使用requests庫和re庫來爬取豆瓣圖書首頁的圖書資訊 

import requests
import re

content = requests.get("http://book.douban.com").text    #get函式獲取豆瓣圖書網頁程式碼
pattern = re.compile('<li.*?cover.*?href="(.*?)".*?alt="(.*?)".*?author">(.*?)<',re.S)    #complip函式儲存正則式
result = re.findall(pattern,content)    #findall尋找符合正則式的資訊
for results in result:
    url,name,author = results
    url = re.sub('\s',' ',url)    #將換行符轉換為空格
    name = re.sub('\s',' ',name)
    author = re.sub('\s','',author)
    print(url,name,author)
 

爬取結果: