合并多个excel文件

经常需要汇总多张excel表格，于是有了下面这个小脚本。

import os
import glob
import pandas as pd

# drop duplications according to parameter 'on'
def merge_excel(path, id):
    all_data = pd.DataFrame()
    for f in glob.glob(path):
        print(f)
        df = pd.read_excel(f) #header=3 可以设置从第几行开始读取，默认从第0行开始
        df_not_null = df.dropna(subset=["目标工作所在地"])  # delete null on some columns
        all_data = all_data.append(df_not_null, ignore_index=True)
    return all_data.drop_duplicates(id,'last')

if __name__ == '__main__':
    source_path = "/Users/sunchenn/sunchenn/mergeExcel/exampleExcels/*.xlsx"
    target_path = "/Users/sunchenn/sunchenn/mergeExcel"

    df = merge_excel(source_path, "学号")
    df.to_excel(os.path.join(target_path,"Total.xlsx"),index=False)