爬取字段和图片 spider_getModelInformation

时间:2022-06-15 01:27:41

import urllib
import urllib2
import re

class Spider:

def getPage(self,pageIndex):
  url="http://mm.taobao.com/json/request_top_list.htm?page="+str(pageIndex)
  request=urllib2.Request(url)
  response=urllib2.urlopen(request)
  return response.read().decode('gbk')

def getContents(self,pageIndex):
  page=self.getPage(pageIndex)
  pattern=re.compile('<a class="lady-name" href="(.*?)".*?>(.*?)</a>.*?<strong>(.*?)</strong>.*?<span>(.*?)</span>',re.S)
  items=re.findall(pattern,page)
  for item in items:
  print "Personal Address",item[0]
  print "Name",item[1],"Age",item[2],"city",item[3]

def start(self,start,end):
  for i in range(start,end+1):
  print "This is NO.",i,"model"
  self.getContents(i)

spider=Spider()
spider.start(1,5)