I don't see an easy way to accomplish this without either pulling in the full text of every article over some period and running something like paragraph/doc/site vectors and then clustering by site vector.
That's putting a lot of faith into unsupervised learning, and it's probably just as likely to pick up on stylistic conventions like byline and date formats as it is to cluster by some common thematic pattern like political leaning.
No need to wait. Here's their statement: https://www.anera.org/press/anera-convoy-attacked-en-route-to-emirati-red-crescent-hospital-four-killed/