大仙帮小弟看看代码，如何将代码简化一下

[shevchenko2010]

with open('data_pps.xml','r') as file:
    data = file.read()
conn = sqlite3.connect('SQLite_pps.db')
c = conn.cursor()
c.execute('''select keyword from mydata where level = 2''')
cc = c.fetchall() #从数据库中获取字段
list_keywords = []
for oo in cc:
    list_keywords.append(oo[0].encode("utf-8"))
#return list_keywords
    #pp = oo[0].encode('utf-8')
#***********************************************************************************************************************
"""筛选掉二级标签，保留数据标签"""
for i in data.split('</goods>')[:-1]:
    city_name = i.split('<city_name>')[-1].split('</city_name>')[0].decode('utf-8')
    site_url = i.split('<site_url>')[-1].split('</site_url>')[0].decode('utf-8')
    title = i.split('<title>')[-1].split('</title>')[0].decode('utf-8')
    goods_url = i.split('<goods_url>')[-1].split('</goods_url>')[0].decode('utf-8')
    desc = i.split('<desc>')[-1].split('</desc>')[0].decode('utf-8')
    #class = i.split('<class>')[-1].split('</class>')[0].decode('utf-8')
    img_url = i.split('<img_url>')[-1].split('</img_url>')[0].decode('utf-8')
    original_price = i.split('<original_price>')[-1].split('</original_price>')[0].decode('utf-8')
    sale_price = i.split('<sale_price>')[-1].split('</sale_price>')[0].decode('utf-8')
    sale_rate = i.split('<sale_rate>')[-1].split('</sale_rate>')[0].decode('utf-8')
    sales_num = i.split('<sales_num>')[-1].split('</sales_num>')[0].decode('utf-8')
    start_time = i.split('<start_time>')[-1].split('</start_time>')[0].decode('utf-8')
    site_name = i.split('<site_name>')[-1].split('</site_name>')[0].decode('utf-8')
    close_time = i.split('<close_time>')[-1].split('</close_time>')[0].decode('utf-8')
    merchant_name = i.split('<merchant_name>')[-1].split('</merchant_name>')[0].decode('utf-8')
    merchant_tel = i.split('<merchant_tel>')[-1].split('</merchant_tel>')[0].decode('utf-8')
    spend_start_time = i.split('<spend_start_time>')[-1].split('</spend_start_time>')[0].decode('utf-8')
    spend_close_time = i.split('<spend_close_time>')[-1].split('</spend_close_time>')[0].decode('utf-8')
    merchant_addr = i.split('<merchant_addr>')[-1].split('</merchant_addr>')[0].decode('utf-8')
    hot_area = i.split('<hot_area>')[-1].split('</hot_area>')[0].decode('utf-8')
    longitude = i.split('<longitude>')[-1].split('</longitude>')[0].decode('utf-8')
    latitude = i.split('<latitude>')[-1].split('</latitude>')[0].decode('utf-8')
    c.execute('''insert into api_data(city_name,site_url,title,goods_url,desc,img_url,original_price,sale_price,sale_rate,
                                        sales_num,start_time,close_time,merchant_name,merchant_tel,spend_start_time,spend_close_time,
                                        merchant_addr,hot_area,longitude,latitude,site_name)
                                        values (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)''',
             (city_name,site_url,title,goods_url,desc,img_url,original_price,sale_price,sale_rate,
                                        sales_num,start_time,close_time,merchant_name,merchant_tel,spend_start_time,spend_close_time,
                                        merchant_addr,hot_area,longitude,latitude,site_name))
conn.commit()
print "Write data sucess!!"

[CDSoftwareWj]

汗， 光这一句 i.split('<city_name>')[-1].split('</city_name>')[0].decode('utf-8') 你就可以提出来做个小函数啊

def getValue(item, name)
    return item.split("<%s>" % name)[-1].split("</%s>" %s name)[0].decode('utf-8')

...
city_name = getValue(i, "city_name")

[CDSoftwareWj]

def getValue(item, name)
    return item.split("<%s>" % name)[-1].split("</%s>" % name)[0].decode('utf-8')

...
city_name = getValue(i, "city_name")

更近一步可以按 name 自动返回变量列表 一个循环就全完成了 -_-||

[angel_su]

标签名死写成字符串不妥，这些标签和api_data的字段一致，那就从数据库提出利用，代码自然会变得精简一些...

[panghuhu250]

用正则表达式找出所有的tag及对应的值。下面的saveRow返回要执行的sql语句。

In [43]: def saveRow(row):
    ...:     pat = re.compile(r"<([a-zA-Z_]*)>(.*)</\1>")
    ...:     tags, values = zip(*re.findall(pat, row))
    ...:     return "insert into api_data (%s) values (%s)" % (','.join(tags), ','.join(values))

In [44]: s = "<a>1</a>  <b>2</b> <c>abcde</c>"

In [45]: saveRow(s)
Out[45]: 'insert into api_data (a,b,c) values (1,2,abcde)'