使用Microsoft Edge批量将HTML转PDF：提速方案及替代方法

你的现有VBA代码每次转换都会启动一个新的Edge进程，进程启动的开销是单个文件耗时7秒的主要原因，针对100个文件的批量处理，以下是具体优化方案和替代选项：

一、优化现有Edge命令行方案（复用进程） #

通过Edge的DevTools远程调试端口，复用单个Edge Headless实例处理所有文件，避免重复启动进程的开销，可将单个文件耗时压缩至1-2秒。

优化后VBA代码： #

Sub BatchConvertHTMLToPDF_EdgeReuse()
    Dim fso As Object, wshShell As Object
    Dim sPath As String, devToolsPort As Integer
    Dim httpReq As Object, jsonResponse As String, targetId As String
    Dim file As Object, sHTMLFile As String, sPDFFile As String
    
    Set fso = CreateObject("Scripting.FileSystemObject")
    Set wshShell = CreateObject("WScript.Shell")
    Set httpReq = CreateObject("MSXML2.XMLHTTP.6.0")
    
    sPath = ThisWorkbook.Path & Application.PathSeparator
    devToolsPort = 9222 ' 自定义DevTools调试端口
    
    ' 启动单个Edge Headless实例
    wshShell.Run "msedge --headless --disable-gpu --remote-debugging-port=" & devToolsPort, 0, False
    Application.Wait Now + TimeValue("00:00:02") ' 等待实例初始化
    
    ' 遍历所有HTML文件
    For Each file In fso.GetFolder(sPath).Files
        If LCase(fso.GetExtensionName(file.Name)) = "html" Then
            sHTMLFile = file.Path
            sPDFFile = sPath & fso.GetBaseName(file.Name) & ".pdf"
            
            ' 加载HTML文件并获取目标ID
            httpReq.Open "GET", "http://localhost:" & devToolsPort & "/json/new?" & sHTMLFile, False
            httpReq.Send
            jsonResponse = httpReq.ResponseText
            targetId = Mid(jsonResponse, InStr(jsonResponse, """id"":""") + 5, _
                InStr(InStr(jsonResponse, """id"":""") + 5, jsonResponse, """") - (InStr(jsonResponse, """id"":""") + 5))
            
            ' 发送PDF转换命令
            httpReq.Open "POST", "http://localhost:" & devToolsPort & "/json/target/" & targetId & "/send", False
            httpReq.SetRequestHeader "Content-Type", "application/json"
            httpReq.Send "{""id"":1,""method"":""Page.printToPDF"",""params"":{""path"":""" & Replace(sPDFFile, "\", "\\") & """}}"
            
            Application.Wait Now + TimeValue("00:00:01") ' 等待转换完成（根据文件大小调整）
        End If
    Next file
    
    ' 关闭Edge进程
    wshShell.Run "taskkill /f /im msedge.exe", 0, True
    MsgBox "批量转换完成！", vbInformation
    
CleanUp:
    Set httpReq = Nothing
    Set wshShell = Nothing
    Set fso = Nothing
End Sub

二、替代方案 #

1. 使用wkhtmltopdf（最快速度） #

wkhtmltopdf是专门的HTML转PDF轻量工具，无界面启动速度极快，单个文件转换耗时通常在1秒以内，总耗时可控制在100秒左右，需先下载安装wkhtmltopdf。

VBA代码示例： #

Sub BatchConvertHTMLToPDF_WK()
    Dim fso As Object, wshShell As Object
    Dim sPath As String, wkPath As String, sCommand As String
    Dim file As Object, sHTMLFile As String, sPDFFile As String
    
    Set fso = CreateObject("Scripting.FileSystemObject")
    Set wshShell = CreateObject("WScript.Shell")
    
    sPath = ThisWorkbook.Path & Application.PathSeparator
    wkPath = "C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe" ' 替换为你的安装路径
    
    If Not fso.FileExists(wkPath) Then
        MsgBox "未找到wkhtmltopdf，请检查路径！", vbExclamation
        GoTo CleanUp
    End If
    
    For Each file In fso.GetFolder(sPath).Files
        If LCase(fso.GetExtensionName(file.Name)) = "html" Then
            sHTMLFile = file.Path
            sPDFFile = sPath & fso.GetBaseName(file.Name) & ".pdf"
            
            sCommand = """" & wkPath & """ """ & sHTMLFile & """ """ & sPDFFile & """"
            wshShell.Run sCommand, 0, True
        End If
    Next file
    
    MsgBox "批量转换完成！", vbInformation
    
CleanUp:
    Set wshShell = Nothing
    Set fso = Nothing
End Sub

注意：wkhtmltopdf对复杂HTML（如CSS3高级特性、JS动态渲染内容）的兼容性略逊于Edge。

2. 使用Word自动化（无需额外工具） #

利用Office Word的HTML解析和PDF导出功能，兼容性好，无需额外安装工具，单个文件转换耗时约3-4秒，总耗时约300-400秒。

VBA代码示例： #

Sub BatchConvertHTMLToPDF_Word()
    Dim fso As Object, wordApp As Object
    Dim sPath As String, file As Object
    Dim sHTMLFile As String, sPDFFile As String, doc As Object
    
    Set fso = CreateObject("Scripting.FileSystemObject")
    Set wordApp = CreateObject("Word.Application")
    wordApp.Visible = False
    
    sPath = ThisWorkbook.Path & Application.PathSeparator
    
    For Each file In fso.GetFolder(sPath).Files
        If LCase(fso.GetExtensionName(file.Name)) = "html" Then
            sHTMLFile = file.Path
            sPDFFile = sPath & fso.GetBaseName(file.Name) & ".pdf"
            
            Set doc = wordApp.Documents.Open(sHTMLFile)
            doc.ExportAsFixedFormat OutputFileName:=sPDFFile, ExportFormat:=17 ' wdExportFormatPDF
            doc.Close SaveChanges:=False
        End If
    Next file
    
    wordApp.Quit
    MsgBox "批量转换完成！", vbInformation
    
CleanUp:
    Set wordApp = Nothing
    Set fso = Nothing
End Sub

方案选择建议 #

• 追求极致速度：选wkhtmltopdf
• 需完美兼容复杂HTML：选Edge复用进程方案
• 不想额外安装工具：选Word自动化方案

内容的提问来源于stack exchange，提问作者YasserKhalil