ArdentMan

@Echo Off&SetLocal EnableDelayedExpansion
(For /F "tokens=4-8 delims==<>: " %%a In ('Findstr /c:"<a href" *.htm') Do (
  If /i "%%~a%%d%%~e" EQU "httptarget_blank" Set "Str=%%a:%%b=%%c"&Echo !Str:~1,-1!
))>1.txt
Start 1.txt
复制代码

ArdentMan

vbs正则提取

Dim FSO, Path, vbStr, File, REGEX, OutStr
Path = CreateObject("Wscript.Shell").CurrentDirectory
Set FSO = CreateObject("Scripting.FileSystemObject")
For Each File In FSO.GetFolder(Path).Files
  If LCase(FSO.GetExtensionName(File)) = "htm" Then
    vbStr = vbStr & FSO.OpenTextFile(File).ReadAll() & vbCrLf
  End If
Next
Set REGEX = New RegExp
REGEX.Global = True
REGEX.IgnoreCase = True
REGEX.Pattern = ".*?<a href=\x22([^<>\s\x22]+)?\x22 target=\x22_blank\x22>.*?\r\n"
OutStr = REGEX.Replace(vbStr, "$1" & vbCrLf)
FSO.OpenTextFile("1.txt", 2, True).Write OutStr
Set FSO = Nothing
Set REGEX = Nothing
MsgBox "提取完成！", , "ArdentMan友情提醒"
复制代码

ArdentMan

8# wrrbb
本想简化下正则，谁知道出错，已修改回来，我的bat版试了没有？

ArdentMan

8# wrrbb
应该是因为你的htm文件名中有空格的原因

二楼代码已修改，也是为了简化代码是少写一个~字符

ArdentMan

请楼主在顶楼给出htm文本格式以调试代码啊