贴吧地址
https://tieba.baidu.com/p/5272413637?red_tag=0606091703
程序如下
import urllib.request
import re
def open_url(url):
req = urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36')
page = urllib.request.urlopen(req)
html = page.read().decode('utf-8')
return html
def get_img(html):
p = r'<img class="BDE_Image" src="([^"]+\.jpg)"'
imglist = re.findall(p, html)
for each in imglist:
file_name = each.split('/')[-1]
urllib.request.urlretrieve(each, file_name)
if __name__ == '__main__':
url = 'https://tieba.baidu.com/p/5272413637?red_tag=0606091703'
get_img(open_url(url))
执行程序结果