yeukhon / re_problem.py

Last active August 29, 2014


    
    View re_problem.py 
  
  
      re_problem.py
    
    
        Raw
      
    
    File suppressed. Click to show.
  
  
            1
            2
            3
            4
            5
            6
            7
            8
            9
            10
            11
            12
            13
            14
            15
            16
            17
            18
            19
            20
            21
            22
            23
            24
            25
            26
            27
            28
            29
          
          
            import re
text1 = "alphanumeric@example.org"
text2 = "alphanumeric@long.subdomain.more.subdomain.domain.org"
 
r1 = re.compile(r'[a-zA-Z0-9]+@[a-zA-Z]+\.[a-zA-Z]+(\.[a-zA-Z]+)*')
 
print(r1.match(text1).group())
print(r1.match(text2).group())
 
print("part 2 - compare with and without (?:")
r2 = re.compile(r'[a-zA-Z0-9]+@[a-zA-Z]+\.[a-zA-Z]+(?:\.[a-zA-Z]+)*')
 
print(r1.findall(text2))
print(r2.findall(text2))
 
print("part 3 - udacity assignment")
 
def addresses(haystack): 
    emails = re.findall(r'\w+@[a-zA-Z]+\.[a-zA-Z]+(?:\.[a-zA-Z]+)*', haystack)
    return [re.sub("NOSPAM", "", email) for email in emails]
 
input1 = """louiseNOSPAMaston@germany.de (1814-1871) was an advocate for
democracy. irmgardNOSPAMkeun@NOSPAMweimar.NOSPAMde (1905-1982) wrote about
the early nazi era. rahelNOSPAMvarnhagen@berlin.de was honored with a 1994
deutsche bundespost stamp. seti@home is not actually an email address."""
 
output1 = ['louiseaston@germany.de', 'irmgardkeun@weimar.de', 'rahelvarnhagen@berlin.de']
 
print addresses(input1) == output1