抽取数据320

import pandas as pd

# 读取的原始文件
read_file = '原始文件.xlsx'

# 要输出的文件名
substrate_coa_data = 'SUBSTRATE_EPITAXY_SUBSTRATE_COA_DATA_11.xlsx'
epi_coa_data = 'SUBSTRATE_EPITAXY_SIC_EPI_COA_DATA_22.xlsx'
thikness_data = 'SUBSTRATE_EPITAXY_SIC_EPI_THIKNESS_DATA_33.xlsx'
doping_data = 'SUBSTRATE_EPITAXY_SIC_EP1_DOPING_DATA_44.xlsx'

"""
衬底原厂数据
"""

df1 = pd.read_excel(read_file, sheet_name='衬底原厂数据', skiprows=3)
del df1['remark']
column1 = ['WAFER ID', 'Substarte ID', 'Thickness(um)', 'Resistivity(Ωcm)', 'MPD', 'RMS', 'TTV', 'LTV', 'BOW',
           'WARP', 'BPD', 'TSD', 'TED', 'EPD']
df1['文件名'] = read_file
column1.insert(2, '文件名')
df1 = df1.reindex(columns=column1)
# for idx, rows in df1.iterrows():
#     line = [rows['Wafer ID'], rows['Substarte ID'], read_file, rows['Thickness(um)'], rows['Resistivity(Ωcm)'],
#             rows['MPD'], rows['RMS'], rows['TTV'], rows['LTV'], rows['BOW'], rows['WARP'], rows['BPD'], rows['TSD'],
#             rows['TED'], rows['EPD']]
#     substrate_coa_data_list.append(line)
# df1 = pd.DataFrame(substrate_coa_data_list, columns=column1)
df1.to_csv(substrate_coa_data, index=False)

"""
外延报告检测
"""
column2 = ['Wafer ID', 'Laser Mark', '厚度', '厚度均匀性', '浓度', '浓度均匀性', 'Downfalls', 'triangle', 'carrot', 'lines',
           'H_LINES', 'V_SHAPE', 'edd', 'dy', 'remark']
df2 = pd.read_excel(read_file, sheet_name='外延报告检测', skiprows=4, names=column2)
del df2['remark']
column2.remove('remark')
df2['原始文件名'] = read_file
column2.insert(2, '原始文件名')
df2 = df2.reindex(columns=column2)
df2.to_csv(epi_coa_data, index=False)

"""
外延厚度测量值
"""
column3 = ['Wafer ID', 'Laser Mark', 'SIC_THK1_1', 'SIC_THK1_2', 'SIC_THK1_3', 'SIC_THK1_4', 'SIC_THK1_5',
           'SIC_THK1_6', 'SIC_THK1_7', 'SIC_THK1_8', 'SIC_THK1_9', 'SIC_THK1_10', 'SIC_THK1_11', 'SIC_THK1_12',
           'SIC_THK1_13', 'SIC_THK1_14', 'SIC_THK1_15', 'SIC_THK1_16', 'SIC_THK1_17', '平均值', 'STD', '均匀性']
df3 = pd.read_excel(read_file, sheet_name='外延厚度测量值', skiprows=3, names=column3)
df3['原始文件名'] = read_file
column3.insert(2, '原始文件名')
df3 = df3.reindex(columns=column3)
df3.to_csv(thikness_data, index=False)

"""
外延浓度测量值
"""
column4 = ['WAFER_ID', 'LASSER_MARK', 'sic-DOP(E15)-1', 'sic-DOP(E15)-2', 'sic-DOP(E15)-3', 'sic-DOP(E15)-4',
           'sic-DOP(E15)-5', 'sic-DOP(E15)-6', 'sic-DOP(E15)-7', 'sic-DOP(E15)-8', 'sic-DOP(E15)-9', '平均值', 'STD',
           '均匀性', 'remark']
df4 = pd.read_excel(read_file, sheet_name='外延浓度测量值', skiprows=3, names=column4)
del df4['remark']
column4.remove('remark')
df4['文件名'] = read_file
column4.insert(2, '文件名')
df4 = df4.reindex(columns=column4)
df4.to_csv(doping_data, index=False)