Scrapy框架微博头条更新

1.自定义
a)当前更新微博头条内容，邮件通知
1.分析页面
a)微博主页：https://weibo.com/，记录cookies
b)登陆链接
https://login.sina.com.cn/sso/login.php
c)头条Url
https://d.weibo.com/623751_1
3.实现思路
a)微博模拟登陆，保存cookie信息
b)关注实时头条
c)每个小时，更新一次，新发布头条，邮件通知
4.编码实现
Spider组件

# -*- coding: utf-8 -*-
from scrapy.spiders import Spider
from scrapy import Spider, Request
from lxml import etree
import re
import datetime,time
import uuid

from SinaTopic.items import SinatopicItem

class SinaspiderSpider(Spider):
    name = 'SinaSpider'
    allowed_domains = ['weibo.com']
    start_urls = ['https://d.weibo.com/623751_1']

    def start_requests(self):
        for i in range(10):
            yield Request(url=self.start_urls[0], callback=self.parse, dont_filter=True)

    def parse(self, response):
        res = response.text.replace('\r','').replace('\\n','').replace('\t','').replace('\\','').strip()
        #with open('html.txt','w') as f:
        #    f.write(res)
        lists = re.findall(r'<li class="pt_li pt_li_2 S_bg2"(.*)</li>', res)[0]
        selector = etree.HTML(str(lists))
        titles = selector.xpath('//div[@class="text_box"]/div[@class="title W_autocut"]/a/text()')
        hrefs = selector.xpath('//div[@class="text_box"]/div[@class="title W_autocut"]/a/@href')
        subs = selector.xpath('//div[@class="text_box"]/div[@class="text text_cut S_txt2"]/text()')
        picmuls = selector.xpath('//ul[@class="pic_m3 clearfix"]/li/img/@src')
        accounts = selector.xpath('//div[@class="subinfo_box clearfix"]/a/span[@class="subinfo S_txt2"]/text()')
        datatimes = selector.xpath('//div[@class="subinfo_box clearfix"]/span[@class="subinfo S_txt2"]/text()')
        refercounts = selector.xpath('//em[@class="W_fico