Make dictionary from txt file using re

Question

Consider the standard web log file in assets/logdata.txt. This file records the access a user makes when visiting a web page (like this one!). Each line of the log has the following items:

• a host (e.g., '146.204.224.152')
• a user_name (e.g., 'feest6811' note: sometimes the user name is missing! In this case, use '-' as the value for the username.)
• the time a request was made (e.g., '21/Jun/2019:15:45:24 -0700')
• the post request type (e.g., 'POST /incentivize HTTP/1.1' note: not everything is a POST!)

Your task is to convert this into a list of dictionaries, where each dictionary looks like the following:

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

This is sample of the txt data file.

I wrote these lines of codes:

import re
def logs():
    with open("assets/logdata.txt", "r") as file:
        logdata = file.read()
        #print(logdata)
        pattern="""
        (?P<host>.*)        
        (-\s)   
        (?P<user_name>\w*)  
        (\s) 
        ([POST]*)
        (?P<time>\w*)               
                 """
        for item in re.finditer(pattern,logdata,re.VERBOSE):
            print(item.groupdict())
        return(item)
logs()

It helped my in making "host" and "user_name" however I can't continue and making the rest of the requirements. can anyone help please?

Answer 1

try this my friend

import re


def logs():
    logs = []
    w = '(?P<host>(?:\d+\.){3}\d+)\s+(?:\S+)\s+(?P<user_name>\S+)\s+\[(?P<time>[-+\w\s:/]+)\]\s+"(?P<request>.+?.+?)"'
    with open("assets/logdata.txt", "r") as f:
        logdata = f.read()
    for m in re.finditer(w, logdata):
        logs.append(m.groupdict())
    return logs

Answer 2

You're using \w to get user_names, however \w doesn't include - that can be in the log (Common Log Format (CLF)), so as an alternative you could use \S+ (one or more of anything except a whitespace). For the time you can create a capturing group allowing only the expected characters (class) for that field (e.g. \w\s, -+ for the timezone, / for the date and : for the time) surrounded by squared brackets (literals), a similar capturing can be made for the request using ".

import re

regex = re.compile(
    r'(?P<host>(?:\d+\.){3}\d+)\s+'
    r'(?:\S+)\s+'
    r'(?P<user_name>\S+)\s+'
    r'\[(?P<time>[-+\w\s:/]+)\]\s+'
    r'"(?P<request>POST.+?)"'
)

def logs():
    data = []
    with open("sample.txt", "r") as f:
        logdata = f.read()
    for m in regex.finditer(logdata):
        data.append(m.groupdict())
    return data

print(logs())

(Replaced user_name from first line with "-" for testing on the second line)

[
   {
      "host":"146.204.224.152",
      "user_name":"feest6811",
      "time":"21/Jun/2019:15:45:24 -0700",
      "request":"POST /incentivize HTTP/l.l"
   },
   {
      "host":"146.204.224.152",
      "user_name":"-",
      "time":"21/Jun/2019:15:45:24 -0700",
      "request":"POST /incentivize HTTP/l.l"
   },
   {
      "host":"144.23.247.108",
      "user_name":"auer7552",
      "time":"21/Jun/2019:15:45:35 -0700",
      "request":"POST /extensible/infrastructures/one-to-one/enterprise HTTP/l.l"
   },
    ...

Answer 3

Please see the code below:

import re

regex = re.compile(
    r'(?P<host>(?:\d+\.){1,3}\d+)\s+-\s+'
    r'(?P<user_name>[\w+\-]+)?\s+'
    r'\[(?P<time>[-\w\s:/]+)\]\s+'
    r'"(?P<request>\w+.+?)"'
)

def logs():
    data = []
    with open("assets/logdata.txt", "r") as f:
        logdata = f.read()
        for item in regex.finditer(logdata):
            x = item.groupdict()
            if x["user_name"] is None:
                x["user_name"] = "-"
            data.append(x)
    return data

logs()

Please find below the part of output as well:

[{'host': '146.204.224.152', 'user_name': 'feest6811', 'time': '21/Jun/2019:15:45:24 -0700', 'request': 'POST /incentivize HTTP/1.1'}, {'host': '197.109.77.178', 'user_name': 'kertzmann3129', 'time': '21/Jun/2019:15:45:25 -0700', 'request': 'DELETE /virtual/solutions/target/web+services HTTP/2.0'}, {'host': '156.127.178.177', 'user_name': 'okuneva5222', 'time': '21/Jun/2019:15:45:27 -0700', 'request': 'DELETE /interactive/transparent/niches/revolutionize HTTP/1.1'}, {'host': '100.32.205.59', 'user_name': 'ortiz8891', 'time': '21/Jun/2019:15:45:28 -0700', 'request': 'PATCH /architectures HTTP/1.0'}, {'host': '168.95.156.240', 'user_name': 'stark2413', 'time': '21/Jun/2019:15:45:31 -0700', 'request': 'GET /engage HTTP/2.0'}, .....] with 979 dictionaries for each line of the text file.

Thank you

Answer 4

import re
def logs():
mydata = []
with open("assets/logdata.txt", "r") as file:
logdata = file.read()
pattern="""
(?P<host>.*)
(\s+)
(?:\S+)
(\s+)
(?P<user_name>\S+)
(\s+)
\[(?P<time>.*)\]\
(\s)
(?P<request>"(.)*")"""
for item in re.finditer(pattern,logdata,re.VERBOSE):
new_item = (item.groupdict())
mydata.append(new_item)
return(mydata)

Answer 5

    import re
    def logs():
        with open("assets/logdata.txt", "r") as file:
            logdata = file.read()

    result = []
    pattern = re.compile(
    r'(?P<host>.*)\s'
    r'(?:-)\s'
    r'(?P<user_name>.*)\s'
    r'\[(?P<time>.*)\]\s'
    r'"(?P<request>.*)"')
    for m in pattern.finditer(logdata):
        data = (m.groupdict())
        result.append(data)
    return result

Answer 6

import re
def logs():
with open("assets/logdata.txt", "r") as file:
    logdata = file.read()   
    lst = []
    for i in re.finditer(r'(?P<host>\S+) - (?P<user_name>\S+) \[(?P<time>.+)\] "(?P<request>.+)"', logdata):
        m = i.groupdict()
        lst.append(m)
    return lst
    raise NotImplementedError()

Answer 7

import re
def logs():
    dict=[]
    with open("assets/logdata.txt", "r") as file:
        logdata = file.read()
        pattern="""(?P<host>[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+)
                    (\ - \ )
                    (?P<user_name>(\w*)(\S))
                    (\  \S)
                    (?P<time>\d+\S\w*\S\d+\S\d+\S\d+\S\d+\s\S\d+)
                    (\S\s\S)
                    (?P<request>\w*\s\S*\s\w*\S\d.\d*)
                 """
    
    for item in re.finditer(pattern,logdata,re.VERBOSE): 
        dict.append(item.groupdict())
    return dict 
    raise NotImplementedError()

#1 import re module to use regex

#2 define function

#3 open the required file

#4 read the file

#5 write down the pattern of your required string. For more detailed information regarding regex, read the documentation. https://docs.python.org/3/library/re.html#module-re