requests+正则爬取豆瓣图书

 #requests+正则爬取豆瓣图书
 
 import requests
 import re
 
 def get_html(url):
     headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36 LBBROWSER'}
     response = requests.get(url,headers=headers)
     html = response.text
     return html
 
 def get_books(url):
 
     html = get_html(url)
     pattern = re.compile(r'<li.*?cover.*?href="(.*?)".*?title="(.*?)".*?more-meta.*?author">(.*?)</span>.*?year">(.*?)</span>.*?</li>',re.S)
     result = re.findall(pattern,html)
     for rs in result:
         link,book,name,data = rs
         book = re.sub('\s','',book)#可用sub去掉换行空白等
 
         print(link,book,name.strip(),data.strip())#也可用strip去掉换行空白
 
 if __name__ == '__main__':
 
     url = 'https://book.douban.com/'
     get_books(url)