terse

处理一下特殊字符吧

@echo off
set/p w=<%~fs0 >nul
set "s=★★★★★"
setlocal enabledelayedexpansion
for /f "tokens=*" %%i in (1.txt) do (
    set "str=%%~i"
    if "!str:~,5!" == "!s!" (
       set "file=!str:*%s%=!.txt"
       set "filename="
       call :loop "!file!"
    ) else if defined filename (>>"!filename!" echo;!str!)
)
pause & exit

:loop
for /f tokens^=1*delims^=:\/*?^<^>^" %%a in ("%~1") do (
     set filename=!filename!%%a
     call :loop "%%b"
)
exit /b
复制代码

terse

powershell 直接从word文档导出txt 这里档名为 a.docx

<# : batch portion (begins PowerShell multi-line comment block)
@echo off & setlocal
powershell -noprofile -NoLogo "iex (${%~f0} | out-string)"
pause
exit 
#>
$word = New-Object -ComObject Word.Application
$file = (ls a.docx).FullName
$doc = $word.Documents.Open($file)
$text = $doc.Content.Text
$pattern =[regex] '(?i)(Module\d+\s+unit\d+)[\r\n]*(.+?)(?=Module\d+\s+unit\d+|$)'
$paragraphs = [regex]::matches($text,$pattern)
$doc.Close()
$word.Quit()
$paragraphs.ForEach({[IO.File]::WriteAllText( $_.Groups[1].Value+ '.txt',$_.Groups[2].Value,[Text.Encoding]::Default)})
复制代码