Python 爬虫（待改进）

#-*- coding: UTF-8 -*-
import urllib.request
import socket
import re
import sys
import os  


imagGetPath = "G:\\zxh_python\\Spider\\ImagesDown"
def saveFile(path):
    if not os.path.isdir(imagGetPath):
        os.mkdir(imagGetPath)
    
    pos = path.rindex(‘/‘)
    t = os.path.join(imagGetPath,path[pos+1:])
    return t


#网址  
url = "https://alpha.wallhaven.cc/random/"
headers = {‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)‘ ‘Chrome/59.0.3071.115 Safari/537.36‘}
#请求  
request = urllib.request.Request(url=url,headers=headers)  
#爬取结果  
response = urllib.request.urlopen(request)  
data = response.read()  
#saveFile(data) 
##设置解码方式
#data = data.decode(‘utf-8‘)
  
##打印结果
#print(data)
##打印爬取网页的各类信息
#print(type(response))
#print(response.geturl())
#print(response.info())
#print(response.getcode())
for link,t in set(re.findall(r‘(https?://[\w./]+\.(jpg|gif|png))‘, str(data))):
    print(link)
    try:
        urllib.request.urlretrieve(link,saveFile(link))
    except:
        print(‘失败‘)