Python提取 Excel 中重复项 / 去重
import pandas as pd
df = pd.read_excel('数据.xlsx')
# 去重
df.drop_duplicates(subset=['手机号'], keep='first').to_excel('去重后.xlsx', index=False)
# 找重复
dup = df[df.duplicated(subset=['手机号'], keep=False)]
dup.to_excel('重复项.xlsx', index=False)
print(f"原始 {len(df)} 行，去重后剩余 {len(df.drop_duplicates(subset=['手机号']))} 行")
更新时间：2026-09-14 13:15:07