#!/usr/bin/env python
#! -*- coding: utf-8 -*-
#图片地址样例:src="http://ww2.sinaimg.cn/large/005Yan1vjw1erf95qkbfog307e08uu0y.gif" style="width:460px"
import urllib,urllib2
import re
#返回网页源代码
def getHtml(url, page):
    tempUrl = url + str(page)
    print tempUrl
    html = urllib2.urlopen(tempUrl)
    srcCode = html.read()
    return srcCode

def getImg(url, start_page, end_page):
    #对网页中图片建立正则
    pattern = re.compile(r'src="(.*?\.gif)".*?style="width:460px"')
    for x in xrange(start_page, end_page+1):
        srcCode = getHtml(url,x)
        #图片完整路径存储为list
        imgSrc = pattern.findall(srcCode)
        num = 0
        for i in imgSrc:
            urllib.urlretrieve(i,'P%s0%s.gif' %(x ,num))
            num += 1
            print "正则下载"
            print i
    print '全部任务完成!'


#----------- 程序的入口处 -----------
print u"""
程序开始运行
#=========================================================
#   程序：暴漫爬虫
#   版本：V0.1
#   作者：江前云后
#   语言：Python 2.7
#   操作：输入要下载的暴漫gif的页码范围，自动下载所有gif图
#=========================================================
"""
#测试url
myUrl = 'http://baozoumanhua.com/gif/hot/page/'
start_page = int(raw_input(u"输入起始页\n"))
end_page = int(raw_input(u"输入结束页\n"))
getImg(myUrl, start_page, end_page)