# -*- coding: utf-8 -*-
import scrapy
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy import Selector

import config
import datetime

class NevraxSpider(CrawlSpider):
    name = "nevrax_crawler"
    custom_settings = {
        'ITEM_PIPELINES': {
            'crawler.nevrax.pipelines.NevraxPipeline': 0
        }
    }
    allow_domains = [config.NEVRAX_URL]
    start_urls = [
        'http://'+config.NEVRAX_URL+'/',
    ]

    rules = [
            Rule(
                LinkExtractor(
                    canonicalize=True,
                    unique=True,
                    allow_domains=config.NEVRAX_URL,
                    #deny=".*\.neodarz\.net.*"
                ),
                follow=True,
                callback="parse_items"
            )
    ]


    def start_requests(self):
        for url in self.start_urls:
            yield scrapy.Request(url, callback=self.parse, dont_filter=True)

    def parse_items(self, response):
        sel = Selector(response)
        yield {
                'url': response.url,
                'title': response.css('title::text').extract_first(),
                'content': ''.join(sel.select("//body//text()").extract()).strip(),
                'content_length': len(response.body),
                'date_updated': datetime.datetime.now()
        }