simhash算法计算两篇文章相似度(弄来玩玩)
MySimHash:import com.hankcs.hanlp.seg.common.Term;import com.hankcs.hanlp.tokenizer.StandardTokenizer;import org.apache.commons.lang3.StringUtils;import org.jsoup.Jsoup;import org.jsoup.safety.Whitelist;import java.math.BigInteger;import java.util.