Motivated by this background, in this paper, we propose an approach to mine causal relations between events with argument structures from the Web. And our work involves three subtasks: (1) the identification of causality expressions; (2) the extraction of cause and effect pairs (3) the measure of extracted relations. We firstly use explicit causal connective markers as linguistic cues to discover causality relations. Then, event-pairs with the predicate-argument structure are extracted based on local dependency parse trees. And finally, we propose a statistical score S to measure the causal association between potential related events, and prune relations with low S value. Experimental results demonstrate the effectiveness of our approach, which had a precision around 80%.