dianping

# -*- coding: utf-8 -*-
import sys
if sys.getdefaultencoding() != 'utf-8':
  reload(sys)
  sys.setdefaultencoding('utf-8')

sys.path.append('..')
import scrapy
from scrapy.selector import Selector
from items import DianpingItem


class xiaoLongXiaSelector():
  def __init__(self):

    pass

  def parse(self):
    fo = open('ch10', 'r')
    body = Selector(text=fo.read())

    for i in range(2, 20):
      print i-1,
      print body.xpath('//h4/text()').extract()[i].encode('utf-8')
    if len(body.xpath('//li[@class="top"]').extract()) > 0:
      print "推广",
      print len(body.xpath('//li[@class="top"]').extract())

    if len(body.xpath('//li[@data-midas]').extract()) > 0:
      print "广告",
      print len(body.xpath('//li[@data-midas]').extract())

    eateries = body.xpath('//li[@class=""]')
    for index, eatery in enumerate(eateries):
      args = (eatery.xpath('.//a[@class="review-num"]/b/text()').extract(), eatery.xpath('.//a[@class="mean-price"]/b/text()').extract())
      if (len(args[1]) == 1) and (len(args[2]) == 1):
        args = (index, args[1][0], args[2][0])
        print 'index: %d, 点评: %s, Price: %s' % args

    _item = DianpingItem()
    _item['name'] = body.xpath('//h4').extract()


xLX = xiaoLongXiaSelector()
xLX.parse()