python第一弹 爬虫淘女郎图片

第一次看到  http://bbs.byr.cn/#!article/Python/1859?p=1&au=lc10210103 看他说的很容易的样子就果断试一试了确实很简单，代码如下：

# -*- coding: utf-8 -*-


import urllib2
import urllib
import sys

class get_mm_pic(object):
   #成员变量?
   page_num = 0
   mmurl = ""

   #定义成员变量初始化函数
   def __init__(self, page_num):
      self.page_num = page_num
      self.mmurl = "http://mm.taobao.com/json/request_top_list.htm?type=0&page="

   #定义主要的图片提取下载函数
   def get_pic(self):
      page_num = self.page_num
      mmurl = self.mmurl
      page_count = 0
      mm_count = 0
      pic_count = 0

      while page_count < page_num:
         page_count += 1
         mm_count  = 0
         pic_count = 0
         url = mmurl + str(page_count)
         up = urllib2.urlopen(url)
         # cont get the url's content
         cont = up.read()
         #print cont
         pa = j = 0
   
         pmmh = pmmt = 0
         while True:
            ahref = '''<a href="http'''
            target = '''" target="'''
            pmmh = cont.find(ahref)

            #打开每一个MM的个人主页
            pmmt = cont.find(target, pmmh)
            if pmmh == -1:
               break
            modelurl = cont[pmmh + len(ahref) - 4 : pmmt]
            mup = urllib2.urlopen(modelurl)
            mm_count += 1
            pic_count = 0
            mcont = mup.read()

            img_style = "<img style="
            jpg = ".jpg"
            src = '''src="'''
            while True:
               pic_hptr = mcont.find(img_style)
               pic_tptr = mcont.find(jpg, pic_hptr)
               if pic_hptr == -1:
                  break
               mm_pic = mcont[pic_hptr : pic_tptr + len(jpg)]
               #定位到 src= 的位置 最终得到 mm图片的url mm_pic_url
               pic_hptr = mm_pic.find(src)
               mm_pic_url = mm_pic[pic_hptr+len(src) : ]
               pic_count += 1
               print mm_pic_url
               
               #下载图片
               try:
                  print ">>>downloading : page_" + str(page_count) + "_lady_" + str(mm_count) + "_pic_" + str(pic_count) + ".jpg......."
                  urllib.urlretrieve(mm_pic_url, "page_"+str(page_count)+"_lady_"+str(mm_count)+"_pic_"+str(pic_count)+".jpg")
               except KeyboardInterrupt:
                  print "SIGINT, exit..."
                  sys.exit(0)
               except:
                  pass
               
               #下一个MM个人主页
               mcont = mcont[pic_tptr : ]
               
            #下一个MM列表页
            cont = cont[pmmt+1 : ]

def main(page_num):
   get_mm_pictures = get_mm_pic(page_num)
   get_mm_pictures.get_pic()

if __name__ == '__main__':
   main(int(sys.argv[1]))

和拖延症战斗了半周终于完成了这个，和男程序员交流真是件痛苦的事情呀 >< 是吧罗瑞阳学长