#!/usr/bin/env python

from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor


class SolidSpider(CrawlSpider):
    name = "solid"
    allowed_domains = ["solidinfo.se"]
    start_urls = ['http://www.solidinfo.se/bransch/=Film-Video-TV-program-produktion-inspelning-12100/&fP=2']

    #http://www.solidinfo.se/bransch/Film-Video-TV-program-produktion-inspelning-12100
    #http://www.solidinfo.se/bransch/=Film-Video-TV-program-produktion-inspelning-12100/&fP=2
    #http://www.solidinfo.se/bransch/=Film-Video-TV-program-produktion-inspelning-12100/&fP=3

    rules = [

        Rule(
            LinkExtractor(
                allow=([r'/&fP=\d+']),
            ),
            callback='parse_item',
            follow=True,
        ),
    ]


    def parse_item(self, response):

        divs = response.css('div0.ftlk')

        for div in divs:
            business_title = div.xpath('div[1]/a/text()').extract()
            business_link = div.xpath ('div[1]/a/@href').extract()
            print business_title
            print business_link


#//*[@id="div0"]/div[1]/a
#//*[@id="div0"]/div[1]/a



#//*[@id="ctl00_ContentPlaceHolder1_ucOversikt_pnlNyckeltal"]
#//*[@id="ctl00_ContentPlaceHolder1_ucOversikt_pnlNyckeltal"]/div/table
#//*[@id="ctl00_ContentPlaceHolder1_ucOversikt_pnlNyckeltal"]/div/table/tbody/tr[2]
##ctl00_ContentPlaceHolder1_ucOversikt_pnlNyckeltal > div > table