Extracting Email IDs from a Html Page using Beautiful Soup, html2text, Regular Expression https://bigdatacv.com/currentjobs/

extract_email_currentjobs.py

import requests
from bs4 import BeautifulSoup
r = requests.get("https://bigdatacv.com/currentjobs/")
content = r.text
soup = BeautifulSoup(content, 'html.parser')
print(soup.prettify())

[s.extract() for s in soup('script')]
[s.extract() for s in soup('style')]
[s.extract() for s in soup('img')]
[s.extract() for s in soup('a')]
print(soup.text)

import html2text
text = html2text.html2text(soup.prettify())
print(text)

import re
# Code from https://github.com/fredericpierron/extract-email-from-text-python-3/
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 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://[email protected]' as '//[email protected]'.
    return (email[0] for email in re.findall(regex, s) if not email[0].startswith('//'))

for email in get_emails(text):
    print (email)