Extracting main content from HTML: where our approach differs from Trafilatura and Readability
Where our extractor diverges from Trafilatura and Readability, and the evaluation harness that tells us whether a change is an improvement.
Blog
Le blog Danubia
Actualités produit, notes techniques et nouvelles de l'équipe Danubia.
Turning HTML into clean markdown for RAG and LLM pipelines
Why extraction quality sets the ceiling for a RAG pipeline: one real page shown three ways, what a clean extractor has to get right, and what it costs to build one yourself.
The API that turns web pages into data, a founder letter
This week I am launching the free public beta of Danubia, a content extraction API. Let me tell you more!