Simon Willison has released a new utility that converts rich text containing embedded HTML tables into plain formats like HTML, Markdown, CSV, TSV, or JSON. The tool accepts data pasted directly from browser windows and immediately outputs the structured content in the selected file type. Users can test the function by copying a table from a Wikipedia page and pasting it into the interface to see the result.
This development addresses a common friction point for researchers and analysts who need to move data from web pages into spreadsheet software without manual transcription. The update also expands Willison’s existing rich text converter to handle tables, improving the overall workflow for text processing. A separate feature now allows the system to search Wikipedia and automatically import any tables found on a specific page using an open CORS API.
* Supports conversion to HTML, Markdown, CSV, TSV, and JSON
* Integrates with Wikipedia via an automated search function
* Relies on Codex to fetch and display the imported data
