:site_name, JSON-LD publisher, or hostname.
language
Optional
BCP 47 language tag, e.g. en or en-US.
wordCount
Optional
Word count of the extracted plain text.
markdown
Optional
Clean Markdown body with links preserved (outputFormat=markdown, the default).
text
Optional
Plain-text body (outputFormat=text).
html
Optional
Cleaned article HTML with absolute links (outputFormat=html).
outputFormat
Optional
Body serialization used for this item.
chunks
Optional
RAG chunks, present only when chunkSize is set.
extractionStatus
Optional
ok = Readability extracted the main content; fallback = heuristic content block; failed = no article body.
extractionError
Optional
Reason for a failed or partial extraction.
fetchedAt
Optional
ISO 8601 timestamp of item creation.
