python爬虫 之 抓取高清图片

#coding=utf-8
from urllib import request
import urllib
import re

url1 = "http://www.hbc333.com/size/2560x1600/"          #壁纸网站开始页面

def getMainPage(url):
    page = request.urlopen(url)
    html = page.read()
    return html

#每页的网址为：http://www.hbc333.com/size/2560x1600/n/    n为页数

count = 2
oriUrl = ‘http://www.hbc333.com‘
while count < 3:
    newUrl = url1 + str(count) + ‘/‘
    count  = count + 1
    print(newUrl)
    html = getMainPage(newUrl)
    print(html)
    dir = []
    html = html.decode(‘utf-8‘)  # python3
    dir = re.findall(r‘/data/out/[0-9]+/[0-9]+-[a-z]+-[a-z]+.jpg‘, html)
    #dir = re.findall(r‘/data/out/[0-9a-zA-Z]+‘, html)
    x = 1
    for u in dir:
        #urllib.request.urlretrieve(oriUrl+u,‘%s.jpg‘ %x)
        print(oriUrl+u)
        x = x+1