django后台批量导入数据
在生产环境中,往往数据不是几条或者几百条,那么举个例子,将公司所有员工员工号或者帐号密码导入进后台,那就不建议你去后台一条条记录去添加了
如何从xml中批量导入svn记录
第一步:
为数据建立模型
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
|
@python_2_unicode_compatible
class SVNLog(models.Model):
vision = models.IntegerField(verbose_name = u "修订版本" , blank = False , null = False ,)
author = models.CharField(verbose_name = u "作者" , max_length = 60 , blank = True , null = True )
date = models.DateTimeField(verbose_name = u "修订时间" ,null = True )
msg = models.TextField(verbose_name = u "注释消息" , blank = False , null = False , default = u"")
paths = models.TextField(verbose_name = u "影响的文件" , blank = False , null = False , default = u"")
created_time = models.DateTimeField(verbose_name = u "创建时间" , auto_now_add = True , )
update_time = models.DateTimeField(verbose_name = u "修改时间" , auto_now = True , )
class Meta:
ordering = [ 'revision' ]
def __str__( self ):
return u 'r%s' % ( self .revision or u"", )
|
既然建立好了模型,那我们再去建立接受我们xml文件的models
1
2
3
4
5
6
7
8
9
10
11
|
@python_2_unicode_compatible
class ImportLogFile(models.Model):
LogFile = models.FileField(upload_to = 'LogFile' )
FileName = models.CharField(max_length = 50 , verbose_name = u '文件名' )
class Meta:
ordering = [ 'FileName' ]
def __str__( self ):
return self .FileName
|
ok,以上代码我们定义好了数据和上传文件的model
同步数据库
1
2
|
python manage.py makemigrations
python manage.py migrate
|
接着我们去修改admin.py 让我们可以从后台上传文件,
1
2
3
4
5
6
7
8
9
10
|
class ImportLogAdmin(admin.ModelAdmin):
list_display = ( 'LogFile' , 'FileName' ,)
list_filter = [ 'FileName' ,]
def save_model( self , request, obj, form, change):
re = super (YDImportLogAdmin, self ).save_model(request, obj, form, change)
update_svn_log( self , request, obj, change)
return re
|
注意上面代码里的save_model,这里才是关键,在这里我重写了ModelAdmin里的save_model方法
因为我们要把上传文件,读取文件,解析文件,操作数据库合为一步来操作,大家可以打开debug,在上传文件的时候,返回参数的obj里包括了文件上传的路径,这个路径也是下一步我们操作解析文件的关键,好了我们在这个app文件夹下新建一个utils.py 用来操作我们操作文件和数据库的工具类,为了简单我写成了函数如下
先贴一下我们要测试的xml文件
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
|
<? xml version = "1.0" encoding = "UTF-8" ?>
< log >
< logentry
revision = "2" >
< author >qwert</ author >
< date >2016-09-27T07:16:37.396449Z</ date >
< paths >
< path
action = "A"
prop-mods = "false"
text-mods = "true"
kind = "file" >/aaa/README
</ path >
</ paths >
< msg >20160927 151630</ msg >
</ logentry >
< logentry
revision = "1" >
< author >VisualSVN Server</ author >
< date >2016-09-20T05:03:12.861315Z</ date >
< paths >
< path
action = "A"
prop-mods = "false"
text-mods = "false"
kind = "dir" >/branches</ path >
< path
action = "A"
prop-mods = "false"
text-mods = "false"
kind = "dir" >/tags</ path >
< path
action = "A"
prop-mods = "false"
text-mods = "false"
kind = "dir" >/trunk</ path >
</ paths >
< msg >hello word</ msg >
</ logentry >
</ log >
|
输出结果格式
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
|
r2 | qwer | 2016 - 09 - 27 15 : 16 : 37 + 0800 (二, 27 9 2016 ) | 1 line
Changed paths:
A / xxx / README
20160927 151630
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
r1 | VisualSVN Server | 2016 - 09 - 20 13 : 03 : 12 + 0800 (二, 20 9 2016 ) | 1 line
Changed paths:
A / branches
A / tags
A / trunk
Initial structure.
from .models import SVNLog
import xmltodict
def update_svn_log( self , request, obj, change):
headers = [ 'r' , 'a' , 'd' , 'm' , 'p' ]
filepath = obj.LogFile.path
xmlfile = xmltodict.parse( open (filepath, 'r' ))
xml_logentry = xml.get( 'log' ).get( 'logentry' )
info_list = []
pathlist = []
sql_insert_list = []
sql_update_list = []
for j in xml:
data_dict = {}
# get path
paths = j.get( 'paths' ).get( 'path' )
if isinstance (paths, list ):
for path in paths:
action = path.get( '@action' )
pathtext = path.get( '#text' )
pathtext = action + ' ' + pathtext
pathlist.append(pathtext)
_filelist = u '\n' .join(pathlist)
_paths = u "Changed paths:\n {}" . format (_filelist)
print _paths
else :
_filelist = paths.get( '@action' ) + ' ' + paths.get( '#text' )
_paths = u "Changed paths:\n {}" . format (_filelist)
print _paths
# get revision
vision = j.get( '@vision' )
# get auth
author = j.get( 'author' )
#get date
date = j.get( 'date' )
#get msg
msg = j.get( 'msg' )
data_dict[headers[ 0 ]] = int (vision)
data_dict[headers[ 1 ]] = author
data_dict[headers[ 2 ]] = date
data_dict[headers[ 3 ]] = msg
data_dict[headers[ 4 ]] = _paths
info_list.append(data_dict)
_svnlog = SVNLog.objects. filter ().order_by( '-vision' ).first()
_last_version = _svnlog.vision if _svnlog else 0
for value in info_list:
vision = value[ 'r' ]
author = value[ 'a' ]
date = value[ 'd' ]
msg = value[ 'm' ]
paths = value[ 'p' ]
print vision,author
_svnlog = YDSVNLog.objects. filter ().order_by( '-revision' ).first()
_last_version = _svnlog.revision if _svnlog else 0
if vision > _last_version:
sql_insert_list.append(SVNLog(revision = revision, author = author, date = date, msg = msg, paths = paths))
else :
sql_update_list.append(SVNLog(revision = revision, author = author, date = date, msg = msg, paths = paths))
SVNLog.objects.bulk_create(sql_insert_list)
SVNLog.objects.bulk_create(sql_update_list)
|
我们使用的xmltodict这个第三方库来解析xml,他把内容解析成了高效率的orderdict类型,就是有序列的字典
这个xml中比较复杂的是那个paths里的path,因为这个xml中包含两个元素,第一个元素的path只含有一个path,第二个元素中的paths包含有三个path,因此我们在解析获取的时候需要判断一下
1
2
3
|
paths = j.get( 'paths' ).get( 'path' )
if isinstance (paths, list ):
pass
|
我们判断这个path是不是一个list类型的,如果是,那我们就按照list的方式来处理,如果不是,那我们就按单个的方式来处理,获取之后按照输出结果格式处理下结果然后获取其他内容
1
2
3
4
5
6
7
|
revision = j.get( '@vision' )
# get auth
author = j.get( 'author' )
#get date
date = j.get( 'date' )
#get msg
msg = j.get( 'msg' )
|
最后我们将获取到的元素存在字典里
在循环中判断当前的版本号和数据库中的版本号,
如果比原来的小,那么我们执行更新操作,反之执行插入操作
最后使用了bulk_create来操作数据库,这样避免了循环中每次都进行数据库操作造成的资源浪费