[文本处理] sed匹配html遇到的问题（基本解决了，谢谢各位）

sed -r "s#.*(\"http[[:alnum:]:?/.`~!@\#\$%^^^&-_=+(){},]*\").*#\1#" a.html
复制代码

Set fso = CreateObject("Scripting.FileSystemObject")
For Each f in fso.GetFolder(".").Files
    ext = LCase(fso.GetExtensionName(f))
    If ext = "htm" or ext = "html" or ext = "txt" Then
        txt = fso.OpenTextFile(f).ReadAll
        fso.OpenTextFile(f & ".txt", 2, true).Write GetUrl(txt)
    End If
Next
MsgBox "OK"

Function GetUrl(str)
    Set re = New RegExp
    re.Pattern = "http://[^""]+(?="")"
    re.Global = True
    re.IgnoreCase = True
    For Each m in re.Execute(str)
        If InStr(s, m & vbCrLf) = 0 Then s = s & m & vbCrLf
    Next
    GetUrl = s
End Function
复制代码

//&cls&(type *.txt|cscript -nologo -e:jscript "%~0") 2>nul>>"批量提取%~nx0.txt"&pause&exit
WSH.echo(WScript.StdIn.ReadAll().match(/http:\/\/[^\"]+(?=\")/g).join('\r\n'))
复制代码

sed -r "s#.*(\"http[[:alnum:]:/.?%%]*\").*#\1#" fea.txt
sed -r "s#.*(\"http[^^\"]*\").*#\1#" fea.txt
::for中：
for /f "delims=" %%h in ('sed -r "s#.*(\"http[[:alnum:]:/.?%%]*\").*#\1#" fea.txt')do (
	echo %%h
)
for /f "delims=" %%h in ('sed -r "s#.*(\"http[^^^^\"]*).*#\1#" fea.txt')do (
	echo %%h"
)
复制代码

sed -r "s#\"#\n#g^" fea.txt|sed -n "/^http/p"
sed -r "s#\"#\n#g^" fea.txt|sed "/^http/!d"
sed -r "s#\"#\n#g^" fea.txt|findstr /i "^https:// ^http://"
复制代码