lagou.py 文件源码

def parse_job(self, response):

        #????????
        item_loader = LagouJobItemLoader(item=LagouJobItem(), response=response)
        item_loader.add_css("title", ".job-name::attr(title)")
        item_loader.add_value("url", response.url)
        item_loader.add_value("url_object_id", get_md5(response.url))
        item_loader.add_css("salary", ".job_request .salary::text")
        item_loader.add_xpath("job_city", "//*[@class='job_request']/p/span[2]/text()")
        item_loader.add_xpath("work_years", "//*[@class='job_request']/p/span[3]/text()")
        item_loader.add_xpath("degree_need", "//*[@class='job_request']/p/span[4]/text()")
        item_loader.add_xpath("job_type", "//*[@class='job_request']/p/span[5]/text()")

        item_loader.add_css("tags", '.position-label li::text')
        item_loader.add_css("publish_time", ".publish_time::text")
        item_loader.add_css("job_advantage", ".job-advantage p::text")
        item_loader.add_css("job_desc", ".job_bt div")
        item_loader.add_css("job_addr", ".work_addr")
        item_loader.add_css("company_name", "#job_company dt a img::attr(alt)")
        item_loader.add_css("company_url", "#job_company dt a::attr(href)")
        item_loader.add_value("crawl_time", datetime.now())

        job_item = item_loader.load_item()

        return job_item