爬虫-正则表达式

 

 

 

 

import requests
import re

content =  requests.get('https://book.douban.com').text
#partten = re.compile('<li.*?cover.*?href="(.*?)".*?title="(.*?)".*?</li>',re.S)
partten = re.compile('<li.*?cover.*?title="(.*?)".*?more-meta.*?author">(.*?)</span>.*?year">(.*?)</span>.*?</li>',re.S)
results = re.findall(partten,content)
for result in results:
    name,author,date = result
    #author = re.sub('\s','',author)
    #date = re.sub('\s','',date)
    print(name,author.strip(),date.strip())