This API allows you to fetch the content, title and images from an article on the web.
Using advanced Machine Learning techniques we are able to determine which parts of the page are ads, menus and other boilerplate data.
Our service will strip the non relevant content and respond with a clean, structured version of that article webpage.
Please note that we offer two endpoints. One for article and one for pages.
The first endpoint is using a classifier trained solely on articles where the second endpoint is able to deal with other types of pages
but will probably perform worse on articles.
The API is not limited to specific languages.