workingnomads.py 文件源码

def parse(self, response):
        data = json.loads(response.text)
        converter = html2text.HTML2Text()
        for job in data['hits']['hits']:
            item = JobItem()
            item['url'] = urljoin(
                "https://www.workingnomads.co/jobs/",
                job['_source']['slug'])
            item['title'] = job['_source']['title']
            item['site'] = 'WorkingNomads'
            item['text'] = converter.handle(job['_source']['description'])
            item['text'] = [item['text'] + ' '.join(item.get('tags', []))]
            try:
                posted = converter.handle(job['_source']['pub_date'])
                item['date_posted'] = posted.split('+')[0]
            except Exception as e:
                self.logger.error(e)
            yield item