如何将此函数的输出更改为字典？ [复制]

Question

我编写了一个包含正则表达式的函数来分隔txt 文件的一些特殊部分。代码工作正常，但我想得到一个字典作为输出，长度应该是 979：

import re

def logs():
    with open("C:/Users/ASUS/Desktop/logdata.txt", "r") as file:
        logdata = file.read()

    pattern = ''' 
    (?P<host>\d{1,}\.\d{1,}\.\d{1,}\.\d{1,})    # host name
    \s+\S+\s+
    (?P<user_name>(?<=-\s)(\w+|-)(?=\s))\s+\[   # user_name
    (?P<time>([^[]+))\]\s+"                     # time
    (?P<request>[^"]+)"                         # request
    '''

    for item in re.finditer(pattern, logdata, re.VERBOSE):
        print(item.groupdict())

这个函数应该变成这样的文本：

146.204.224.152 - feest6811 [21/Jun/2019:15:45:24 -0700] "POST /incentivize HTTP/1.1" 302 4622

到此捕获host、user_name 等：

{"host":"146.204.224.152", 
 "user_name":"feest6811", 
 "time":"21/Jun/2019:15:45:24 -0700",
 "request":"POST /incentivize HTTP/1.1"}

我该怎么做？

Answer 1

晚了，但这个详细的正则表达式也可以（返回字典列表]

import re
def logs():
    with open("C:/Users/ASUS/Desktop/logdata.txt", "r") as file:
        logdata = file.read()
    
    pattern = """
    (?P<host>[\d\.]*)       #IP host
    (\ -\ )                 #followed by 
    (?P<user_name>[\w-]*)   #user name
    (\ *\[)                 #followed by 
    (?P<time>[^\]]*)        #time
    (\]\ *")                #followed by 
    (?P<request>[^\"]*)     #request"""

    return [item.groupdict() for item in re.finditer(pattern, logdata, re.VERBOSE)]

Answer 2

直接使用groupdict()即可：

import re 

def rtr_dict(txt):
  pattern = ''' 
  (?P<host>\d{1,}\.\d{1,}\.\d{1,}\.\d{1,})   # host name
  \s+\S+\s+
  (?P<user_name>(?<=-\s)(\w+|-)(?=\s))\s+\[   # user_name
  (?P<time>([^[]+))\]\s+"   # time
  (?P<request>[^"]+)"   # request
  '''
  
  if m:=re.match(pattern, txt, flags=re.VERBOSE):
    return m.groupdict()

tgt='146.204.224.152 - feest6811 [21/Jun/2019:15:45:24 -0700] "POST /incentivize HTTP/1.1" 302 4622'


>>>rtr_dict(tgt)
{'host': '146.204.224.152', 'user_name': 'feest6811', 'time': '21/Jun/2019:15:45:24 -0700', 'request': 'POST /incentivize HTTP/1.1'}

---

请你告诉我，我怎样才能做到不止一行，就像我使用 for 循环那样。

给定：

tgt='''146.204.224.152 - feest6811 [21/Jun/2019:15:45:24 -0700] "POST /incentivize HTTP/1.1" 302 4622
146.204.224.153 - feest6811 [21/Jun/2019:15:45:24 -0700] "POST /incentivize HTTP/1.1" 302 4623
146.204.224.154 - feest6811 [21/Jun/2019:15:45:24 -0700] "POST /incentivize HTTP/1.1" 302 4624'''

如果你有多个匹配，你可以返回一个字典列表：

def rtr_dict(txt):
  pattern = ''' 
  (?P<host>\d{1,}\.\d{1,}\.\d{1,}\.\d{1,})   # host name
  \s+\S+\s+
  (?P<user_name>(?<=-\s)(\w+|-)(?=\s))\s+\[   # user_name
  (?P<time>([^[]+))\]\s+"   # time
  (?P<request>[^"]+)"   # request
  '''
  
  return [m.groupdict() for m in re.finditer(pattern, txt, flags=re.VERBOSE)]

>>> rtr_dict(tgt)
[{'host': '146.204.224.152', 'user_name': 'feest6811', 'time': '21/Jun/2019:15:45:24 -0700', 'request': 'POST /incentivize HTTP/1.1'}, {'host': '146.204.224.153', 'user_name': 'feest6811', 'time': '21/Jun/2019:15:45:24 -0700', 'request': 'POST /incentivize HTTP/1.1'}, {'host': '146.204.224.154', 'user_name': 'feest6811', 'time': '21/Jun/2019:15:45:24 -0700', 'request': 'POST /incentivize HTTP/1.1'}]

或者使用生成器：

def rtr_dict(txt):
  pattern = ''' 
  (?P<host>\d{1,}\.\d{1,}\.\d{1,}\.\d{1,})   # host name
  \s+\S+\s+
  (?P<user_name>(?<=-\s)(\w+|-)(?=\s))\s+\[   # user_name
  (?P<time>([^[]+))\]\s+"   # time
  (?P<request>[^"]+)"   # request
  '''
  
  for m in re.finditer(pattern, txt, flags=re.VERBOSE):
    yield m.groupdict()

>>> list(rtr_dict(tgt))
# same list of dicts...