Web数据挖掘是当前数据挖掘的热点研究领域之一,由于Web页面数据的半结构化、不规则性和动态更新等特征,使得基于Web内容的数据挖掘研究具有一定的复杂性.本文首先简介如何从Web页面中提取半结构化数据,接着提出一种增量FP-Growth挖掘方法,使传统的FP-Growth方法适应于动态数据环境的关联规则挖掘,最后以中国汽车市场为例,挖掘消费者对不同类型、不同型号、小同价格轿车的购买偏好. Web data mining is one of the hot research areas of data mining at present, and the research on data mining based on Web content has certain complexity due to the characteristics of semi-structure, irregularity and dynamic update of Web page data. Semi-structured data is extracted from Web pages, and then an incremental FP-Growth mining method is proposed to adapt the traditional FP-Growth method to the association rules mining in dynamic data environment. Finally, taking Chinese auto market as an example, Different types, different models, small and small price cars purchase preferences.