dzdp_spider.py 文件源码

def parse_location(self,response):

        loc_hxs = scrapy.Selector(response)
        loc_xs = loc_hxs.xpath('//div[@id="aside"]/script[1]').extract()[0]
        coord_text = re.findall(r'lng:\w+.\w+,lat:\w+.\w+',loc_xs)[0]

        item = response.meta['item']
        item['location'] = coord_text.encode('gbk')
        return item
        #print  coord_text