cve_details按照时间爬取(pyspider)

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2017-08-11 10:19:23
#Created by zhangguodong
# Project: CVE_Details

from pyspider.libs.base_handler import *
import re
from collections import defaultdict

#url = "www.cvedetails.com/cve/CVE-2007-6593/"
#pattern = "<table class=\"listtable\" .*?>.*?<tr.*?>.*?</tr>.*?(<tr.*?>.*?</tr>)+</table>"


class Handler(BaseHandler):
    crawl_config = {
    }
    
    def __init__(self):
        self.base_url = 'http://www.cvedetails.com/vulnerability-list/year-'
        self.start_year = 1999
        self.last_year = 2017
          
    @every(minutes=24 * 60)
    def on_start(self):
        while self.start_year<=self.last_year