By default, Olostep supports returning content in various formats including:

  • HTML
  • Text
  • Raw PDF
  • Markdown

For some use cases you might not need the entire content but only specified, structured and clean data in JSON format.

To achieve this, you may use:

  • Parsers: Ideal for high-volume, consistent, recurring website scraping
  • LLM Extraction: Ideal for flexible extraction needs or websites with changing structures

Both methods provide clean, structured JSON data that can be immediately used in your applications without additional processing.

Suggest editsRaise issue
Get StartedUsing Parsers