Is this something you can do fast enough that the delays wouldn't be user-perceptible? Or maybe something that would be feasible to do in batch mode for a bunch of articles?
(In any case, it's amazing. Congratulations on making this.)
In any case, if the feature extraction is taking too much time, what is sometimes done is to dynamically select which features to extract for a test example based both on the expected predictive value (e.g. via mutual information or some other feature selection method) as well as the time it takes to actually compute the feature. This can be measured by, say, average computation time per feature on the training set. This can speed things up a fair bit if the feature extraction takes too long, since you only bother computing the features you really need, and are biased towards the ones that are quick to compute. This may not translate to your particular application, though, if I remember correctly, I've seen it used a while back for image spam classification.
My guess is that they need to render the page so they can determine the visual layout. So regardless of which visual features they use, the rendering step cannot necessarily be avoided.
For example, some of us might be interested in the CSS parsing and feature extraction, but in an alternate machine learning technique.
If you are going to assume tech savvy users, then you might as well expose low-level functionality and see if people like it.