python爬取网页图片

# html:网页地址
def getImg2(html):
    soup = BeautifulSoup(html, 'html.parser')
    href_regex = re.compile(r'^http.*?(jpg|png)')
    imgurlset = set()
    item = soup.find_all('img', {'data-original': href_regex})
    for a in item:
        if 'data-original' in a.attrs:
            imgurlset.add(a.attrs['data-original'])
    x = 0    
    for url in imgurlset:
        print(url)
        # 下载图片
        urllib.request.urlretrieve(url, 'F:\\img\\%s.jpg' % x)
        x += 1

 

转载于:https://www.cnblogs.com/luoluosha/p/10950297.html