爬取百度贴吧图片
import urllib.request
import re
def url_open(url):
req = urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36')
response = urllib.request.urlopen(req)
html = response.read().decode('utf-8')
return html
def get_page(html):
p = r'<img class="BDE_Image" src="([^"]+\.jpg)"'
imglist = re.findall(p,html)
for each in imglist:
filename = each.split("/")[-1]
urllib.request.urlretrieve(each,filename,None)
if __name__ == '__main__':
url = "https://tieba.baidu.com/p/3385100879"
get_page(url_open(url))