import pandas as pd
import argparse
def read_excel_file(excel_file, key_word_list, save_path):
'''
todo: pick up keyword from excel
'''
df = pd.read_excel(excel_file)
data=df.values
col_name = df.columns.tolist()
for i in range(1,len(key_word_list)+1):
col_name.insert(len(col_name) + i,key_word_list[i-1])
df[key_word_list[i-1]] = df[col_name[0]]
for key in key_word_list:
for i in range(len(data)):
df[key][i] = 0
row = data[i]
for j in range(len(row)):
cell = row[j]
if key in str(cell):
df[key][i] = 1
df.to_excel(save_path)
def main():
excel_file = 'ori.xlsx'
save_path = 'after.xlsx'
key_word_list = []
parser = argparse.ArgumentParser('pick up keyword in excel')
parser.add_argument('-i', type=str, default=excel_file,help='the input folder of files')
parser.add_argument('-k', nargs = '+', default=key_word_list,help='the list of keyword')
parser.add_argument('-o', type=str, default=save_path,help='the output folder of files')
args = parser.parse_args()
read_excel_file(args.i, args.k, args.o)
if __name__ == '__main__':
main()
使用方法:python xx.py -k key_a key_b key_c