Python Regular expressions 正则表达式学习笔记

//search lines that start with the string “From:”

import re
hand = open(‘mbox-short.txt‘)
for line in hand:
　　line = line.rstrip()
　　if re.search(‘ˆFrom:‘, line) :
　　　　print line

// match any of the strings “From:”, “Fxxm:”, “F12m:”, or “[email protected]:”

1 import re
2 hand = open(‘mbox-short.txt‘)
3 for line in hand:
4     line = line.rstrip()
5     if re.search(‘ˆF..m:‘, line) :
6         print line    

//search lines that start with “From:”, followed by one or more characters (“.+”), followed by an at-sign

1 import re
2 hand = open(‘mbox-short.txt‘)
3 for line in hand:
4     line = line.rstrip()
5     if re.search(‘ˆFrom:[email protected]‘, line) :
6         print line    

//uses findall() to find the lines with email addresses in them,

1 import re
2 s = ‘Hello from [email protected] to [email protected] about the meeting @2PM‘
3 lst = re.findall(‘\[email protected]\S+‘, s)
4 print lst

The output of the program would be:[‘[email protected]‘, ‘[email protected]‘]
 The “\S+” matches as many non-whitespace characters as possible.