As a web search engine is able to find relevant sources for a keyword query, the web of data clearly needs a source selection engine able to find relevant endpoints for a SPARQL query. However, source selection requires to get informations about the content of endpoints and currently, it remains difficult to automatically explore the content of endpoints as web robots explore the content of web servers. Thanks to the web preemption principle, we propose to automatically build RDF summaries of endpoints through SPARQL queries. We propose SemCat, an approach to compute the source selection of a query Q by evaluating a rewriting of Q on summaries. As all queries terminate under the web preemption paradigm, SemCat is able to provide a web automated source selection service relying on preemptable SPARQL servers. We empirically demonstrate that various summaries can be extracted with a data transfer proportional to the size of the summary, and highlight the trade-off between the size of the summaries, the accuracy of source selection and the execution time of source selection.