爬虫一

 1 #! /usr/bin/env python
 2 # encoding: utf-8
 3 
 4 from bs4 import BeautifulSoup
 5 import requests
 6 
 7 
 8 response = requests.get("http://www.autohome.com.cn/news/")  
 9 # response.text
10 response.encoding = response.apparent_encoding  # 解决爬虫乱码
11 
12 soup = BeautifulSoup(response.text, features="html.parser")  # 生成Soup对象
13 soup_obj = soup.find(id="auto-channel-lazyload-article")  # find查找第一个符合条件的对象
14 
15 li_list = soup_obj.find_all("li")  # find_all查找所有符合的对象，查找出来的值在列表中
16 # print(target)
17 for i in li_list:
18     a = i.find("a")
19     if a:
20         a_attrs = a.attrs.get("href")  # attrs查找属性
21         print(a_attrs)
22         a_h = a.find("h3")
23         print(a_h)
24         img = a.find("img")
25         print(img)