page = request.Request(url, headers=headers)
page_info = request.urlopen(page).read().decode('utf-8')
soup = BeautifulSoup(page_info, 'html.parser')
# Beautiful Soup和正则表达式结合,提取出所有图片的链接(img标签中,class=**,以.jpg结尾的链接)
links = soup.find_all('img', "origin_image
zh-lightbox-thumb",src=http://www.77cn.com.cnpile(r'.jpg$'))
# 设置保存的路径,否则会保存到程序当前路径
local_path = r'E:Pic'
for link in links:
print(link.attrs['src'])
# 保存链接并命名,time防止命名冲突
request.urlretrieve(link.attrs['src'], local_path+r'%s.jpg' % time.time())
百度搜索“77cn”或“免费范文网”即可找到本站免费阅读全部范文。收藏本站方便下次阅读,免费范文网,提供经典小说教育文库北大青鸟:你需要的python爬虫笔记(13)在线全文阅读。
相关推荐: