careerbuilder.py 文件源码

def parse_job(self, response):
        """Parse a joblink into a JobItem.
        """
        s = Selector(response)
        item = JobItem()
        item['url'] = response.url.split('?')[0]
        item['site'] = 'CareerBuilder'
        item['title'] = s.css('h1::text').extract_first()
        item['text'] = s.css('.job-facts::text').extract()
        item['text'].extend(s.css('.item').css('.tag::text').extract())
        item['text'].extend(s.css('.description::text').extract())
        try:
            posted = s.xpath(
                '//h3[@id="job-begin-date"]/text()').extract_first()
            item['date_posted'] = utilities.naturaltime(
                posted.replace('Posted ', '')).isoformat()
        except Exception as e:
            self.logger.error(e)
        yield item