1234567891011 |
- package spiderutil
- import "regexp"
- var Reg = regexp.MustCompile("[^0-9A-Za-z\u4e00-\u9fa5]+")
- var Filter = regexp.MustCompile("<[^>]*?>|[\\s\u3000\u2003\u00a0]")
- // FilterDetail 去除无效文本
- func FilterDetail(con string) string {
- return Reg.ReplaceAllString(Filter.ReplaceAllString(con, ""), "")
- }
|