用golang的正则regexp：去除HTML，CSS，SCRIPT代码，仅保留页面文字
package main
import (
"fmt"
"io/ioutil"
"net/http"
"regexp"
"strings"
)
func main() {
resp, err := http.Get("http://www.baidu.com")
// resp, err := http.Get("http://www.163.com")
if err != nil {
fmt.Println("http get error.")
}
defer resp.Body.Close()
body, err := ioutil.ReadAll(resp.Body)
if err != nil {
fmt.Println("http read error")
}
src := string(body)
//将HTML标签全转换成小写
re, _ := regexp.Compile("\\<[\\S\\s]+?\\>")
src = re.ReplaceAllStringFunc(src, strings.ToLower)
//去除STYLE
re, _ = regexp.Compile("\\<style[\\S\\s]+?\\</style\\>")
src = re.ReplaceAllString(src, "")
//去除SCRIPT
re, _ = regexp.Compile("\\<script[\\S\\s]+?\\</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("\\<[\\S\\s]+?\\>")
src = re.ReplaceAllString(src, "\n")
//去除连续的换行符
re, _ = regexp.Compile("\\s{2,}")
src = re.ReplaceAllString(src, "\n")
fmt.Println(strings.TrimSpace(src))
}