爬取汽车之家新闻首页数据

1 import requests
2 res=requests.get('https://www.autohome.com.cn/news/1/#liststart').text
3 print(res)

import bs4
import requests
from bs4 import BeautifulSoup
import pymysql
conn = pymysql.connect(
    user='root',
    password="123456",
    host='127.0.0.1',
    database='news'
)
cursor = conn.cursor()
for i in range(100):
    res = requests.get('https://www.autohome.com.cn/news/%s/#liststart'%i)
    soul = BeautifulSoup(res.text, 'lxml')
    #查询所有ul标签，class=article的元素
    ul_list = soul.find_all(name='ul', class_='article')
    for ul in ul_list:
        #查询出ul标签下所有li元素
        li_list = ul.find_all(name='li')
        for li in li_list:
            # 查询li标签下的h3标签
            title = li.find(name='h3')
            # 因为有广告的存在，做一层判断过滤广告
            if title:
                title = title.text
                desc = li.find(name='p').text
                address = 'https:' + li.find(name='a').attrs.get('href')
                img = li.find(name='img').attrs.get('src')
                print(title)
                # 存入数据库
                cursor.execute('insert into news (title,img,address,`desc`) values (%s,%s,%s,%s)', args=[title, img, address, desc])
                conn.commit()