fetch any mailto email addresses found on a web page

README.md

basic script to extract any email addresses from a website that can be found

usage

get all emails you can find from this page:

http://zombierecords.com/staff

$   python3 findemails.py https://zombierecords.com/staff/
email,label
support@zombierecords.com,support@zombierecords.com
firefly@zombierecords.com,Contact
huttch@zombierecords.com,Contact
99ntt@zombierecords.com,Contact
badassmonkey@zombierecords.com,Contact
canadubstep@zombierecords.com,Contact
captainrevolution@zombierecords.com,Contact
choco@zombierecords.com,Contact
edlac@zombierecords.com,Contact
Hamptonkidd318@zombierecords.com,Contact
juggarnost@zombierecords.com,Contact
killerchaz@zombierecords.com,Contact
mashmanos@zombierecords.com,Contact
plasmidjeff@zombierecords.com,Contact
semtex@zombierecords.com,Contact
smarter@zombierecords.com,Contact
suzuki@zombierecords.com,Contact
tnegrao@zombierecords.com,Contact

findemails.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*- 
"""findemails.py

Usage:
    findemails URL [--output OUTPUT]

Arguments:
    URL                    Website from which you want to extract email addresses

Options:
    -o --output OUTPUT     [default: stdout].
    -h --help              Show this message.

Examples:
    findemails https://zombierecords.com/staff/
    findemails findemails.py https://zombierecords.com/staff/ --output zombie-emails.csv

"""

import os
import sys
from docopt import docopt
import requests
from bs4 import BeautifulSoup
import html5lib
import pandas as pd

def get_soup(url):
    r = requests.get(url)
    try:
        soup = BeautifulSoup(r.text, "html5lib")
    except Exception as err:
        sys.stderr.write(str(err))
        soup = None
    return soup

def find_emails(soup):
    emails = []
    for tag in soup.find_all("a"):
        link = tag.get('href','').strip()
        if link and link.startswith('mailto:'):
            email = link.split(':')[-1].strip()
            label = tag.get_text().strip()
            emails.append({"email": email, "label": label})
    return emails


def main():
    args = docopt(__doc__)
    url = args['URL']
    output = args['--output']
    soup = get_soup(url)
    if not soup:
        sys.stderr.write('couldnt access the URL provided')
        sys.exit(1)
    emails = find_emails(soup)
    if not emails:
        sys.stderr.write('couldnt find any emails')
        sys.exit(1)
    emails = pd.DataFrame(emails)
    if output == 'stdout':
        outfile = sys.stdout
    else:
        outfile = output
    emails.to_csv(outfile, index=False, encoding='utf-8')
    sys.exit(0)

if __name__ == '__main__':
    main()