python-31: 极视界大图爬取

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
__author__ = '217小月月坑'

'''
网页跳转，相册图片下载
下载大图片
'''

import urllib
import urllib2
import re
import os

# 极视界主页
home_url = 'http://product.yesky.com/more/506001_31372_photograph_1.shtml'
user_agent = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:40.0) Gecko/20100101 Firefox/40.0'
headers = {'User-Agent':user_agent}

try:
    home_request = urllib2.Request(home_url,headers=headers)
    home_response = urllib2.urlopen(home_request)
    home_conents = home_response.read().decode("gbk")
    # 使用RE在主页源码获取相册的网址和相册名字
    home_pattern = re.compile(r'<dt><a href="(.*?)" title="(.*?)"',re.S)
    # 返回存有相册的网址的列表
    album_urls = re.findall(home_pattern,home_conents)
    for album_url in album_urls:
        print album_url[0],album_url[1]
        # 以相册名字创建文件夹
        path = r'/home/ym/test/'+album_url[1]
        os.mkdir(path)
        # 传入相册网址
        album_response = urllib2.urlopen(album_url[0])
        album_conents = album_response.read().decode("gbk")
        album_pattern = re.compile(r'<li >.*?<a href="(.*?)".*?</li>',re.S)
        photo_urls = re.findall(album_pattern,album_conents)
        i = 1
        print u'正在下载'+album_url[1]+u'相册里的图片'
        for photo_url in photo_urls:
            photo_response = urllib2.urlopen(photo_url)
            photo_conents = photo_response.read().decode("gbk")
            photo_pattern = re.compile(r'class="effect".*?<img src="(.*?)"',re.S)
            img_urls = re.findall(photo_pattern,photo_conents)
            for img_url in img_urls:
                img_path = path+'/'+str(i)
                i+=1
                urllib.urlretrieve(img_url,img_path)
                print u'图片'+img_path+u'下载完成'
except urllib2.URLError,e:
    if hasattr(e,"code"):
        print e.code
    if hasattr(e,"reason"):
        e.reason