python脚本练习（3）:正则表达式实例

>>> text
'Got It\r\nThis website usesCOOKIEs to improve your experience. Learn More\r\nSkip to maincontent\r\n
Home\r\nSearch form\r\nSearch\r\nCatalog\r\nBlog\r\nMedia\r\nWritefor Us\r\nAbout Us\r\nContact Us\r\n
We are currently shipping with some delays.Please see our FAQ.\r\n\r\nTopics\r\nArt & Design\r\nGeneralComputing\r\nHacking & Computer Security\r\n
Hardware /DIY\r\nKids\r\nLEGO®\r\nLinux &BSD\r\nManga\r\nProgramming\r\nPython\r\n
Science & Math\r\nScratch\r\nSystemAdministration\r\nEarly Access\r\nFree ebook edition with every print bookpurchased from nostarch.com!\r\nShopping cart\r\n
0 Items\tTotal: $0.00\r\nUserlogin\r\nLog in\r\nCreate account\r\nContact Us\r\n\r\n
No Starch Press,Inc.\r\n245 8th Street\r\nSan Francisco, CA 94103 USA\r\nPhone: 800.420.7240 or+1 415.863.9900 (9 a.m. to 5 p.m., M-F, PST)\r\nFax: +1415.863.9950\r\n\r\n
Reach Us by Email\r\n\r\nGeneral inquiries:info@nostarch.com\r\n
Media requests: media@nostarch.com\r\nAcademic requests:academic@nostarch.com (Further information)\r\nHelp with your order:info@nostarch.com\r\nReach Us on SocialMedia\r\nTwitter\r\nFacebook\r\nInstagram\r\nLinkedin\r\nPinterest\r\n\r\n
Navigation\r\nMyaccount\r\nWant sweet deals?\r\nSign up for our newsletter.\r\n\r\n\r\nAboutUs  | Jobs!  |  Sales and Distribution  | Rights  |  Media |  Academic Requests  | Conferences  |  FAQ |  Contact Us  | Write for Us  |  Privacy\r\n
Copyright 2020. No Starch Press,Inc\r\n\r\n'

# Create phone regex.
phoneRegex = re.compile(r'''(
(\d{3}|\(\d{3}\))? # area code
(\s|-|\.)? # separator
(\d{3}) # first 3 digits
(\s|-|\.) # separator
(\d{4}) # last 4 digits
)''', re.VERBOSE)

# Create email regex.
emailRegex = re.compile(r'''(
[a-zA-Z0-9._%+-]+ # username
@ # @ symbol
[a-zA-Z0-9.-]+ # domain name
(\.[a-zA-Z]{2,4}){1,2} # dot-something
)''',re.VERBOSE)

matches = []
for groups in phoneRegex.findall(text):
matches.append(groups[0])

>>>phoneRegex.findall(text)
[
('800.420.7240','800', '.', '420', '.', '7240'),
('415.863.9900','415', '.', '863', '.', '9900'),
('415.863.9950','415', '.', '863', '.', '9950')]

>>> matches
['800.420.7240', '415.863.9900','415.863.9950']

for groups in emailRegex.findall(text):
matches.append(groups[0])

if len(matches) > 0:
print('\n'.join(matches))
else:
print('No phone numbers or email addressesfound.')

800.420.7240
415.863.9900
415.863.9950
info@nostarch.com
media@nostarch.com
academic@nostarch.com
info@nostarch.com