def parse_job_detail(self, response): loader = JobLoader(JobItem()) loader.add_item(response.request.meta['item']) loader.add_value('id', self.generate_id(response.url)) loader.add_value('source', self.name) loader.add_value('source_label', self.label) loader.add_value('content', response.body_as_unicode()) yield loader.load_item()
def parse_job_detail(self, response): hxs = HtmlXPathSelector(response) loader = JobLoader(JobItem()) loader.add_item(response.request.meta['item']) loader.add_value('id', self.generate_id(response.url, ('IDEPD'))) loader.add_value('source', self.name) loader.add_value('source_label', self.label) loader.add_value('summary', hxs.select("//div[@class='cc-gv']//tr/td[contains(text(),'Opis del in nalog')]/following-sibling::td[1]/text()").extract_unquoted()) loader.add_value('content', response.body_as_unicode()) yield loader.load_item()