分析了两种当前主流的网页结构化信息抽取技术方法:基于模版的分装器方法和不依赖模版的基于 视觉的网页信息抽取技术方法,并在此基础上实现了一种新的网页结构化信息抽取算法,一定程度上提高了抽取 效率和精度-Analysis of two pages of the current structure of the mainstream of information extraction techniques: template-based packaging methods and device

网页信息抽取最新研究成果，基于文本标签比的抽取算法，该方法简单易实现-Web information extraction latest research results, based on the text labels than the extraction algorithm, the method is simple and easy to implement