[JAVA] Comment convertir des pages Web en PDF, PNG, JPG avec VBA (Excel) (Selenium Basic)

Comment convertir des pages Web en PDF, PNG, JPG avec VBA (Excel)

-Aperçu- Je l'ai fait parce que je l'ai souvent utilisé dans les affaires.

Selenium est un outil qui automatise facilement les opérations du navigateur. J'entends souvent comment utiliser Selenium avec Python ou JavaScript, mais en fait, il peut être exécuté avec Visual Basic.

Surtout au Japon, je pense que de nombreuses entreprises sont fortement dépendantes d'Excel, donc utiliser Excel comme interface graphique ne semble pas avoir de résistance psychologique. (Je pense que j'ai beaucoup à dire ...)

-procédure-

1. Téléchargez Selenium Basic depuis Selenium Release.
2. Installez le fichier ci-dessus.
3. Téléchargez le pilote du navigateur dont vous avez besoin. (Cette fois, j'utiliserai Chrome) Chrome Driver
4. Mettez à jour chromedriver.exe dans C: \ Users \ [nom d'utilisateur] \ AppData \ Local \ Selenium Basic avec chromedriver.exe téléchargé dans 3. (Juste écraser le fichier)
5. Écrivez vba

-Détails- 1.2. L'URL etc. peut changer. Veuillez vérifier chacun d'eux. Vous pouvez l'installer par défaut. 3. Là encore, l'URL peut changer. Veuillez vérifier chacun d'eux. Pour Chrome, veuillez télécharger la même version de Chrome que vous utilisez. 4. Remplacez simplement. 5.

Si vous passez à 4, la bibliothèque de types de sélénium apparaîtra dans Outils-> Paramètres de référence dans l'environnement de développement Excel, alors vérifiez-le. Si vous ne le faites pas, vous ne pourrez pas utiliser Selenium. Vérifiez également les paramètres de référence tels que Microsoft Scripting Runtime.

Voici un exemple. à ~ (enregistrer le répertoire de destination, enregistrer le nom du fichier, l'URL de la page Web, le numéro de ligne de la feuille (pour la confirmation ou l'écriture du répertoire de sauvegarde), la feuille à gérer si elle est enregistrée ou non)

Pour PDF

Option Explicit

Sub toPDF(ByVal directory, ByVal filename, ByVal url, ByVal i, ByVal sheetn As String)
  On Error GoTo myerror:
    Dim sheet1 As Worksheet
    Set sheet1 = Sheets(sheetn)
    Dim sPath As String, WSH As Variant
    Set WSH = CreateObject("WScript.Shell")
    sPath = WSH.SpecialFolders("Desktop") & "\"
    If (directory = "") Then directory = sPath
    If (Right(directory, 1) <> "\") Then directory = directory & "\"
    If (filename = "") Then filename = Format(Now(), "yyyy-mm-dd-hh-mm-ss")
    Dim savepath As String
    savepath = directory & filename & ".pdf"
    Dim driver As New Selenium.ChromeDriver
    driver.SetPreference "download.default_directory", directory
    driver.SetPreference "download.directory_upgrade", True
    driver.SetPreference "download.prompt_for_download", False
    driver.SetPreference "safebrowsing.enabled", True
    driver.SetPreference "plugins.plugins_disabled", Array("Chrome PDF Viewer")
    driver.AddArgument "headless"
    driver.AddArgument "disable-gpu"
    driver.AddArgument "hide-scrollbars"
    Dim w As Long
    Dim h As Long

    driver.Start
    driver.Get url

    w = driver.ExecuteScript("return document.body.scrollWidth")
    h = driver.ExecuteScript("return document.body.scrollHeight")
    
    Dim pdf As Object
    
    driver.Window.SetSize w, h
    
    Set pdf = CreateObject("Selenium.PdfFile")
    pdf.SetPageSize 210, 297, "mm"
    pdf.AddImage driver.TakeScreenshot, True
    pdf.SaveAs savepath
    sheet1.Cells(i, 5).Value = 1
    sheet1.Cells(i, 6).Value = savepath
    driver.Quit
    Exit Sub
myerror:
    MsgBox "no"
    sheet1.Cells(i, 5).Value = 0
End Sub
Sub dopdf()
  Dim sPath As String, WSH As Variant
    Set WSH = CreateObject("WScript.Shell")
    sPath = WSH.SpecialFolders("Desktop") & "\"
    Dim directory As String
    Dim filename As String
    directory = sPath
    If (Right(Len(directory), 1) <> "\") Then directory = directory & "\"
    
  Dim sheet1 As String
  Dim i As Long
  
  sheet1 = "Pour pdf"
  
  Dim sheetn As Worksheet
  Set sheetn = Sheets(sheet1)
  Dim r As Long
  r = sheetn.Cells(Rows.Count, 4).End(xlUp).Row
  For i = 2 To r
    If (sheetn.Cells(i, 4).Value = "") Then
      GoTo a1:
    End If
    filename = sheetn.Cells(i, 3).Text
    If (filename = "") Then filename = Format(Now(), "yyyy-mm-dd-hh-mm-ss")
    Dim result
    result = Dir(sheetn.Cells(i, 2).Text, vbDirectory)
    If (directory <> "" Or result <> True) Then sPath = sheetn.Cells(i, 2).Text
    Call toPDF(sPath, filename, sheetn.Cells(i, 4).Text, i, sheet1)
a1:
  Next i
End Sub

Pour JPG

Option Explicit

Sub toJPG(ByVal directory, ByVal filename, ByVal url, ByVal i, ByVal sheetn As String)
  On Error GoTo myerror:
    Dim sheet1 As Worksheet
    Set sheet1 = Sheets(sheetn)
    Dim sPath As String, WSH As Variant
    Set WSH = CreateObject("WScript.Shell")
    sPath = WSH.SpecialFolders("Desktop") & "\"
    If (directory = "") Then directory = sPath
    If (Right(directory, 1) <> "\") Then directory = directory & "\"
    If (filename = "") Then filename = Format(Now(), "yyyy-mm-dd-hh-mm-ss")
    Dim savepath As String
    savepath = directory & filename & ".jpg "
    Dim driver As New Selenium.ChromeDriver
    driver.SetPreference "download.default_directory", directory
    driver.SetPreference "download.directory_upgrade", True
    driver.SetPreference "download.prompt_for_download", False
    driver.SetPreference "safebrowsing.enabled", True
    driver.SetPreference "plugins.plugins_disabled", Array("Chrome PDF Viewer")
    driver.AddArgument "headless"
    driver.AddArgument "disable-gpu"
    driver.AddArgument "hide-scrollbars"
    Dim w As Long
    Dim h As Long
    
    driver.Start
    driver.Get url
    driver.FindElementByClass("tab02").Click
    driver.ExecuteScript ("this.document.getElementById('tab01').setAttribute('class','tabContent01');")
    driver.ExecuteScript ("this.document.getElementById('tab03').setAttribute('class','tabContent03');")
    w = driver.ExecuteScript("return document.body.scrollWidth")
    h = driver.ExecuteScript("return document.body.scrollHeight")
    driver.Window.SetSize w, h
    driver.TakeScreenshot.SaveAs savepath
    sheet1.Cells(i, 5).Value = 1
    sheet1.Cells(i, 6).Value = savepath
    driver.Quit
    Exit Sub
myerror:
    
    sheet1.Cells(i, 5).Value = 0
End Sub
Sub dojpg()
  Dim sPath As String, WSH As Variant
    Set WSH = CreateObject("WScript.Shell")
    sPath = WSH.SpecialFolders("Desktop") & "\"
    Dim directory As String
    Dim filename As String
    directory = sPath
    If (Right(Len(directory), 1) <> "\") Then directory = directory & "\"
    
  Dim sheet1 As String
  Dim i As Long
  
  sheet1 = "Pour jpg"
  
  Dim sheetn As Worksheet
  Set sheetn = Sheets(sheet1)
  Dim r As Long
  r = sheetn.Cells(Rows.Count, 4).End(xlUp).Row
  For i = 2 To r
    If (sheetn.Cells(i, 4).Value = "") Then
      GoTo a1:
    End If
    filename = sheetn.Cells(i, 3).Text
    If (filename = "") Then filename = Format(Now(), "yyyy-mm-dd-hh-mm-ss")
    Dim result
    result = Dir(sheetn.Cells(i, 2).Text, vbDirectory)
    If (directory <> "" Or result <> True) Then sPath = sheetn.Cells(i, 2).Text
    Call toJPG(sPath, filename, sheetn.Cells(i, 4).Text, i, sheet1)
a1:
  Next i
End Sub

Pour PNG

Option Explicit

Sub toPNG(ByVal directory, ByVal filename, ByVal url, ByVal i, ByVal sheetn As String)
  On Error GoTo myerror:
    Dim sheet1 As Worksheet
    Set sheet1 = Sheets(sheetn)
    Dim sPath As String, WSH As Variant
    Set WSH = CreateObject("WScript.Shell")
    sPath = WSH.SpecialFolders("Desktop") & "\"
    If (directory = "") Then directory = sPath
    If (Right(directory, 1) <> "\") Then directory = directory & "\"
    If (filename = "") Then filename = Format(Now(), "yyyy-mm-dd-hh-mm-ss")
    Dim savepath As String
    savepath = directory & filename & ".png "
    Dim driver As New Selenium.ChromeDriver
    driver.SetPreference "download.default_directory", directory
    driver.SetPreference "download.directory_upgrade", True
    driver.SetPreference "download.prompt_for_download", False
    driver.SetPreference "safebrowsing.enabled", True
    driver.SetPreference "plugins.plugins_disabled", Array("Chrome PDF Viewer")
    driver.AddArgument "headless"
    driver.AddArgument "disable-gpu"
    driver.AddArgument "hide-scrollbars"
    Dim w As Long
    Dim h As Long
    
    driver.Start
    driver.Get url
    driver.FindElementByClass("tab02").Click
    driver.ExecuteScript ("this.document.getElementById('tab01').setAttribute('class','tabContent01');")
    driver.ExecuteScript ("this.document.getElementById('tab03').setAttribute('class','tabContent03');")
    w = driver.ExecuteScript("return document.body.scrollWidth")
    h = driver.ExecuteScript("return document.body.scrollHeight")
    driver.Window.SetSize w, h
    driver.TakeScreenshot.SaveAs savepath
    sheet1.Cells(i, 5).Value = 1
    sheet1.Cells(i, 6).Value = savepath
    driver.Quit
    Exit Sub
myerror:
    
    sheet1.Cells(i, 5).Value = 0
End Sub
Sub dopng()
  Dim sPath As String, WSH As Variant
    Set WSH = CreateObject("WScript.Shell")
    sPath = WSH.SpecialFolders("Desktop") & "\"
    Dim directory As String
    Dim filename As String
    directory = sPath
    If (Right(Len(directory), 1) <> "\") Then directory = directory & "\"
    
  Dim sheet1 As String
  Dim i As Long
  
  sheet1 = "Pour png"
  
  Dim sheetn As Worksheet
  Set sheetn = Sheets(sheet1)
  Dim r As Long
  r = sheetn.Cells(Rows.Count, 4).End(xlUp).Row
  For i = 2 To r
    If (sheetn.Cells(i, 4).Value = "") Then
      GoTo a1:
    End If
    filename = sheetn.Cells(i, 3).Text
    If (filename = "") Then filename = Format(Now(), "yyyy-mm-dd-hh-mm-ss")
    Dim result
    result = Dir(sheetn.Cells(i, 2).Text, vbDirectory)
    If (directory <> "" Or result <> True) Then sPath = sheetn.Cells(i, 2).Text
    Call toPNG(sPath, filename, sheetn.Cells(i, 4).Text, i, sheet1)
a1:
  Next i
End Sub

La structure du livre se compose de trois feuilles «pdf», «png» et «jpg».

Colonnes B, C, D après la deuxième ligne Entrez la destination d'enregistrement, le nom d'enregistrement et l'URL Il est enregistré lorsque vous déplacez la macro.

Au fait, vous pouvez également manipuler le DOM avec driver.executescirpts etc., afin de pouvoir capturer la page Web après avoir joué avec.

somnolent. .. .. Aussi, je joindrai une photo plus tard.