import urllib.request
import socket
import re
import sys
import os
targetDir = r"E:\\DATA\常用py脚本"
def destFile(path):
if not os.path.isdir(targetDir):
os.mkdir(targetDir)
pos = path.rindex('/')
t = os.path.join(targetDir, path[pos+1:])
return t
if __name__ == "__main__":
hostname = "http://www.douban.com"
req = urllib.request.Request(hostname)
webpage = urllib.request.urlopen(req)
html = webpage.read()
#\s:任意空白字符
#^：匹配字符串的开头
#*:匹配前一个字符0次或无数次
#?:匹配前一个字符0次或1次
result=re.findall(r'(https:[^\s]*?(jpg|png|gif))', str(html))
#print(result)
for link, t in result:
#print(link,t)
urllib.request.urlretrieve(link, destFile(link)) 最佳答案
