Python+VBA删除Excel重复行的两种实用方法详解

pip install Spire.Xls.Free

from spire.xls import *

# 创建Workbook实例
workbook = Workbook()
workbook.LoadFromFile("duplicates.xlsx")
sheet = workbook.Worksheets[0]

# 配置关键参数
key_column = 1  # A列（Spire.XLS中列号从1开始）
last_row = sheet.LastRow
# 定义要处理的范围
data_range = sheet.Range[f"A1:A{last_row}"]

# 用于跟踪已出现的值（去重核心）
seen_values = set()
rows_to_remove = []

# 获取总行数
row_count = data_range.Rows.Length

# 核心逻辑：从最后一行向前遍历
for i in range(row_count, 0, -1):
    # 获取单元格值并标准化
    cell = data_range[i, key_column]  
    cell_value = str(cell.DisplayedText).strip()
    
    # 规则：空值 或 已出现过的值 → 标记为删除
    if not cell_value or cell_value in seen_values:
        rows_to_remove.append(i) 
    else:
        seen_values.add(cell_value)

# 批量删除标记的行（逆序遍历收集的行号，直接删即可）
for row in rows_to_remove:
    sheet.DeleteRow(row)

# 保存并释放资源
workbook.SaveToFile("RemoveDuplicates.xlsx", ExcelVersion.Version2016)
workbook.Dispose()

Sub VBA_RemoveDuplicates_SpecCol()
    Dim ws As Worksheet
    Dim lastRow As Long
    Dim dict As Object
    Dim targetCol As String
    Dim cellVal As String
    Dim i As Long
    
    ' 指定判重列（如"A"列）
    targetCol = "A"
    
    Set ws = ActiveSheet
    Set dict = CreateObject("Scripting.Dictionary")
    lastRow = ws.UsedRange.Rows.Count
    
    If lastRow < 2 Then
        MsgBox "数据不足！", vbInfo
        Exit Sub
    End If
    
    ' 倒序遍历，仅按指定列判重
    For i = lastRow To 2 Step -1
        cellVal = IIf(IsEmpty(ws.Cells(i, targetCol).Value), "", ws.Cells(i, targetCol).Value)
        If dict.Exists(cellVal) Then
            ws.Rows(i).Delete
        Else
            dict.Add cellVal, i
        End If
    Next i
    
    Set dict = Nothing
    Set ws = Nothing
    MsgBox "按" & targetCol & "列去重完成！", vbInfo
End Sub