python清洗excel的数据还是很简单的
这里就列举例子说一下
这是原始数据，这里要处理的是地区和薪水两个字段。
清洗前数据
import xlrd
import codecs
import re
def get_salary(salary):
# 利用正则表达式提取月薪，把待遇规范成千/月的形式
# 返回最低工资，最高工资的形式
if '-' in salary: # 针对1-2万/月或者10-20万/年的情况，包含-
low_salary = re.findall(re.compile('(\d*\.?\d+)'), salary)[0]
high_salary = re.findall(re.compile('(\d?\.?\d+)'), salary)[1]
if u'万' in salary and u'年' in salary: # 单位统一成千/月的形式
low_salary = float(low_salary) / 12 * 10
high_salary = float(high_salary) / 12 * 10
elif u'万' in salary and u'月' in salary:
low_salary = float(low_salary) * 10
high_salary = float(high_salary) * 10
else: # 针对20万以上/年和100元/天这种情况，不包含-，取最低工资，没有最高工资
low_salary = re.findall(re.compile('(\d*\.?\d+)'), salary)[0]
high_salary = ""
if u'万' in salary and u'年' in salary: # 单位统一成千/月的形式
low_salary = float(low_salary) / 12 * 10
elif u'万' in salary and u'月' in salary:
low_salary = float(low_salary) * 10
elif u'元' in salary and u'天' in salary:
low_salary = float(low_salary) / 1000 * 21 # 每月工作日21天
return low_salary, high_salary
def open_xlsx(file):
# 加载Excel数据，获得工作表和行数
data = xlrd.open_workbook(file) #读取工作表名称
table0 = data.sheet_by_name('51') #读取 当前sheet表
nrows = table0.nrows # 获取行数
return table0, nrows
def main():
table, nrows = open_xlsx('512.xlsx') # 调用打开excel的函数
print('一共有{}行数据，开始清洗数据'.format(nrows))
for i in range(1, nrows):
job = table.row_values(i)[0]
company = table.row_values(i)[1]
companytype = table.row_values(i)[2]
area = table.row_values(i)[3][:2] # 地区取到城市，把区域去掉
if area:
area_list.append(area)
experience = table.row_values(i)[4]
degree = table.row_values(i)[5]
salary = table.row_values(i)[6]
if salary: # 如果待遇这栏不为空，计算最低最高待遇
getsalary = get_salary(salary)
low_salary = getsalary[0]
high_salary = getsalary[1]
else:
low_salary = high_salary = ""
print('正在写入第{}条，最低工资是{}k,最高工资是{}k'.format(i, low_salary, high_salary))
output = ('{}\t{}\t{}\t{}\t{}\t{}\t{}\t{}\n').format(job, company, companytype, area,
experience,degree, low_salary, high_salary
)
f = codecs.open('51jobanaly.xls', 'a+')
f.write(output)
f.close()
if __name__ == '__main__':
main()
主要把薪资处理成以千/月为单位。保留城市。
处理后的数据：
处理后的数据