This paper presents a stochastic graph based method for recommending or selecting a small subset of blogs that best represents a much larger set. within a certain topic. Each blog is assigned a score that reflects how representative it is. Blog scores are calculated recursively in terms of the scores of their neighbors in a lexical similarity graph. A random walk is performed on a graph where nodes represent blogs and edges link lexically similar blogs. Lexical similarity is measured using either the cosine similarity measure, or the Kullback-Leibler (KL) divergence. In addition, the presented method combines lexical centrality with information novelty to reduce redundancy in ranked blogs. Blogs similar to highly ranked blogs are discounted to make sure that diversity is maintained in the final rank. The presented method also allows us to include additional initial quality priors to assess the quality of the blogs, such as frequency of new posts per day and the text fluency measured by n-gram model probabilities, etc. We evaluate our approach using data from two large blog datasets. We measure the selection quality by the number of blogs covered in the network as calculated by an information diffusion model. We compare our method to other heuristic and greedy selection methods and show that it significantly outperforms them.