对CSV文件和XML文件的处理

来源：互联网发布：哪几个网站能查数据编辑：程序博客网时间：2024/05/23 01:24

1.重新格式化数据并写入到CSV文件中

#!/usr/bin/python3#coding:utf-8#重新格式化数据(日期)并写入到CSV文件import csvfrom datetime import datetimedef convertDate(item):    theDate = item[-1]          #从记录中提取日期域    dateObj = datetime.strptime(theDate,'%Y-%m-%d') #解析(parse)日期域      dateStr = datetime.strftime(dateObj,'%m/%d/%Y') #格式化(format)日期对象    item[-1] = dateStr    return itemif __name__ == '__main__':    with open('ToolhireData/tooldesc.csv') as td: #打开原始CSV文件       rdr =  csv.reader(td)       items = list(rdr)        #读取记录并保存在items的列表    items = [convertDate(item) for item in items]    with open("./ToolhireData/tooldesc2.csv",'w',newline = '') as td:        wrt = csv.writer(td)        for item in items:            wrt.writerow(item)

2.添加标题行(键值)到CSV文件中

#!/usr/bin/python3#coding:utf-8#将标题行(键值)添加到CSV文件#DicReader 返回字典dict  而reader 返回列表listimport csvfields = ['ItemID','Name','Description','Owner',        'Price','Condition','DateRegistered']with open('ToolhireData/tooldesc2.csv') as td_in:    rdr = csv.DictReader(td_in,fieldnames = fields) #初始化fieldnames     items = [item for item in rdr]with open('ToolhireData/tooldesc3.csv','w',newline = '') as td_out:    wrt = csv.DictWriter(td_out,fieldnames = fields)#通过fieldnames指定了域的顺序(字典保存的域是无序的)    wrt.writeheader()    wrt.writerows(items)        #将整个items列表一次写出

3.使用ElementTree 解析 XML

#!/usr/bin/python3#coding:utf-8#使用ElementTree 解析 XML 文件#提取日期并计算书本的平均借出时间import xml.etree.ElementTree as ET #导入ElementTree解析器import datetime as dtdef parseDates(filename):    dates = []    rows  = []    dom   = ET.parse(filename)     #文件解析    #root  = dom.getroot()         #得到文件根结点    for node in dom.iter('*'):     #查找文件中所有内容 ‘*’通配符        if 'Row' in node.tag:            rows.append(node)      #结点列表    #检查结点列表中的每一行#    for row in rows:        row_dates = []        for node in row.iter('*'):            for key,value in node.attrib.items():   #检查特性key为‘Type’,value为'DateTime'的行                if 'Type' in key and 'DateTime' in value:                    row_dates.append(node.text)        if len(row_dates) == 2:                     #如果row_dates列表包含两个日期(借书日期,还书日期),则添加到dates列表            dates += row_dates        return datesdef calculateAverage(dates):    loan_periods = []    while dates:        lent = dates.pop(0).split('T')[0]        ret  = dates.pop(0).split('T')[0]        lent_date = dt.datetime.strptime(lent,'%Y-%m-%d')        ret_date  = dt.datetime.strptime(ret,'%Y-%m-%d')        loan_periods.append( (ret_date - lent_date).days )    average = sum(loan_periods)/len(loan_periods)    return averageif __name__ == '__main__':    dates = parseDates('toolhire.xml')    avg   = calculateAverage(dates)    print('Average loan period is: {} days'.format(avg))

注:测试目录和文件已上传

0 0