Python 爬虫_正则表达式

1. re.match ==>尝试从字符串的起始位置匹配一个模式，如果第一个字符不嫩匹配，则不能正常匹配
        re.match(pattern,sring,flags=0)

import re
        content=‘Hello 1234567 world_this is a regex demo‘
        result=re.match(‘^Hello\s(\d+)\sworld.*demo$‘,content)    #正则表达式
        print(result.group(1))    #输出第一个括号的内容
        print(result.span())     #输出输出字符串的数量

import re
        content=‘Hello 1234567 world_this is a regex demo‘
        result=re.match(‘^He.*(\d+)\sworld.*demo$‘,content)    
        print(result.group(1))    #只能输出7

#非贪婪匹配
        import re
        content=‘Hello 1234567 world_this is a regex demo‘
        result=re.match(‘^He.*?(\d+).*demo$‘,content)    
        print(result.group(1))     #输出1234567

#匹配模式：
        import re
        content=‘‘‘Hello 1234567 world_this 
        is a regex demo
        ‘‘‘
        result=re.match(‘^He.*?(\d+).*?demo$‘,content,re.s)    #re.s 是匹配换行符的
        print(result.group(1))    #输出1234567

import re
        content=‘price is $500‘
        result=re.match(‘price is \$500\‘,content)     #转义之后才能匹配

import re
        content=‘Hello 1234567 world_this is a regex demo‘
        result=re.search(‘Hello\s(\d+)\sworld.*demo$‘,content)     #输出全部字符串

results=re.findall(‘正则表达式‘,html,re.S)
        for result in results:
        print(result)
        print(result[1],result[2]...)

import re
        content=‘Hello 1234567 world_this is a regex demo extra stings‘
        content=re.sub(‘\d+‘,‘‘,content)

import re
        content=‘‘‘Hello 1234567 world_this 
        is a regex demo
        ‘‘‘
        result=re.compile(‘hello.*demo‘,re.s)    #re.s 是匹配换行符的
        result=re.match(pattern,content)

#实战练习：
        import requests
        import re
        content=requests.get(‘http://book.doubancom/‘).text
        patten=re.compile(‘<li,*cover.*?href="(.*?)".*?title="(.*?)".*?more-meta.*?author>(.*?)</span>.*?year>(.*?)</span>.*?</li>‘,re.S)
        results=re.findall(pattern.content)
        #print (results)
        for result in results
            url, name,author,date=result
            author=re.sub(‘\s‘,‘‘,author)
            date=re.sub(‘\s‘,‘‘,date)
            print(url,name,author,date)