電商 Python html格式訪客數據轉為excel格式的數據 html格式的excel轉換為excel

原文：
https://www.jianshu.com/p/4f38fe021fb3

# -*- coding: utf-8 -*-





# # 找出非excel格式的文件
# import pandas as pd
# import os
# from shutil import copyfile

# excel_dir = 'D:/工作/數據轉換/訪客數據/'
# os.chdir(excel_dir)
# for filename in os.listdir(excel_dir):
    # root_dir = ""
    # print(filename)    
    # try:
        # frame = pd.read_excel(excel_dir+filename)       
        # root_dir = "D:/工作/數據轉換/excel格式/"        
    # except Exception as e:
        # print("異常：", e)
        # root_dir = "D:/工作/數據轉換/html格式/"
    # copyfile(excel_dir+filename, root_dir+filename)









# # html的table轉換為excel
# # 原文：https://www.jianshu.com/p/4f38fe021fb3

# import pandas
# import os
# from shutil import copyfile

# excel_dir = 'D:/工作/數據轉換/html格式/'
# os.chdir(excel_dir)
# for filename in os.listdir(excel_dir):
    # print(filename)
    
    # try:
        # with open(excel_dir+filename, 'rb') as f:  
            # df = pandas.read_html(f.read(),encoding='utf-8')           
        # bb = pandas.ExcelWriter("D:/工作/數據轉換/轉換數據/" + filename)  
        # df[0].to_excel(bb,index=False)  
        # bb.close()  
    # except Exception as e:
        # print("異常："+e)
        # # copyfile(excel_dir+filename, "D:/工作/數據轉換/出錯數據/" + filename)
    




# # 單文件測試
# import pandas
# import os
# with open('訪客-2020-09-18 23_45_16.xlsx', 'rb') as f:  
    # df = pandas.read_html(f.read(),encoding='utf-8')           
# bb = pandas.ExcelWriter('訪訪客-2020-09-18 23_45_16-1.xlsx')  
# df[0].to_excel(bb,index=False)  
# bb.close()  








# # 批量文件改名
# import os

# excel_dir = 'D:/工作/數據轉換/1/'
# os.chdir(excel_dir)
# for filename in os.listdir(excel_dir):
    # print(filename)
    # oldFullName = excel_dir+filename
    # newFullName = excel_dir+"1店-"+filename
    # os.rename(oldFullName, newFullName)


    





# # excel轉換為csv文件
# import pandas as pd
# import os
# import re


# excel_dir = 'D:/工作/數據轉換/轉換數據/'
# os.chdir(excel_dir)
# for filename in os.listdir(excel_dir):
    # print(filename)
   
    # # filename = "訪客-2020-07-30 23_11_30.xlsx"
    # df = pd.read_excel(filename,index_col=0)


    # # 訪問時間列 增加 日期
    # m = re.search("(\d{4}-\d{1,2}-\d{1,2})", filename)   
    # strdate = m.group(1)
    # df["訪問時間"] =['%s %s' % (strdate, s) for s in df["訪問時間"]]

    # col_name = df.columns.tolist()
    # if '搜索關鍵字' not in col_name:
        # # 插入列
        # index = col_name.index('入店來源') + 1
        # col_name.insert(index, '搜索關鍵字')
        # df = df.reindex(columns = col_name)

        # # 修改值
        # df.loc[df['入店來源'].str.find('手淘搜索') > -1 , '搜索關鍵字'] = df['入店來源'].str.replace('手淘搜索','')
        # df.loc[df['入店來源'].str.find('手淘搜索') > -1 , '入店來源'] = '手淘搜索'


    # file_name = os.path.splitext(filename)[0]
    # df.to_csv('D:/工作/數據轉換/CSV數據/'+file_name+'.csv',encoding='utf-8')







# # 數據合並
# import pandas as pd
# import os

# path = "./2店/"
# files = os.listdir(path)
# list_excel = []

# for filename in files:
    # fullname = path + filename# excel的相對路徑
    # df = pd.read_csv(fullname)# 默認讀取Excel的第一個表單    
    # list_excel.append(df)# 把Excel追加到list中

# writer = pd.ExcelWriter('合並后的數據.xlsx')
# pd.concat(list_excel).to_excel(writer,'sheet1',index=False)
# writer.save()
# print('合並完成')