# Write a function that finds all phone numbers from
# http://www.virginia.edu/contact

# The function then returns a list of all phone numbers
# in the area code 434.
# If the same phone number appears multiple times,
# only one should be reported.

# For practice purposes, you should create 2 versions of your solutions.
# One version reads a file from the internet;
# one version reads a file from your computer (locally).

import re
import urllib.request

def findPhoneNumber(url):

    phone_list = []

    # Define regular expression patter that describes
    # phone number in area code 434.
    # Create a regular expression object.
    regex = re.compile(r'(\(434\) [0-9]{3}-[0-9]{4})')

    stream = urllib.request.urlopen(url).read().decode('UTF-8')

    matches = regex.finditer(stream)
    for match in matches:
        if match.group() not in phone_list:
            phone_list.append(match.group())

    return phone_list

url = "http://www.virginia.edu/contact"
print(findPhoneNumber(url))

##########################
# Challenging: (not be in Fall 2018 final exam)
# Write another function to extract the urls from the hyperlinks
# for example,
#    a url to African-American Affairs, Office of
#       is http://oaaa.virginia.edu/
#    a url to Financial Aid is
#       http://sfs.virginia.edu/
# and store them in a list of links









##########################
# Even more challenging: (not be in Fall 2018 final exam)
# Modify your findHyperlink(url) function such that
# the urls and link texts are stored in
# a dictionary, where url is a key
# and the associated link text is a value