python - pandas html格式的excel文件
网页上下载的excel文件，用记事本打开显示如下：
用pandas.read_excel读取的话，提示
XLRDError: Unsupported format, or corrupt file: Expected BOF record; found b'<html x'假如用excel打开再另存为excel，读取当然可以，但是有很多excel文件这样处理就很繁琐，有没有什么方法么
VBS处理代码
Function GetPath()
Const WINDOW_HANDLE = 0
Const OPTIONS = 0
Set objShell = CreateObject("Shell.Application")
Set objFolder = objShell.BrowseForFolder(WINDOW_HANDLE, "Select a folder:", OPTIONS)
If objFolder Is Nothing Then
Wscript.Quit
End If
Set objFolderItem = objFolder.Self
GetPath = objFolderItem.Path
End Function
Function SaveToExcel(src_file,dest_file)
csv_format = 1 '6另存为csv,1另存为xls
Set objFSO = CreateObject("Scripting.FileSystemObject")
Dim oExcel
Set oExcel = CreateObject("Excel.Application")
oExcel.DisplayAlerts=false
Dim oBook
Set oBook = oExcel.Workbooks.Open(src_file)
oBook.Worksheets(1).Activate
oBook.SaveAs dest_file, csv_format
oBook.Close False
oExcel.Quit
End Function
Dim i : i=0
Set oFso = CreateObject("Scripting.FileSystemObject")
Set oFolder = oFso.GetFolder(GetPath())
Set oFiles = oFolder.Files
For Each oFile In oFiles
If Right(oFile.Path,3)="xls" or Right(oFile.Path,4)="xlsx" Then
SaveToExcel oFile.Path,oFile.Path
i=i+1
End If
Next
MsgBox "总共处理了"&i&"个EXCEL文件"
Wscript.Quit
