该博客介绍了如何将搜狗2008版新闻分类语料库和全网新闻分类语料库整理并转存至MySQL数据库。通过分析URL前缀，确定新闻类别如汽车、财经、IT、健康等，并提供了相应的Java代码示例。
packagezju.dawn.ai.corpus.sogou;publicfinalclassCategoryDetector {privatestaticString category=null;publicstaticString detectCategory(String url) {//xinhuanet.if(url.startsWith("http://www.xinhuanet.com/auto/")) {
category="car";
}elseif(url.startsWith("http://www.xinhuanet.com/fortune")) {
category="finance";
}elseif(url.startsWith("http://www.xinhuanet.com/internet/")) {
category="IT";
}elseif(url.startsWith("http://www.xinhuanet.com/health/")) {
category="health";
}elseif(url.startsWith("http://www.xinhuanet.com/sports")) {
category="sports";
}elseif(url.startsWith("http://www.xinhuanet.com/travel")) {
category="travel";
}elseif(url.startsWith("http://www.xinhuanet.com/edu")) {
category="education";
}elseif(url.startsWith("http://www.xinhuanet.com/employment")) {
category="employment";
}elseif(url.startsWith("http://www.xinhuanet.com/life")) {
category="culture";
}elseif(url.startsWith("http://www.xinhuanet.com/mil")) {
category="military";
}elseif(url.startsWith("http://www.xinhuanet.com/olympics/")) {
category="olympics";
}elseif(url.startsWith("http://www.xinhuanet.com/society")||url.startsWith("http://www.xinhuanet.com/local/")||url.startsWith("http://www.xinhuanet.com/world")) {
category="society";
}elseif(url.startsWith("http://www.xinhuanet.com/house")) {
category="house";
}elseif(url.startsWith("http://www.xinhuanet.com/ent")) {
category="ent";
}elseif(url.startsWith("http://www.xinhuanet.com/lady")) {
category="lady";
}elseif(url.startsWith("http://www.xinhuanet.com/school")) {
category="school";
}//chinaif(url.startsWith("http://auto.china.com/")) {
category="car";
}elseif(url.startsWith("http://caifu.china.com/")) {
category="finance";
}elseif(url.startsWith("http://tech.china.com/zh_cn/news/net/")) {
category="IT";
}elseif(url.startsWith("http://health.china.com/")) {
category="health";
}elseif(url.startsWith("http://sports.china.com/")) {
category="sports";
}elseif(url.startsWith("http://goo66.china.com/")) {
category="travel";
}elseif(url.startsWith("http://edu.533.com/")) {
category="education";
}elseif(url.startsWith("http://culture.china.com/")) {
category="culture";
}elseif(url.startsWith("http://military.china.com/")) {
category="military";
}elseif(url.startsWith("http://2008.china.com/")) {
category="olympics";
}elseif(url.startsWith("http://news.china.com/zh_cn/social/")||url.startsWith("http://news.china.com/zh_cn/domestic/")||url.startsWith("http://news.china.com/zh_cn/international/")) {
category="society";
}elseif(url.startsWith("http://china.soufun.com/")) {
category="house";
}elseif(url.startsWith("http://fun.china.com/zh_cn/star/")) {
category="ent";
}elseif(url.startsWith("http://meirong.533.com/")) {
category="lady";
}elseif(url.startsWith("http://edu.533.com/news/xiaoyuan/")) {
category="school";
}//sina.com.cnif(url.startsWith("http://auto.sina.com.cn/")) {
category="car";
}elseif(url.startsWith("http://finance.sina.com.cn/")) {
category="finance";
}elseif(url.startsWith("http://tech.sina.com.cn/it/")) {
category="IT";
}elseif(url.startsWith("http://sina.kangq.com/")) {
category="health";
}elseif(url.startsWith("http://sports.sina.com.cn/")) {
category="sports";
}elseif(url.startsWith("http://tour.sina.com.cn/")) {
category="travel";
}elseif(url.startsWith("http://edu.sina.com.cn/j/")) {//employment和education不能互换.category="employment";
}elseif(url.startsWith("http://edu.sina.com.cn/")) {
category="education";
}elseif(url.startsWith("http://cul.book.sina.com.cn/")) {
category="culture";
}elseif(url.startsWith("http://mil.news.sina.com.cn/")) {
category="military";
}elseif(url.startsWith("http://2008.sina.com.cn/")) {
category="olympics";
}elseif(url.startsWith("http://news.sina.com.cn/society/")||url.startsWith("http://news.sina.com.cn/china/")||url.startsWith("http://news.sina.com.cn/world/")) {
category="society";
}elseif(url.startsWith("http://house.sina.com.cn/")) {
category="house";
}elseif(url.startsWith("http://ent.sina.com.cn/")) {
category="ent";
}elseif(url.startsWith("http://eladies.sina.com.cn/")) {
category="lady";
}elseif(url.startsWith("http://edu.sina.com.cn/y/")) {
category="school";
}//163.comif(url.startsWith("http://auto.163.com/")) {
category="car";
}elseif(url.startsWith("http://money.163.com/")) {
category="finance";
}elseif(url.startsWith("http://tech.163.com/it/")) {
category="IT";
}elseif(url.startsWith("http://163.39.net/")) {
category="health";
}elseif(url.startsWith("http://sports.163.com/")) {
category="sports";
}elseif(url.startsWith("http://war.163.com/")) {
category="military";
}elseif(url.startsWith("http://2008.163.com/")) {
category="olympics";
}elseif(url.startsWith("http://news.163.com/shehui/")||url.startsWith("http://news.163.com/domestic/")||url.startsWith("http://news.163.com/world/")) {
category="society";
}elseif(url.startsWith("http://house.163.com/")) {
category="house";
}elseif(url.startsWith("http://ent.163.com/")) {
category="ent";
}elseif(url.startsWith("http://lady.163.com/")) {
category="lady";
}//qq.comif(url.startsWith("http://auto.qq.com/")) {
category="car";
}elseif(url.startsWith("http://finance.qq.com/")) {
category="finance";
}elseif(url.startsWith("http://tech.qq.com/a/")) {
category="IT";
}elseif(url.startsWith("http://sports.qq.com/")) {
category="sports";
}elseif(url.startsWith("http://edu.qq.com/job/")) {//employment和education不能互换.category="employment";
}elseif(url.startsWith("http://edu.qq.com/")) {
category="education";
}elseif(url.startsWith("http://cul.qq.com/")) {
category="culture";
}elseif(url.startsWith("http://mil.qq.com/")) {
category="military";
}elseif(url.startsWith("http://news.qq.com/a/")) {
category="society";
}elseif(url.startsWith("http://2008.qq.com/")) {
category="olympics";
}elseif(url.startsWith("http://house.qq.com/")) {
category="house";
}elseif(url.startsWith("http://ent.qq.com/")) {
category="ent";
}elseif(url.startsWith("http://lady.qq.com/")) {
category="lady";
}elseif(url.startsWith("http://campus.qq.com/")) {
category="school";
}//sohu.comif(url.startsWith("http://auto.sohu.com/")) {
category="car";
}elseif(url.startsWith("http://business.sohu.com/")) {
category="finance";
}elseif(url.startsWith("http://it.sohu.com/")) {
category="IT";
}elseif(url.startsWith("http://health.sohu.com/")) {
category="health";
}elseif(url.startsWith("http://sports.sohu.com/")) {
category="sports";
}elseif(url.startsWith("http://travel.sohu.com/")) {
category="travel";
}elseif(url.startsWith("http://learning.sohu.com/")) {
category="education";
}elseif(url.startsWith("http://career.sohu.com/")) {
category="employment";
}elseif(url.startsWith("http://cul.sohu.com/")) {
category="culture";
}elseif(url.startsWith("http://news.sohu.com/")) {
category="society";
}elseif(url.startsWith("http://mil.news.sohu.com/")) {
category="military";
}elseif(url.startsWith("http://2008.sohu.com/")) {
category="olympics";
}elseif(url.startsWith("http://house.sohu.com/")) {
category="house";
}elseif(url.startsWith("http://yule.sohu.com/")) {
category="ent";
}elseif(url.startsWith("http://women.sohu.com/")) {
category="lady";
}returncategory;
}publicstaticvoidmain(String args[]) {
category=CategoryDetector.detectCategory("http://edu.sina.com.cn/");
System.out.println(category);
}
}
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
