Python-сообщество

# -*- encoding: utf-8 -*-
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.selector import HtmlXPathSelector
from job.items import JobItem
import time
 
 
class JobSpider(CrawlSpider):
    name = 'superjob'
    allowed_domains = ['superjob.ru']
    start_urls = [
        'http://www.superjob.ru/vacancy/search/?t%5B0%5D=4&sbmit=1&period=7'
    ]
 
    rules = [
        Rule(SgmlLinkExtractor(allow='/vacancy/search/?',
                               restrict_xpaths=(
                                   u'//a[@class="h_border_none"]/<span>следующая</span>')),
             callback='parse',
             follow=True),
    ]
 
    def parse(self, response):
        hxs = HtmlXPathSelector(response)
        titles = hxs.select(
                '//*[@id="ng-app"]/div[2]/div/div[2]/div/div[1]/div[2]/div/div/h2/a')
        items = []
        count = 0
        for title in titles:
            item = JobItem()
            item['title'] = title.select('//h2/a/text()').extract()
            items.append(item)
            count += 1
 
        name_time_file = time.strftime("%Y-%m-%d-%H-%M")
        data_file = open('{}.csv'.format(name_time_file), 'w')
        data_file.write(str(count))
        data_file.close()
        # return items