spec_spider.py 文件源码

def parse(self, response):
        url = response.url
        log.msg('[url]%s' % url)
        body = response.body
        soup = BeautifulSoup(body, 'lxml').select('.cardetail-infor')[0]
        text = str(self.gettextonly(soup)).decode('utf-8')
        m = re.findall(ur'(????|????|?????|????|????|? ? ?|? ? ?|????|??????)?\n?(.+)\n', text, re.M | re.U)
        map = dict([(d[0], d[1]) for d in m])
        result = SpecItem()
        result['id'] = url.split('/')[-1]
        result['spec'] = map
        yield result