Commit 16314308 by yangchen

链接是否删除规则添加

parent 1ecccbba
......@@ -279,12 +279,15 @@ public class UrlLiveCrawler {
,"提示信息","跳转页","跳转中...","此帐号在冻结期,内容无法查看","东北新闻网"
,"百度一下,你就知道","帐号已迁移","手机百度","内容被删除","亚博国际|首页"
,"中国软件网","云广网","新浪首页","文章暂时找不到了","-法易网"
,"【一点资讯】www.yidianzixun.com","错误页面","网站暂停通知","【快资讯】你的专属资讯平台");
,"【一点资讯】www.yidianzixun.com","错误页面","网站暂停通知","【快资讯】你的专属资讯平台"
,"百度新闻——全球最大的中文新闻平台","以上文章由以下机构判定为不实信息","该公众号已迁移"
,"财经网-CAIJING.COM.CN","蚂蚁资讯","参数错误","时尚头条_YOKA时尚网","该文章已经被删除"
,"网易","链接已过期","找不到页面","今晚网","该文章已被删除");
List<String> cList = Arrays.asList("提示信息-","此内容因违规无法查看","微信公众号不存在"
,"此内容被投诉且经审核涉嫌侵权,无法查看","thepageyourequestedwasnotfound","未知错误"
,"Objectmoved","404","页面没有找到","页面未找到","301MovedPermanently","加载异常",
"此帐号已被屏蔽, 内容无法查看");
"此帐号已被屏蔽, 内容无法查看","链接不存在");
return cList.stream().anyMatch(title::contains) || eList.stream().anyMatch(title::equals);
}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment