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

from selenium import webdriver

from scrapy.contrib.spiders import CrawlSpider, Rule

from scrapy.contrib.linkextractors import LinkExtractor

from sina_comment.items import SinaCommentItem

import re

class MySpider(CrawlSpider):

	name = "sina"

	#设置下载延时

	download_delay = 2

	allowed_domains = ['ent.sina.com.cn']

	#第一篇文章地址

	start_urls = ['http://ent.sina.com.cn/']

	rules = [

	    Rule(LinkExtractor(allow=('http://ent.sina.com.cn/.*shtml')), callback='parse_item'),

	]

	def __init__(self,*args, **kwargs):

		super(MySpider, self).__init__(*args, **kwargs)  # 这里是关键

		self.driver = webdriver.Chrome()

	def parse_item(self, response):

	    self.log('Hi, this is an article page! %s' % response.url)

	    try:

	    	self.driver