import pandas as pd
import re
import xlwt
a=pd.DataFrame(pd.read_excel(R'F:\001識別後\A.xlsx'))
workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet('My Worksheet')
k=1
for i,j in zip(a['A'],a['B']):
try:
if i[:4].isdigit():
sch_code=i[:4]
schname=re.findall('([\\u4e00-\\u9fa5]{0,})\[*'
 
,i[4:])
num=re.findall(r'\d+',j)
num0=num[0]
sch_name = schname[0].strip('.；,， •■')
worksheet.write(k, 0, i)
worksheet.write(k, 1, j)
worksheet.write(k, 2, sch_code)
worksheet.write(k, 3, sch_name)
worksheet.write(k, 8, num0)
k = k + 1
elif i[:1].isalpha():
major_id=i[:2]
major_name=re.findall('(\D+)\(|(\D+)'
 
,i[2:])[0]
other = re.findall('\((\D+)\)', i)
if j[:1].isdigit():
num1=re.findall('\d+',str(j))
num10=num1[0]#學費
num11=num1[1]#年制
num12=num1[2]#人數
else:
num1 = re.findall('\d+', str(j))
num10 = '待定'  # 學費
num11 = num1[0]  # 年制
num12 = num1[1]  # 人數
# all = re.findall('\D+', i[2:])
worksheet.write(k, 0, i)
 
worksheet.write(k, 1, str(j))
worksheet.write(k, 2, sch_code)
worksheet.write(k, 3, sch_name)
worksheet.write(k, 4, major_id)
worksheet.write(k, 5, major_name)
worksheet.write(k, 6, num10)
worksheet.write(k, 7, num11)
worksheet.write(k, 8, num12)
if other!=[]:
worksheet.write(k, 9, other[0])k=k+1
else:
print(k+1)
worksheet.write(k, 0, i)
worksheet.write(k, 1, j)
k = k + 1
except:
print(k+1)
worksheet.write(k, 0, i)
worksheet.write(k, 1, j)
k = k + 1
workbook.save(R'F:\002跑程式後\B.xls')