requests bs4 爬取 资讯 图片

#!/usr/bin/env python
# Version = 3.5.2
# __auth__ = '无名小妖'
import requests
from bs4 import BeautifulSoup
import uuid


response = requests.get(
    url='http://www.autohome.com.cn/news/'
)
response.encoding = response.apparent_encoding  # 使用原页面的编码进行解析
# response.status_code 状态码
# 将页面字符串转化成bs对象，features 是转化方式，此处用的html.parser，而生产中用的是lxml，性能较好
soup = BeautifulSoup(response.text, features='html.parser')
# 获取id为'auto-channel-lazyload-article' 的标签
target = soup.find(id='auto-channel-lazyload-article')
# 在此标签下找到所有的li标签
li = target.find_all('li')
# 获取每个li标签下的a标签
for i in li:
    a = i.find('a')
    if a:
        # print(a.attrs.get('href'))
        txt = a.find('h3').text
        # 获取图片的地址
        img_url = a.find('img').attrs.get('src')
        if not img_url.startswith("http:"):
            img_url = "http:" + img_url
        # 下载图片
        img_response = requests.get(url=img_url)
        h = img_url.split('.')
        jpg_name = '{}.{}'.format(uuid.uuid4(), h[-1])
        with open(jpg_name, 'wb') as f:
            f.write(img_response.content)

　　

 

转载于:https://www.cnblogs.com/wumingxiaoyao/p/8528906.html