I'm assuming you are referring to this work: Mihalcea, R., & Tarau, P. (2004). Textrank: Bringing order into texts. In Proceedings of EMNLP 2004. Barcelona, Spain.
A Java implementation of the key phrase extraction part (not sentence extraction) is here: https://github.com/ceteri/textrank
See also https://github.com/karchr/icetextsum, which adds sentence extraction to the implementation.
Unfortunately it is a little bit tricky to get DKPro Keyphrases working. However, once you have it running it provides you with a bunch of powerful computational linguistic algorithms along with DKPro Core and DKPro Similarity.
If you want to try it just send me a message and I can give you detailed installation instructions.
I want to ask a thing, how can I use textrank for a turkish text? I tried some exampla, but I didn't take good results by it. is there someone who can help me about this issue?