model_spider.py 文件源码

def parse(self, response):
        log.msg('[parse] %s' % response.url)

        # ????ID???????????URL?request??
        for seriesId in response.xpath('body/dl').re(r'id="s(\d+)"'):
            series_page_url = "http://www.autohome.com.cn/" + seriesId
            log.msg('series_page_url:%s' % series_page_url)
            request = scrapy.Request(url=series_page_url, callback=self.parse_model_selling, dont_filter=True)
            request.meta['series_id'] = seriesId
            yield request

    # ???????