小例题-爬取汽车之家资讯

1、https://www.autohome.com.cn/news/1/#liststart
　　检查代码

2、爬取代码

#爬取的地址
# https://www.autohome.com.cn/news/1/#liststart
from bs4 import BeautifulSoup
import requests
url='https://www.autohome.com.cn/news/1/#liststart'
res = requests.get(url)

# 生成一个bs4对象

soup=BeautifulSoup(res.text,'lxml')

div = soup.find(id='auto-channel-lazyload-article')
# div 是个对象

ul=div.find(name='ul')

li_list = ul.find_all(name='li')
for li in li_list:
    h3 = li.find(name='h3')
    if h3:
        title = h3.text
        print(title)

    img = li.find(name='img')
    if img:
        img_url = img.get('src')
        print(img_url)

    a = li.find(name='a')
    if a:
        article_url = a.get('href')
        print(article_url)

    p = li.find(name='p')
    if p:
        content = p.text
        print(content)

3、爬取结果