这两天在优化公司一个python的项目，顺便研究了一下如何将python日志转成json格式，原来在Java的项目中搞过类似的事情，知道日志转成json之后有很多便利的之处，最常见的就是可以直接对接各种日志分析系统，如开源的ELK，将数据导入之后就能快速的进行查询和分析，方便做各种统计，监控或报警等。
python里面的logging组件，其实已经是组件化了，有Logger组件，Handler组件，Fomatter组件，如下图所示：
进群“943752371” 即可获取书十套PDF！
logger=>handler=>formatter分别是一对多的关系，日志的格式其实是由formatter决定的，所以想要扩展成你想要的各种格式，就重写定制formatter组件就可以了，它实际上和Java里面Log4j的LayOut组件类似。
核心代码如下：
REMOVE_ATTR
=
[
"filename"
,
"module"
,
"exc_text"
,
"stack_info"
,
"created"
,
"msecs"
,
"relativeCreated"
,
"exc_info"
,
"msg"
]
class
JSONFormatter
(
logging
.
Formatter
):
host_name
,
host_ip
=
HostIp
.
get_host_ip
()
def
format
(
self
,
record
):
extra
=
self
.
build_record
(
record
)
self
.
set_format_time
(
extra
)
# set time
self
.
set_host_ip
(
extra
)
# set host name and host ip
extra
[
'message'
]
=
record
.
msg
# set message
if
record
.
exc_info
:
extra
[
'exc_info'
]
=
self
.
formatException
(
record
.
exc_info
)
if
self
.
_fmt
==
'pretty'
:
return
json
.
dumps
(
extra
,
indent
=
1
,
ensure_ascii
=
False
)
else
:
return
json
.
dumps
(
extra
,
ensure_ascii
=
False
)
@classmethod
def
build_record
(
cls
,
record
):
return
{
attr_name
:
record
.
__dict__
[
attr_name
]
for
attr_name
in
record
.
__dict__
if
attr_name
not
in
REMOVE_ATTR
}
@classmethod
def
set_format_time
(
cls
,
extra
):
now
=
datetime
.
datetime
.
utcnow
()
format_time
=
now
.
strftime
(
"%Y-%m-%dT%H:%M:%S"
+
".%03d"
%
(
now
.
microsecond
/
1000
)
+
"Z"
)
extra
[
'@timestamp'
]
=
format_time
return
format_time
@classmethod
def
set_host_ip
(
cls
,
extra
):
extra
[
'host_name'
]
=
JSONFormatter
.
host_name
extra
[
'host_ip'
]
=
JSONFormatter
.
host_ip
使用的时候，可以通过简单配置即可：
[
loggers
]
keys
=
root
[
handlers
]
keys
=
console
,
file
[
formatters
]
keys
=
json
,
json_pretty
[
logger_root
]
level
=
DEBUG
;
handlers
=
console
,
file
,
rotate
handlers
=
console
,
file
[
handler_console
]
class
=
StreamHandler
level
=
INFO
formatter
=
json_pretty
args
=(
sys
.
stderr
,)
[
handler_file
]
class
=
FileHandler
level
=
INFO
formatter
=
json
args
=(
'log/base_conf.log'
,
'a'
,
'utf-8'
)
[
handler_rotate
]
class
=
handlers
.
TimedRotatingFileHandler
level
=
INFO
formatter
=
json
args
=(
'log/rotate.log'
,
'D'
,
1
,
0
,
'utf-8'
)
[
formatter_json
]
class
=
format
.
json_formatter
.
JSONFormatter
[
formatter_json_pretty
]
format
=
pretty
class
=
format
.
json_formatter
.
JSONFormatter
如下的一段异常代码：
fileConfig
(
'log_conf.ini'
)
log
=
logging
.
getLogger
(
__name__
)
try
:
a
=
1
/
0
except
Exception
:
log
.
exception
(
" occurred exception "
)
输出结果如下：
{
"name"
:
"__main__"
,
"args"
:
[],
"levelname"
:
"ERROR"
,
"levelno"
:
40
,
"pathname"
:
"C:/texx.py"
,
"lineno"
:
17
,
"funcName"
:
"base_configuration"
,
"thread"
:
10608
,
"threadName"
:
"MainThread"
,
"processName"
:
"MainProcess"
,
"process"
:
11916
,
"@timestamp"
:
"2019-01-10T12:50:20.392Z"
,
"host_name"
:
"your-PC"
,
"host_ip"
:
"192.168.10.11"
,
"message"
:
" occurred exception "
,
"exc_info"
:
"Traceback (most recent call last): File "C:/txxx.py", line 14, in base_configuration a = 1 / 0ZeroDivisionError: division by zero"
}
可以看到内容非常详细，并且组件还支持自定义字段的加入，在收集到日志系统上，可以非常的方便检索统计。
详细的解释和代码，可以fork我的github：https://github.com/qindongliang/python_log_json