jobspresso.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
        item['site'] = 'Jobspresso'
        item['title'] = s.xpath(
            '//h2[@class="page-title"]//text()').extract_first()
        item['text'] = s.xpath(
            '//div[@itemprop="description"]//text()').extract()
        try:
            posted = s.xpath('//date/text()').extract_first()
            item['date_posted'] = parse_time(posted).isoformat()
        except Exception as e:
            self.logger.error(e)
        yield item