爬虫 图片下载

爬取搜狐列维坦图片并下载

import os
from urllib.request import urlretrieve
from urllib.request import Request, urlopen
import bs4

s = 1
url='https://www.sohu.com/a/286956359_301394'
header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}
ret = Request(url=url, headers=header)
html = urlopen(ret)
bs = bs4.BeautifulSoup(html, 'html.parser')
alls = bs.find('article',{'class':{'article'}}).find_all('img')
for all in alls:
    links=all.attrs['src']
    dir = os.path.abspath('D:\\pictures')
    work_path = os.path.join(dir, str(s)+'.jpeg')
    urlretrieve(links, work_path)
    s += 1