|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- import urllib.request
- import re
- def open_url(url):
- req = urllib.request.Request(url)
- req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36')
- page = urllib.request.urlopen(req)
- html= page.read().decode('utf-8')
- return html
- def get_img(html):
- p = r'<img src="([^"]+\.gif)" style='
- imglist = re.findall(p, html)
- for each in imglist:
- print(each)
- for each in imglist:
- filename = each.split("/")[-1]
- urllib.request.urlretrieve(each, filename, None)
-
- if __name__ =='__main__':
- url = 'https://tieba.baidu.com/p/2125145202?fid=8740&red_tag=3527456532#!/l/p1'
- get_img(open_url(url))
复制代码
|
|