feat:1、增加文档和文章的危险标签和属性过滤

2、移除文档的客户端缓存
This commit is contained in:
lifei6671
2018-09-13 18:19:26 +08:00
parent 91d010664b
commit 732b1db281
8 changed files with 282 additions and 256 deletions

View File

@@ -3,6 +3,9 @@ package utils
import (
"regexp"
"strings"
"github.com/PuerkitoBio/goquery"
"bytes"
"github.com/lifei6671/mindoc/conf"
)
func StripTags(s string) string {
@@ -54,3 +57,60 @@ func AutoSummary(body string,l int) string {
}
return content
}
//安全处理HTML文档过滤危险标签和属性.
func SafetyProcessor(html string) string {
//安全过滤,移除危险标签和属性
if docQuery, err := goquery.NewDocumentFromReader(bytes.NewBufferString(html)); err == nil {
docQuery.Find("script").Remove()
docQuery.Find("form").Remove()
docQuery.Find("link").Remove()
docQuery.Find("applet").Remove()
docQuery.Find("frame").Remove()
docQuery.Find("meta").Remove()
docQuery.Find("iframe").Remove()
docQuery.Find("*").Each(func(i int, selection *goquery.Selection) {
if href, ok := selection.Attr("href"); ok && strings.HasPrefix(href, "javascript:") {
selection.SetAttr("href", "#")
}
if src, ok := selection.Attr("src"); ok && strings.HasPrefix(src, "javascript:") {
selection.SetAttr("src", "#")
}
selection.RemoveAttr("onafterprint").
RemoveAttr("onbeforeprint").
RemoveAttr("onbeforeunload").
RemoveAttr("onload").
RemoveAttr("onclick").
RemoveAttr("onkeydown").
RemoveAttr("onkeypress").
RemoveAttr("onkeyup").
RemoveAttr("ondblclick").
RemoveAttr("onmousedown").
RemoveAttr("onmousemove").
RemoveAttr("onmouseout").
RemoveAttr("onmouseover").
RemoveAttr("onmouseup")
})
//处理外链
docQuery.Find("a").Each(func(i int, contentSelection *goquery.Selection) {
if src, ok := contentSelection.Attr("href"); ok {
if strings.HasPrefix(src, "http://") || strings.HasPrefix(src, "https://") {
if conf.BaseUrl != "" && !strings.HasPrefix(src, conf.BaseUrl) {
contentSelection.SetAttr("target", "_blank")
}
}
}
})
if html, err := docQuery.Html(); err == nil {
return strings.TrimSuffix(strings.TrimPrefix(strings.TrimSpace(html), "<html><head></head><body>"), "</body></html>")
}
}
return html
}