import os
from urllib.request import urlretrieve
from urllib.request import Request, urlopen
import bs4
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')
# allinfos=bs.find_all('article', {'class': "article"})
i=1
for link in bs.find('article',{'class':{'article'}}).find_all('img'):
links=link.attrs['src']
# url1=links
dir=os.path.abspath('C:\\Users\\user\\PycharmProjects\\pythonProject\\pict\\')
work_path=os.path.join(dir,str(i)+'.jpg')
urlretrieve(links,work_path)
i+=1
爬取图片并下载
最新推荐文章于 2023-10-22 12:00:00 发布