Ben New

from extract_emails import ExtractEmails
from email.utils import parseaddr
import re
import cloudscraper
from bs4 import BeautifulSoup



def getEmail(source):
    e_mails =parseaddr(source)
    e_mails = [e for e in e_mails if "@" in e]
    print(e_mails)



def getEmail(url):
    em = ExtractEmails("https://carealestate.herokuapp.com", depth=7)

    return em.emails





def getPhone(source):
    phones_array = []
    phones = re.findall(r'[\+\(]?[0-9][0-9 .\-\(\)]{8,}[0-9]', source)

    prefixes = ["1300", "1800",
    "02", "03", "04", "05", "07", "08",
    "612", "613", "614", "615", "617", "618"]

    for prefix in prefixes:
        for phone in phones:
            if phone.startswith(str(prefix)) and len(phone.strip().replace(" ", "").strip()) <= 13 and phone.strip().replace(" ", "").strip().isnumeric():
                phones_array.append(phone)

    return phones_array



#em = ExtractEmails("https://carealestate.herokuapp.com", depth=1)

#print(em.emails)


'''
Source = <p><strong>Kuala Lumpur</strong><strong>:</strong> +60 (0)3 2723 7900</p>
        <p><strong>Mutiara Damansara:</strong> +60 (0)3 2723 7900</p>
        <p><strong>Penang:</strong> + 60 (0)4 255 9000</p>
        <h2>Where we are </h2>
        <strong>&nbsp;Call us on:</strong>&nbsp;+6 (03) 8924 8686
        </p></div><div class="sys_two">
    <h3 class="parentSchool">General enquiries</h3><p style="FONT-SIZE: 11px">
     <strong>&nbsp;Call us on:</strong>&nbsp;+6 (03) 8924 8000
+ 60 (7) 268-6200 <br />
 Fax:<br />
 +60 (7) 228-6202<br />
Phone:</strong><strong style="color: #f00">+601-4228-8055</strong>

'''



scraper = cloudscraper.CloudScraper(browser="chrome")


#url = "https://www.softwaretestinghelp.com/email-service-providers/amp/"


url = "https://aaa.edu.au"


r = scraper.get(url)


soup = BeautifulSoup(r.text, "html.parser")

Source = str(soup)

print(getPhone(Source))