pip install pandas pip install openpyxl import pandas as pd class Excel(): def __init__(self): pass def get_index(self): datas = pd.read_excel('satisfaction.xlsx',sheetname='Sheet1') all_rigion = list(datas.ix[:,1]) series_list = [] rigion = ['Northeast Europe','Western Europe','Middle East'] NE_index,WE_index,ME_index, = [],[],[] row_index = [NE_index,WE_index,WE_index] for index, item in enumerate(all_rigion): for i in range(len(row_index)): if item == rigion[i]: row_index[i].append(index) for j in range(len(row_index)): for k in row_index[j]: series_list.append(datas.ix[k,:]) result = pd.DataFrame(series_list) result.to_excel(rigion[j]+'.xlsx',index=False) t = Excel() t.get_index()
def read_info(): data = xlrd.open_workbook('tmp_info.xlsx') table = data.sheets()[0] info_list, tmp_list = [], [] for i in range(1, table.nrows): tmp = table.row_values(i) for j in range(3): val = re.sub(' ', '', tmp[j]) # .encode('utf-8') val = re.sub('#', '', val) val = re.sub('$', '-', val) val = re.sub('&', '-', val) val = re.sub('+', '-', val) if len(tmp[2]) > 50: val = re.sub('_', '', val) val = re.sub('$', '', val) tmp_list.append(val) info_list.append(tmp_list) tmp_list = [] return info_list