How to compare strings of lines from two different files using python?

This is my solution

In [1]: import re

In [2]: pat = r'(?P<month>[A-Za-z]{3})\s{1,3}(?P<day>\d{1,2})\s{1,2}(?P<ts>\d+:\d+:\d+).*to=<(?P<email>([\w\.-]+)@([\w\.-]+))'

In [3]: emails = set()

In [4]: date_email = {}

In [6]: with open('maillog.txt', mode='r') as f:
   ...:     for line in f:
   ...:         month, day, ts, email = re.search(pat, line).group('month', 'day', 'ts', 'email')
   ...:         date_email[email] = (month, day, ts)
   ...:         

In [7]: date_email
Out[7]: 
{'[email protected]': ('Nov', '3', '10:08:43'),
 '[email protected]': ('Nov', '3', '10:10:45'),
 '[email protected]': ('Nov', '3', '10:16:42'),
 '[email protected]': ('Nov', '3', '10:15:45'),
 '[email protected]': ('Nov', '3', '10:18:42'),
 '[email protected]': ('Nov', '3', '10:17:44')}

In [11]: with open('testmail.txt', mode='r') as f:
    ...:     for line in f:
    ...:         emails.add(line.strip())
    ...:         

In [12]: emails
Out[12]: {'[email protected]', '[email protected]'}

In [15]: for email in emails:
    ...:     if email in date_email:
    ...:         print(email, date_email[email])
    ...:         
('[email protected]', ('Nov', '3', '10:08:43'))

You can format output the way you want.

open statement along with "with" keyword can be combined like this

with open(file1, mode='r') as f1, open(file2, mode='r') as f2:
    # do something with f1
    # do something with f2

Quick and untested but simple enough conceptually: compile a big whoppin' regex with all the addresses already in it.

import re

with open("testmail.txt") as fh1:
    emails = []
    for addr in fh1:
        emails.append(re.escape(addr.strip()))
    pattern=re.compile(
        r'(?P<month>[A-Za-z]{3})\s{1,3}(?P<day>\d{1,2})\s{1,2}(?P<ts>\d+:\d+:\d+).*to=<(?P<email>%s)' %
            '|'.join(emails))

with open("maillog.txt") as fh:
    for line in fh:
        for match in pattern.finditer(line):
            print(match.groupdict())

You can try with regex and capture the group :

Let's solve your solution in three steps :

Step first capturing all email address from email.txt :

emails=[]
    with open('emails.txt','r') as f:
        for line in f:
            emails.append(re.search(email_pattern,line).group())

Second step capturing needed data from data.txt:

with open('data.txt','r') as f:
        month_day=[[find.group(4) if find.group(4) != None else [find.group(1), find.group(2), find.group(3)] for find in re.finditer(pattern,line)]for line in f]

Third step : Now we have all the data , just check if that email in our data list then add that group info to dict:

for item in month_day:
        final_dict = {}
        if item[1] in emails:
            final_dict['month'] = item[0][0]
            final_dict['day'] = item[0][1]
            final_dict['ts'] = item[0][2]
            final_dict['email'] = item[1]
        if final_dict:
            print(final_dict)

Full code:

 import re
pattern='^(\w{0,3})\s.(\d)\s(\d.+?\s)|<(\w+[@]\w+[.]\w+)>'
email_pattern='\w+[@]\w+[.]\w+'

emails=[]
with open('emails.txt','r') as f:
    for line in f:
        emails.append(re.search(email_pattern,line).group())
with open('data.txt','r') as f:
    month_day=[[find.group(4) if find.group(4) != None else [find.group(1), find.group(2), find.group(3)] for find in re.finditer(pattern,line)]for line in f]


for item in month_day:
    final_dict = {}
    if item[1] in emails:
        final_dict['month'] = item[0][0]
        final_dict['day'] = item[0][1]
        final_dict['ts'] = item[0][2]
        final_dict['email'] = item[1]
    if final_dict:
        print(final_dict)

output:

{'ts': '10:08:43 ', 'month': 'Nov', 'email': '[email protected]', 'day': '3'}

Regex information :

^ asserts position at start of a line
\w{0,3} matches any word character (equal to [a-zA-Z0-9_])
\s matches any whitespace character (equal to [\r\n\t\f\v ])
\d matches a digit (equal to [0-9])