ximaSpider.py 文件源码

def content_parse(self, response):
        logging.info(response.url)
        # ??????
        sound_ids = response.xpath('//div[@class="personal_body"]/@sound_ids').extract_first().split(',')
        for i in sound_ids:
            sound_json_url = 'http://www.ximalaya.com/tracks/{}.json'.format(i)
            yield Request(url=sound_json_url, headers=self.headers, callback=self.json_parse)