Extract email sub-strings from large document

If you’re looking for a specific domain:

>>> import re
>>> text = "this is an email [email protected], it will be matched, [email protected] will not, and [email protected] will"
>>> match = re.findall(r'[w-._+%][email protected]',text) # replace test.com with the domain you're looking for, adding a backslash before periods
>>> match
['[email protected]', '[email protected]']

You can also use the following to find all the email addresses in a text and print them in an array or each email on a separate line.

import re
line = "why people don't know what regex are? let me know [email protected], [email protected] " 
       "[email protected],[email protected]"
match = re.findall(r'[w.-]+@[w.-]+', line)
for i in match:
    print(i)

If you want to add it to a list just print the "match"

# this will print the list
    print(match)

Here’s another approach for this specific problem, with a regex from emailregex.com:

text = "blabla <[email protected]>><[email protected]> <huhu@fake> bla bla <[email protected]>"

# 1. find all potential email addresses (note: < inside <> is a problem)
matches = re.findall('<S+?>', text)  # ['<[email protected]>', '<[email protected]>', '<huhu@fake>', '<[email protected]>']

# 2. apply email regex pattern to string inside <>
emails = [ x[1:-1] for x in matches if re.match(r"(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+.[a-zA-Z0-9-.]+$)", x[1:-1]) ]
print emails   # ['[email protected]', '[email protected]', '[email protected]']

import re
rgx = r'(?:.?)([w-_+#~!$&'.]+(?<!.)(@|[ ]?(?[ ]?(at|AT)[ ]?)?[ ]?)(?<!.)[w]+[w-.]*.[a-zA-Z-]{2,3})(?:[^w])'
matches = re.findall(rgx, text)
get_first_group = lambda y: list(map(lambda x: x[0], y))
emails = get_first_group(matches)

Forgive me lord for having a go at this infamous regex. The regex works for a decent portion of email addresses shown below. I mostly used this as my basis for the valid chars in an email address.

Feel free to play around with it here

I also made a variation where the regex captures emails like name at example.com

(?:.?)([w-_+#~!$&'.]+(?<!.)(@|[ ](?[ ]?(at|AT)[ ]?)?[ ])(?<!.)[w]+[w-.]*.[a-zA-Z-]{2,3})(?:[^w])

import re 
txt = 'hello from [email protected] to [email protected] about the meeting @2PM'
email  =re.findall('S+@S+',s)
print(email)

Printed output:

['[email protected]', '[email protected]']

import re
with open("file_name",'r') as f:
    s = f.read()
    result = re.findall(r'S+@S+',s)
    for r in result:
        print(r)

import re
mess = '''[email protected] [email protected]
            abc@gmail'''
email = re.compile(r'([w.-][email protected])')
result= email.findall(mess)

if(result != None):
    print(result)

The above code will help to you and bring the Gmail, email only after calling it.

import re

reg_pat = r'S+@S+.S+'

test_text = '[email protected]    [email protected]   uiufubvcbuw bvkw  ko@com    m@urice'   

emails = re.findall(reg_pat ,test_text,re.IGNORECASE)
print(emails)

Output:

['[email protected]', '[email protected]']

You can use b at the end to get the correct email to define ending of the email.

The regex

[w.-]+@[w-.]+b

Example : string if mail id has (a-z all lower and _ or any no.0-9), then below will be regex:

>>> str1 = "[email protected]"
>>> regex1 = "^[a-z0-9]+[._]?[a-z0-9]+[@]w+[.]w{2,3}$"
>>> re_com = re.compile(regex1)
>>> re_match = re_com.search(str1)
>>> re_match
<_sre.SRE_Match object at 0x1063c9ac0>
>>> re_match.group(0)
'[email protected]'

content = ' abcdabcd [email protected]  afgh [email protected]  qwertyuiop [email protected]'

match_objects = re.findall(r'w+@w+[.w+]+', content)

#    b[w|.]+   ---> means begins with any english and number character or dot.

import re

marks = '''

!()[]{};?#$%:'",/^&é*

'''

text = 'Hello from [email protected] to [email protected], datascience@@gmail.com and machinelearning@@yahoo..com wrong email address: [email protected]'
# list of sequences of characters:
text_pieces = text.split()
pattern = r'b[a-zA-Z]{1}[w|.]*@[w|.]+.[a-zA-Z]{2,3}$'
for p in text_pieces:
  for x in marks:
    p = p.replace(x, "") 
  if len(re.findall(pattern, p)) > 0:
    print(re.findall(pattern, p))

One other way is to divide it into 3 different groups and capture the group(0). See below:

emails=[]
for line in email: # email is the text file where some emails exist. 
    e=re.search(r'([.wd-]+)(@)([.wd-]+)',line) # 3 different groups are composed. 
    if e:
        emails.append(e.group(0))

print(emails)