论文部分内容阅读
在总结主题爬行器的“真、假隧道”策略的基础上,提出一种解决“假隧道”问题的KBES算法。通过实验分析KBES算法能在一定程度上提高锚与链接文本在启发策略中预测新链接相关性的效率。
On the basis of summarizing the “true and false tunnel” strategy of the theme crawler, a KBES algorithm to solve the problem of “false tunnel” is proposed. By analyzing KBES algorithm experimentally, the efficiency of predicting the relevance of new links in heuristic strategies can be improved to a certain extent.