your title

Stanford Project CS229

Url Text classification

1. url features
   1.1 meta tag ??
   1.2 title
   1.3 url content: key word or substring of key words:->先转成拼音？,首字母（不好弄）？
   1.4 keywords 怎么获取,-> meta tag
   1.5 page content

2. Adult vocabulary
   2.1 Adult.txt and gray.txt,近义词怎么解决,需不需要？

3. get origin url data