本文共 1644 字，大约阅读时间需要 5 分钟。

?????????????HTML????????????????Windows 7???Python 3.5.2??????????????

????<??>string<??>???????string???????????

import re
p = re.compile(r'
   
   
   
    
    (.*)
    
   
   ')
matchp = p.search("
   
   
   
    
    positive
    
   
   ")
if matchp:
    print(matchp.group(1))  # ????
    print(matchp.group(0))  # ?????

???????matchp.group(1) ???? "positive"?? matchp.group(0) ?????????

???????????

???????HTML????????????????????????

?????<??>string<??>???????string???????????

import re
p = re.compile(r'
   
   
   
    
    (.*)
    
   
   ')
matchp = p.search("
   
   
   
    
    positive
    
   
   ")
if matchp:
    print(matchp.group(1))  # ????
    print(matchp.group(0))  # ?????

???????matchp.group(1) ???? "positive"?? matchp.group(0) ?????????

???????????

?????

???????HTML???????????????????????????????????????????????????????

import re
p = re.compile(r'
   
   
   
    
    (.*)
    
   
   ')
matchp = p.search("
   
   
   
    
    positive
    
   
   ")
if matchp:
    print(matchp.group(1))  # ????
    print(matchp.group(0))  # ?????

?????

positive
   
   
   
    
    positive
    
   
   

???

????????????????

?????

???????????????????????????????? .* ??????????????????????????HTML??????? <div> ???????????????????

????????????????

import re
p = re.compile(r'
   
    (.*?)
   ', re.DOTALL)
matchp = p.search("
   
   
   
        positive    
   ")
if matchp:
    print(matchp.group(1))  # ??????????

????????? r'<polarity>(.*?)</polarity>' ??? re.DOTALL flag??? . ????????????????????????????????

???

??????????????????????????????????????????????????????

转载地址：http://bszc.baihongyu.com/