Question

是否有一个可以将doc文件转换为pdf的好的库？有一些付费选项，例如cloudconvert，convertApi等，但我正在寻找免费选项。我的python应用程序托管在EC2计算机上。我还查看了python-docx库，该库可以允许我读取doc文件的内容，但是将内容写入pdf文件将破坏我认为的样式。

Answer 1

这是为您提供的VBA解决方案（我不知道如何使用Python做到这一点）。

如果您需要将多个Word文件转换为其他格式，例如TXT，RTF，HTML或PDF，请运行以下脚本。

Option Explicit On

Sub ChangeDocsToTxtOrRTFOrHTML()
    'with export to PDF in Word 2007
    Dim fs As Object
    Dim oFolder As Object
    Dim tFolder As Object
    Dim oFile As Object
    Dim strDocName As String
    Dim intPos As Integer
    Dim locFolder As String
    Dim fileType As String
    On Error Resume Next

    locFolder = InputBox("Enter the folder path to DOCs", "File Conversion", "C:\Users\your_path_here\")
    Select Case Application.Version
        Case Is < 12
            Do
                fileType = UCase(InputBox("Change DOC to TXT, RTF, HTML", "File Conversion", "TXT"))
            Loop Until (fileType = "TXT" Or fileType = "RTF" Or fileType = "HTML")
        Case Is >= 12
            Do
                fileType = UCase(InputBox("Change DOC to TXT, RTF, HTML or PDF(2007+ only)", "File Conversion", "TXT"))
            Loop Until (fileType = "TXT" Or fileType = "RTF" Or fileType = "HTML" Or fileType = "PDF")
    End Select

    Application.ScreenUpdating = False
    Set fs = CreateObject("Scripting.FileSystemObject")
    Set oFolder = fs.GetFolder(locFolder)
    Set tFolder = fs.CreateFolder(locFolder & "Converted")
    Set tFolder = fs.GetFolder(locFolder & "Converted")

    For Each oFile In oFolder.Files
        Dim d As Document
        Set d = Application.Documents.Open(oFile.Path)
        strDocName = ActiveDocument.Name
        intPos = InStrRev(strDocName, ".")
        strDocName = Left(strDocName, intPos - 1)
        ChangeFileOpenDirectory tFolder
        Select Case fileType
            Case Is = "TXT"
                strDocName = strDocName & ".txt"
                ActiveDocument.SaveAs FileName:=strDocName, FileFormat:=wdFormatText
        Case Is = "RTF"
                strDocName = strDocName & ".rtf"
                ActiveDocument.SaveAs FileName:=strDocName, FileFormat:=wdFormatRTF
        Case Is = "HTML"
                strDocName = strDocName & ".html"
                ActiveDocument.SaveAs FileName:=strDocName, FileFormat:=wdFormatFilteredHTML
        Case Is = "PDF"
                strDocName = strDocName & ".pdf"
                ActiveDocument.ExportAsFixedFormat OutputFileName:=strDocName, ExportFormat:=wdExportFormatPDF
        End Select
        d.Close
        ChangeFileOpenDirectory oFolder
    Next oFile
    Application.ScreenUpdating = True

End Sub

Answer 2

您可以使用 Aspose.Words Cloud SDK for Python。它支持 DOC/DOCX 到 PDF 的转换并保持格式/样式不变。其免费试用计划每月提供 150 次 API 调用。

P.S：我是 Aspose 的开发人员布道者。

# For complete examples and data files, please go to https://github.com/aspose-words-cloud/aspose-words-cloud-python
# Import module
import asposewordscloud
import asposewordscloud.models.requests
from shutil import copyfile

# Please get your Client ID and Secret from https://dashboard.aspose.cloud.
client_id='xxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxx'
client_secret='xxxxxxxxxxxxxxxxxxxxxxxxxxxxx'

words_api = asposewordscloud.WordsApi(client_id,client_secret)
words_api.api_client.configuration.host='https://api.aspose.cloud'

filename = 'C:/Temp/02_pages.docx'
dest_name = 'C:/Temp/02_pages.pdf'
#Convert DOCX to PDF
request = asposewordscloud.models.requests.ConvertDocumentRequest(document=open(filename, 'rb'), format='pdf')
result = words_api.convert_document(request)
copyfile(result, dest_name)
print("Result {}".format(result))

在Python中将doc / docx文件转换为pdf

2 个答案: