We've released several new features, some of which will remain in beta whilst we fine tune them. These features are:
- download an online file using Gaffa (only available for PDFs for now).
The following are avaiable only to select accounts but message us if you'd like to try them!
- extract the innerHTML of a particular element.
- define a schema and then parse online data into JSON using a large language model, currently only works with online PDFs.
- parse a table to a JSON object.
- save a JSON object with the cookies for a given web page.
We've added a new tutorial which walks you through how to use Gaffa in a Python script to ask questions about the content of a web page.