Python爬虫之正则表达式的使用教程详解

import re
content ='hello 123456 World_This is a Regex Demo'
print(len(content))
result = re.match('^hello\s\d{6}\s\w{10}.*Demo$$',content)
print(result)
print(result.group()) #返回匹配结果
print(result.span()) #返回匹配结果的范围

import re
content ='hello 123456 World_This is a Regex Demo'
result = re.match('^hello.*Demo$',content)
print(result)
print(result.group())

import re
content ='hello 123456 World_This is a Regex Demo'
result = re.match('^hello\s(\d{6})\s.*Demo$',content)
print(result)
print(result.group(1))#获取匹配目标

import re
content ='hello 123456 World_This is a Regex Demo'
result = re.match('^he.*(\d+).*Demo$',content)
print(result)
print(result.group(1))

import re
content ='hello 123456 World_This is a Regex Demo'
result = re.match('^he.*?(\d+).*Demo$',content)
print(result)
print(result.group(1))　

import re
content ='hello 123456 World_This ' \
'is a Regex Demo'
result = re.match('^he.*?(\d+).*?Demo$',content,re.S)
print(result)
print(result.group(1))

import re
content = 'price is $5.00'
result = re.match('^price.*\$5\.00',content)
print(result.group())

re.search(pattern,string,flags=0)

import re
content ='hello 123456 World_This is a Regex Demo'
result = re.match('\d{6}',content)
print(result)
import re
content ='hello 123456 World_This is a Regex Demo'
result = re.search('\d{6}',content)
print(result)
print(result.group())

import re
content = '2009年中信出版社出版图书'
result = re.search('(.*?)',content)
print(result.group(1))
2009年中信出版社出版图书
re.findall(pattern,string,flags=0)

import re
html ='''

网络歌曲


2009年中信出版社出版图书

'''
result = re.findall('(.*?)',html,re.S)
count = 0
for list in result:
  print(result[count])
  count+=1
网络歌曲
2009年中信出版社出版图书
re.sub( pattern，repl，string，count，flags)

import re
content = 'hello 123456 World_This is a Regex Demo'
content = re.sub('\d+','',content)
print(content)

import re
html ='''

网络歌曲


2009年中信出版社出版图书

'''
html = re.sub('
|
','',html)
print(html)

网络歌曲
2009年中信出版社出版图书
compile(pattern [, flags])

import re
content = 'hello 123456 ' \
'World_This is a Regex Demo'
pattern = re.compile('hello.*?Demo',re.S)
result = re.match(pattern,content)
print(result.group())　

import re
html = '''

    
      

        
      
      

        解除好友2：暗网
          7.9
      
    
    
      

        
      
      

        镰仓物语
          6.9
      
    
    
      

        
      
      

        特工
          8.3
      
    
    
      

        
      
      

        幸福的拉扎罗
          8.6
      
    
    
      

        
      
      

        大师兄
          5.2
      
    
    
      

        
      
      

        风语咒
          6.9
      
    
    
      

        
      
      

        精灵旅社3：疯狂假期
          6.8
      
    
    
      

        
      
      

        狄仁杰之四大天王
          6.2
      
    
    
      

        
      
      

        摩天营救
          6.4
      
    
    
      

        
      
      

        复仇者联盟3：无限战争
          8.1
      
    
  
'''
count = 0
for list in result:
  print(result[count])
  count+=1