从源代码中提取或过滤网页标签

网页标签的提取与过滤技巧

最新推荐文章于 2024-10-04 20:12:28 发布

jiutao_tang

最新推荐文章于 2024-10-04 20:12:28 发布

阅读量2.1k

点赞数

CC 4.0 BY-SA版权

分类专栏： # 网站建设文章标签： string html function 正则表达式 integer object

本文链接：https://blog.youkuaiyun.com/jiutao_tang/article/details/6226684

网站建设专栏收录该内容

18 篇文章

订阅专栏

本文介绍了如何使用正则表达式和字符串操作在源代码中过滤和提取网页标签，特别是针对图片、脚本、嵌入多媒体和对象标签的处理。通过替换、删除或修改特定标签，实现了对HTML内容的定制化处理。

1.删除非图片标签

先把img标签转换成特定字符，再其他的html中 <和> 过滤掉，再把刚才的特定字符转换回来

html = html.replace(// <img/g, "♂ "); ///替换 " <img "
html = html.replace(/(♂[^> ]*)> /g, "$1♀ "); ///替换 "> "
alert(html);
html = html.replace(// <[^> ]*> /g, " "); ///过滤其它所有 " <...> "标签
alert(html);
html = html.replace(/♂/g, " <img "); ///还原 " <img "
html = html.replace(/♀/g, "> "); ///还原 "> "

2.正则表达式过滤图片标签自己所写

Function RemoveImg(ByVal str As String) As String
    Dim re
    Set re = New RegExp
    re.IgnoreCase = True
    re.Global = True
    re.Pattern = "<img[^>]*>"
    RemoveImg = re.Replace(str, " ")
End Function

Function RemoveScript(ByVal str As String) As String '过滤脚本
    Dim re
    Set re = New RegExp
    re.IgnoreCase = True
    re.Global = True
    re.Pattern = "<script[/w/W]*script>"
    RemoveScript = re.Replace(str, " ")
End Function

Function RemoveEmbed(ByVal str As String) As String '过滤嵌入多媒体
    Dim re
    Set re = New RegExp
    re.IgnoreCase = True
    re.Global = True
    re.Pattern = "<embed[/w/W]*embed>"
    RemoveEmbed = re.Replace(str, " ")
End Function

Function RemoveObject(ByVal str As String) As String '过滤嵌入多媒体
    Dim re
    Set re = New RegExp
    re.IgnoreCase = True
    re.Global = True
    re.Pattern = "<object[/w/W]*object>"
    RemoveEmbed = re.Replace(str, " ")
End Function

3.字符串遍历过滤图片标签

Private Function RemoveImg(ByVal str As String) As String
    '不显示图片
    Dim i As Integer
    Dim tempSource, tempStr As String
    Dim img() As String
    tempSource = str
    img = Split(str, "<img")
    For i = 1 To UBound(img) - 1
        tempStr = Split(img(i), ">")(0) '<img> 标签的结束
        tempSource = Replace(tempSource, "<img" & tempStr & ">", "", 1, -1, 1)
    Next
    RemoveImg = tempSource
End Function

4.操作页面元素

for(i=0;i<document.getElementsByTagName.length;i++){
document.getElementsByTagName("input")[i].style.background="#CCCCCC";

}