Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
A python script for extracting email addresses from text files.You can pass it multiple files. It prints the email addresses to stdout, one address per line.For ease of use, remove the .py extension and place it in your $PATH (e.g. /usr/local/bin/) to run it like a built-in command.
#!/usr/bin/env python
#
# Extracts email addresses from one or more plain text files.
#
# Notes:
# - Does not save to file (pipe the output to a file if you want it saved).
# - Does not check for duplicates (which can easily be done in the terminal).
#
# (c) 2013 Dennis Ideler <ideler.dennis@gmail.com>
from optparse import OptionParser
import os.path
import re
regex = re.compile(("([a-z0-9!#$%&'*+\/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+\/=?^_`"
"{|}~-]+)*(@|\sat\s)(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?(\.|"
"\sdot\s))+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?)"))
def file_to_str(filename):
"""Returns the contents of filename as a string."""
with open(filename) as f:
return f.read().lower() # Case is lowered to prevent regex mismatches.
def get_emails(s):
"""Returns an iterator of matched emails found in string s."""
# Removing lines that start with '//' because the regular expression
# mistakenly matches patterns like 'http://foo@bar.com' as '//foo@bar.com'.
return (email[0] for email in re.findall(regex, s) if not email[0].startswith('//'))
## desinence filter
def emailFilter(s):
if s.endswith('.it'):
f = "ok"
else:
f = "no"
return f
if __name__ == '__main__':
parser = OptionParser(usage="Usage: python %prog [FILE]...")
# No options added yet. Add them here if you ever need them.
options, args = parser.parse_args()
if not args:
parser.print_usage()
exit(1)
for arg in args:
if os.path.isfile(arg):
for email in get_emails(file_to_str(arg)):
filter = emailFilter(email)
if filter=="ok":
print email
else:
print '"{}" is not a file.'.format(arg)
parser.print_usage()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.