RegexLesson.py

RegexLesson.py

"""
The regular expressions operations module (re) is a standard Python
library.  It is beautiful collection of operations for finding and manipulating 
matched text.  
This program use the re library to search the text in a file, regex.txt, for email addresses and phone numbers.  It copies
them to a list called matches and prints then them neatly in a standard format.  The program has a string call text that 
is commented out.   Use the program by saving some text in a file called regex.txt. Or use the string call text.   Comment out the code for the part you don't use.

The program is a slight modification of a program found at: 
https://automatetheboringstuff.com/chapter7/
See also the documentation at Python.org for the re library (regular expression operations) here:
    https://docs.python.org/3/library/re.html#re.ASCII
"""
import re
import os


# Use this code if you want to save the text you woild like to search to a file before you run the program.
# with open('regex.txt') as f1: text=f1.read()
 
"""
Use the string called text for the program  instead of reading a text file from the local current working directory.
"""

text =  'This text file contains a few emails addresses and phone numbers. Alex\'s is home number is 813-123-4567. He has two email addresses [email protected] and [email protected]. Gregory has two phone nunbers:  (cell) (813) 685-1234 and work 253-7000 ext. 1234. His email address is [email protected].'

# Create a regex for matching emails.
emailRegex = re.compile(r'''(
    [a-zA-Z0-9._%+-]+      # username
     @                      # @ symbol
    [a-zA-Z0-9.-]+         # domain name
    (\.[a-zA-Z]{2,4})      # dot-something
    )''', re.VERBOSE)
    
# Create a regex for matching phone numbers and identify 
# the parts of a phone number.
phoneRegex = re.compile(r'''(
    (\d{3}|\(\d{3}\))?    # area code
    (\s|-|\.)?            # separator
    (\d{3})               # first 3 digits
    (\s|-|\.)             # separator
    (\d{4})               # last 4 digits
    (\s*(ext|x|ext.)\s*(\d{2,5}))?    # extension
    )''', re.VERBOSE)
    
# Any text in the file which has a typical email or phone number will be added to the list matches.
matches = []
for groups in phoneRegex.findall(text):
       # This code reformats the phone number in a standard way by using
       # the blocks identified when the number was matched to the regex.
       phoneNum = '-'.join([groups[1], groups[3], groups[5]])
       if groups[8] != '':
           phoneNum += ' x' + groups[8]
       matches.append(phoneNum)
for groups in emailRegex.findall(text):
       matches.append(groups[0])
    
# Neatly prints out emails and phone numbers found 
# in the regex.txt file.
if len(matches) > 0:
    print('\n'.join(matches))
else:
    print('No phone numbers or email addresses found.')