Read text content from docx file using batch script - batch-file

Question

I am able to read text from txt files in Windows batch script. But I can't find a way to read the data from docx files. How can I do it?

Answer 1

Put in same folder where are the File.docx that you want get txt:
docx2txt.cmd file.docx
or use:
Drag_and_Drop
result in a notepad txt opened with txt in file same name from .docx but in .txt
docx2txt.cmd updated
#echo off & setlocal enabledelayedexpansion
((
echo/"%~1"| findstr /lic:["\.docx\""$] >nul) && (
for /f "tokens=* delims= " %%i in ('echo/%~1') do (
set "_Docx2txt=%%~dpni.txt" && >nul copy /y "!_Docx2txt:~0,-4!.docx" "%temp%\Docx.zip")
if /i not exist "%temp%\Docx.zip" set "_Msg_Err=%~1 not valid^!" && goto :_error_:
set "_Docx_zDir_=%temp%\Docx_Zip"
set "_Docx_uZip_=%temp%\Docx.zip"
set "_replace_00=openxmlformats"
set "_replace_01=urn:schemas-microsoft-com:vml"
set "_replace_02=urn:schemas-microsoft-com:office:word"
set "_replace_03=urn:schemas-microsoft-com:office:office"
set _Run_CScript="%Windir%\System32\CScript.exe" //nologo
set _Break_line=!_Run_CScript! "%temp%\Break_line.vbs"
set _Replc_Qute=!_Run_CScript! "%temp%\Replc_Qute.vbs"
set _Replc_Dots=!_Run_CScript! "%temp%\Replc_Dots.vbs"
set _Replc_Tag1=!_Run_CScript! "%temp%\Replc_Tag1.vbs"
set _Replc_Tag2=!_Run_CScript! "%temp%\Replc_Tag2.vbs"
set _Find_Replc=!_Run_CScript! "%temp%\Find_Rep.vbs"
set _UnZip_Docx=!_Run_CScript! "%temp%\UnZip.vbs"
set _Drop_Lines=^
<nul & rem .:| This blank line is needed to do this job! So, do not remove it! |:.
) 2>nul || (
:_error_:
cls & echo/ & color F4 & set "_Arg_PS=New-Object -ComObject Wscript.Shell" & echo/
set "_Arg_Err=Valid: Some_Document.Docx" & set "_Err=E R R O R ^! Argument missing: "
if not defined _Msg_Err set _Msg_Err="%~0" [+ !_Arg_Err!]& echo/ Well, something is really wrong^^!
echo/ & powershell ^(!_Arg_PS!^).Popup^("""!_Msg_Err!""",0,"""!_Err!""",0x10^) 2>nul >nul
echo/ Use: !_Msg_Err! & timeout /t -1 2>nul >nul & color 0A & goto :eof
)) 2>nul
call :_write_vbs_files_: & type nul >"!_Docx2txt!"
(rmdir /q /s "!_Docx_zDir_!" & ping 127.1 -n 1 >nul && mkdir "!_Docx_zDir_!" || mkdir "!_Docx_zDir_!") 2>nul >nul
!_UnZip_Docx! && type nul >"!_Docx_zDir_!\Docx_Text.txt" & type nul >"!_Docx_zDir_!\Docx.tmp"
copy /y "!_Docx_zDir_!\word\document.xml" "!_Docx_zDir_!\Docx.tmp" >nul
for %%r in ("/^>^</","^<w:t xml:space^=","/^>","^</a:^","w:rPr^>","^<w:r","^</w:t^>","xmlns:","^<w:instrText", "^</w:instrText"^
) do !_Find_Replc! "!_Docx_zDir_!\Docx.tmp" %%r "!_Drop_Lines!"
for /l %%l in (0 1 3) do !_Find_Replc! "!_Docx_zDir_!\Docx.tmp" "!_replace_0%%l!" "!_Drop_Lines!"
!_Replc_Tag1! "!_Docx_zDir_!\Docx.tmp"
!_Replc_Tag2! "!_Docx_zDir_!\Docx.tmp"
!_Replc_Qute! "!_Docx_zDir_!\Docx.tmp"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" chr^(47^)^&"schemas"^&chr^(46^)^&"microsoft"^&chr^(46^)^&"com"^&chr^(47^)^&^chr^(47^) "!_Drop_Lines!"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" chr^(47^)^&"schemas"^&chr^(46^)^&"openxmlformats"^&chr^(46^) "!_Drop_Lines!"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" chr^(46^)^&"org"^&^chr^(47^)^&^chr^(47^) "!_Drop_Lines!"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" "^<w:t^>" "1#2##3#4#"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" "^<a:t^>" "1#2##3#4#"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" chr^(32^)^&"1#2##3#4#" "1#2##3#4#"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" "1#2##3#4#"^&char^(32^) "1#2##3#4#"
!_Find_Replc! "!_Docx_zDir_!\Docx.tmp" "^>^<" "!_Drop_Lines!"
!_Replc_Dots! "!_Docx_zDir_!\Docx.tmp"
for %%r in (org/officeDocument,org/officeDocument/,org/,relationships,wordprocessingDrawing,http://schemas.,^
presentationml,spreadsheetDrawing,speadsheetDrawing,wordprocessingml,drawingml,wordprocessingShape^
) do !_Find_Replc! "!_Docx_zDir_!\Docx.tmp" %%r "!_Drop_Lines!"
for %%r in (chr^(60^)^&chr^(63^),chr^(63^)^&chr^(62^),chr^(9^)) do !_Find_Replc! "!_Docx_zDir_!\Docx.tmp" %%r "!_Drop_Lines!"
type "!_Docx_zDir_!\Docx.tmp"|findstr "1#2##3#4#">>"!_Docx_zDir_!\Docx_Text.txt"
!_Find_Replc! "!_Docx_zDir_!\Docx_Text.txt" "1#2##3#4#" "!_Drop_Lines!"
!_Break_line! "!_Docx_zDir_!\Docx_Text.txt"
!_Find_Replc! "!_Docx_zDir_!\Docx_Text.txt" chr^(32^)^&chr^(46^) "!_Drop_Lines!"
!_Find_Replc! "!_Docx_zDir_!\Docx_Text.txt" chr^(32^)^&chr^(32^)^&chr^(46^) "!_Drop_Lines!"
type "!_Docx_zDir_!\Docx_Text.txt"| more /e /s /p +3 | findstr /rc:"[\ ]" | findstr /vb "\ \." >>"!_Docx2txt!"
!_Find_Replc! "!_Docx_zDir_!\Docx_Text.txt" "xml"^&chr^(58^) "!_Droplines!
!_Find_Replc! "!_Docx_zDir_!\Docx_Text.txt" "space"^&chr^(61^) "!_Drop_Lines!"
start /b notepad.exe "!_Docx2txt!" && rmdir /q /s "!_Docx_zDir_!" 2>nul >nul
>nul (for %%D in (Find_Rep Replc_Tag1 Replc_Tag2 Replc_Qute Replc_Dots Break_Line UnZip) do del /q /f "%temp%\%%D.vbs"
del /q /f "%temp%\docx.zip") & goto :_end_of_file_:
:_write_vbs_files_:
>"%temp%\Find_Rep.vbs"^
(
echo/ Const ForReading = 1
echo/ Const ForWriting = 2
echo/ strFileName = WScript.Arguments^(0^)
echo/ strOldText = WScript.Arguments^(1^)
echo/ strNewText = WScript.Arguments^(2^)
echo/ Set objFSO = CreateObject^("Scripting.FileSystemObject"^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForReading,ForReading^)
echo/ strText = objFile.ReadAll
echo/ strNewText = Replace^(strText, strOldText, strNewText^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForWriting^)
echo/ objFile.Write strNewText 'WriteLine adds extra CR/LF
echo/ objFile.Close
)
>"%temp%\Replc_Tag1.vbs"^
(
echo/ Const ForReading = 1
echo/ Const ForWriting = 2
echo/ strFileName = Wscript.Arguments^(0^)
echo/ strOldText = ^(chr^(60^)^&chr^(87^)^&chr^(58^)^&chr^(84^)^&chr^(62^)^)
echo/ strNewText = ^(vbCr^&vbLf^&chr^(34^)^&preserv^&chr^(34^)^&chr^(62^)^)
echo/ Set objFSO = CreateObject^("Scripting.FileSystemObject"^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForReading,ForReading^)
echo/ strText = objFile.ReadAll
echo/ objFile.Close
echo/ strNewText = Replace^(strText, strOldText, strNewText^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForWriting^)
echo/ objFile.Write strNewText 'WriteLine adds extra CR/LF
echo/ objFile.Close
)
>"%temp%\Replc_Tag2.vbs"^
(
echo/ Const ForReading = 1
echo/ Const ForWriting = 2
echo/ strFileName = Wscript.Arguments^(0^)
echo/ strOldText = ^(chr^(34^)^&"preserve"^&chr^(34^)^&chr^(62^)^)
echo/ strNewText = ^("1"^&chr^(35^)^&"2"^&chr^(35^)^&chr^(64^)^&"3"^&chr^(35^)^&"4"^&chr^(35^)^)
echo/ Set objFSO = CreateObject^("Scripting.FileSystemObject"^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForReading,ForReading^)
echo/ strText = objFile.ReadAll
echo/ objFile.Close
echo/ strNewText = Replace^(strText, strOldText, strNewText^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForWriting^)
echo/ objFile.Write strNewText 'WriteLine adds extra CR/LF
echo/ objFile.Close
)
>"%temp%\Replc_Qute.vbs"^
(
echo/ Const ForReading = 1
echo/ Const ForWriting = 2
echo/ strFileName = Wscript.Arguments^(0^)
echo/ strOldText = ^(chr^(34^)^&"preserve"^&chr^(34^)^&chr^(62^)^)
echo/ strNewText = ^("1"^&chr^(35^)^&"2"^&chr^(35^)^&chr^(64^)^&"3"^&chr^(35^)^&"4"^&chr^(35^)^)
echo/ Set objFSO = CreateObject^("Scripting.FileSystemObject"^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForReading,ForReading^)
echo/ strText = objFile.ReadAll
echo/ objFile.Close
echo/ strNewText = Replace^(strText, strOldText, strNewText^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForWriting^)
echo/ objFile.Write strNewText 'WriteLine adds extra CR/LF
echo/ objFile.Close
)
>"%temp%\Replc_Dots.vbs"^
(
echo/ Const ForReading = 1
echo/ Const ForWriting = 2
echo/ strFileName = Wscript.Arguments^(0^)
echo/ strOldText = ^(chr^(46^)^&^chr^(0^)^)
echo/ strNewText = ^(chr^(46^)^&chr^(13^)^&"1"^&chr^(35^)^&"2"^&chr^(35^)^&chr^(64^)^&"3"^&chr^(35^)^&"4"^&chr^(35^)^)
echo/ Set objFSO = CreateObject^("Scripting.FileSystemObject"^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForReading,ForReading^)
echo/ strText = objFile.ReadAll
echo/ objFile.Close
echo/ strNewText = Replace^(strText, strOldText, strNewText^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForWriting^)
echo/ objFile.Write strNewText 'WriteLine adds extra CR/LF
echo/ objFile.Close
)
>"%temp%\Break_Line.vbs"^
(
echo/ Const ForReading = 1
echo/ Const ForWriting = 2
echo/ strFileName = Wscript.Arguments^(0^)
echo/ strOldText = ^(chr^(46^)^)
echo/ strNewText = ^(chr^(46^)^&vbCr^&vbLf^)
echo/ Set objFSO = CreateObject^("Scripting.FileSystemObject"^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForReading,ForReading^)
echo/ strText = objFile.ReadAll
echo/ objFile.Close
echo/ strNewText = Replace^(strText, strOldText, strNewText^)
echo/ Set objFile = objFSO.OpenTextFile^(strFileName, ForWriting^)
echo/ objFile.Write strNewText 'WriteLine adds extra CR/LF
echo/ objFile.Close
)
>"%temp%\UnZip.vbs"^
(
echo/ ZipFile="!_Docx_uZip_!"
echo/ ExtractTo="!_Docx_zDir_!\"
echo/ set objShell = CreateObject^("Shell.Application"^)
echo/ set FilesInZip=objShell.NameSpace^(ZipFile^).items
echo/ Set fso = CreateObject^("Scripting.FileSystemObject"^)
echo/ objShell.NameSpace^(ExtractTo^).CopyHere^(FilesInZip^)
echo/ Set fso = Nothing
echo/ Set objShell = Nothing
)
exit /b
:_end_of_file_: