golang使用正则表达式解析网页

2019-11-10 09:55:01王冬梅

src = re.ReplaceAllString(src, "<table")
re,_ = regexp.Compile("</table>[Ss]+?</html>")
src = re.ReplaceAllString(src, "</table>")
// 干掉行首的空格
 re,_ = regexp.Compile("(<tr>)([Ss<>"d]+?)(</tr>)")
 //src = re.ReplaceAllString(src, "$2")
 src = re.ReplaceAllString(src, "$2]")
 // 去掉<>标签
re,_ = regexp.Compile("<[Ss]+?>")
src = re.ReplaceAllString(src, "")
re,_ = regexp.Compile("n")
src = re.ReplaceAllString(src, "")
re,_ = regexp.Compile("[ ]+")
src = re.ReplaceAllString(src, " ")
re,_ = regexp.Compile("]")
 src = re.ReplaceAllString(src, "n")
// 变成 json                1           2                3           4
re,_ = regexp.Compile("(w*)(w{2}:w{2}:w{2}:w{2}:w{2}:w{2})([A-Za-z ]*)(d{4}-d{2}-d{2} d{2}:d{2}:d{2} )([Vd.]* )(d{4}-d{2}-d{2}( d{2}:d{2}(:d{2})?)?)")
/* (((d{4}-d{2}-d{2})+ (d{2}:d{2}:d{2})*?)")
*/
src = re.ReplaceAllString(src, "$1,$2,$3,$4,$5,$6,")
//re,_ = regexp.Compile("(<[Ss]*?">)([Ss]+?)(</t")
//src = re.ReplaceAllString(src, "$2,")
// re,_ = regexp.Compile("<[Ss]+?>")
// src = re.ReplaceAllString(src, "")
//reg := regexp.MustCompile("([A-Za-z]+?)(n[s]+)([d]+)")
// src =  reg.ReplaceAllString(src, "$1:$3")
//去除连续的换行符
//re, _ = regexp.Compile("s{2,}")
//src = re.ReplaceAllString(src, "n")
//re = regexp.MustCompile("nd+")
//fmt.Println(re.ReplaceAllLiteralString("hellon2nwork", 'd'))
src = strings.Replace(src,"虚拟机名称 虚拟机MAC 虚拟机状态 心跳时间 引擎版本 病毒库日期 扫描样本数" , "vm_name,vm_mac,vm_state,vm_heart,vm_eg,vm_av_db,vm_count",-1)
fmt.Println(src)
//reg, err := regexp.Compile("[[0-9A-Za-z]{2}:?]{6}")
//fmt.Printf("%q,%vn", reg.FindString("00:16:3e:4a:29:35"), err)
// "Hello",
// text := "Hellon123nGon123"
// reg = regexp.MustCompile("([A-Za-z]+?)(n)([d]+)")
// fmt.Printf("%qn", reg.ReplaceAllString(text, "$3:$1"))
//fmt.Println(strings.TrimSpace(src))
//去除STYLE
//re, _ = regexp.Compile("<style[Ss]+?</style>")
//src = re.ReplaceAllString(src, "")
//去除SCRIPT
//re, _ = regexp.Compile("<script[Ss]+?</script>")
//src = re.ReplaceAllString(src, "")
//去除所有尖括号内的HTML代码,并换成换行符
//re, _ = regexp.Compile("<[Ss]+?>")
//src = re.ReplaceAllString(src, "n")