Article Content Extractor — Clean Text for RAG & LLM
Pricing
from $8.00 / 1,000 useful article rows
Clean article text for RAG/LLM. Markdown/CSV. No login. Open Input → leave defaults → Start (~$0.008): https://console.apify.com/actors/yyg7LdbdGh1Tko3Ic/input From $8 / 1,000 useful rows.
Leave the prefilled Wikipedia URL and click Start for the first run (≈ $0.008). Do not clear — empty fails validation (required). Or paste 1–10 public article/news/blog URLs. Keep report/export OFF.
Content output format. Markdown is recommended for first-run proof and LLM ingestion.
Leave off for the first proof (~$0.008). Include the inline images array in the result; the heroImage field can still be returned separately when available.
Parallel article requests (1-10).
Request timeout per article in milliseconds.
Reject HTML responses larger than this limit before parsing.
Maximum public HTTP redirects followed per article.
Optional. Leave false for first proof (~$0.008 useful row). true charges one article-content-audit-report.
Optional. Leave false for first proof (~$0.008 useful row). true charges one article-batch-export.
Select dataset-only output or webhook handoff. Non-dry-run always writes canonical dataset rows first; webhook delivery runs only after dataset/PPE output succeeds.
URL to POST article payloads when delivery=webhook. The webhook is sent after canonical dataset rows and PPE output succeed, and is skipped on dryRun.
