AI & DATA
Clean article content
ready for LLMs
Strip navigation, ads, footers, and scripts. Extract clean title, body, author, and date from accessible article pages. Check the returned text and metadata before use. Powered by Mozilla’s Readability, used by Firefox Reader View.
This is my Apify Actor. I earn from its usage and may receive a referral commission when you use the Apify links on this page. Check the current price before running it.
Readability
Article extraction approach
Inspect
Check output completeness
Usage-based
Check current Actor pricing
JSON
LLM-Ready Output
USE CASES
What you can do with this data
RAG Pipeline Ingestion
Prepare article text for a RAG pipeline. Check that the extracted body preserves the passages your retrieval task needs before indexing it.
Content Summarization at Scale
Extract text from a permitted URL batch before summarization. Measure token use on the actual output; the reduction depends on the source pages.
News Monitoring
Extract clean text from news URLs for brand monitoring, competitive intelligence, sentiment analysis.
Dataset Building for ML
Build training datasets from web articles. Clean text + metadata (author, date, site) for fine-tuning or classification.
Newsletter Curation
Pull clean body text from shared links. Auto-summarize, auto-tag, auto-publish to your newsletter.
Research Assistant Apps
Build apps that read articles for users. Integrate with Claude, GPT, Gemini to extract then answer questions about content.
OUTPUT FIELDS
Fields returned per article
Cleaned title
Clean body text (no ads/nav)
Byline / author
Published date
Main image URL
Language detected
Word count
Excerpt (first 200 chars)
Site name
Canonical URL
All inline images
Reading time estimate
HOW IT WORKS
Three steps to structured data
Pass URL(s)
Pass a permitted URL or bounded URL list supported by the current Actor input. Start with a representative sample.
Extraction runs
Fetches page, applies Mozilla Readability, strips nav/ads/scripts, returns structured text.
Use in your stack
JSON output is ready for OpenAI embeddings, Claude, Gemini, or any vector DB (Pinecone, Weaviate, Qdrant).
COMPARISON
Why this actor vs alternatives
| Feature | This Actor | Firecrawl | Diffbot |
|---|---|---|---|
| Price to compare | Current Actor price plus applicable Apify usage | Current plan credits and options | Current extraction plan and usage |
| Extraction fit | Inspect Readability output | Inspect output on the same URLs | Inspect output on the same URLs |
| Output fit | Inspect content and metadata | Check required output formats | Check required output formats |
| Metadata completeness | Check author and date per page | Check author and date per page | Check author and date per page |
| JavaScript-heavy sites | Test required page behavior | Check current rendering settings | Check current rendering settings |
| Trial budget | Check current Apify account credits | Check current trial credit conditions | Check current trial conditions |
FAQ
Frequently asked questions
What is Mozilla Readability?
An open-source article-extraction library used by Firefox Reader View. Extraction quality depends on the page structure; verify the body and metadata on your own representative URLs.
Does it handle paywalled articles?
It extracts whatever the page returns. For soft paywalls (teaser visible), you get the teaser. For hard paywalls, you get the login prompt.
What about JS-heavy sites?
Check the current Actor input and run a representative JavaScript-dependent page. Rendering and retries can change both elapsed time and billed usage; no fixed surcharge is established here.
Why use this vs Firecrawl?
Use a representative URL sample to compare required fields, extraction completeness, retries, and total cost per usable article. This page does not establish a universal price advantage over Firecrawl.
Can I batch 10,000 URLs?
Start with a small permitted batch, inspect output completeness and usage, then increase the run limit within the current Actor and platform settings. This page does not establish throughput for a 10,000-URL job.
START NOW
Clean article text, ready for your LLM
Feed the article text your workflow needs into an LLM. Test output completeness and billed usage on a representative sample.
Open Extractor on Apify→