spider_jd.py 文件源码

def __data_parser__(self, data):
        html = etree.HTML(data)
        search_results = []
        for li in html.xpath('//li[@class="gl-item"]'):
            try:
                div = li.xpath('.//div[contains(@class, "p-img")]')[0]
                search_results.append({
                    'url': div.xpath('./a/@href')[0],
                    'intro': div.xpath('./a/@title')[0],
                    'price': float(li.xpath('.//div[@class="p-price"]')[0]
                                   .xpath('./strong/i/text()')[0].strip()),
                    'sales': li.xpath('.//div[@class="p-commit"]')[0]
                    .xpath('./strong/a/text()')[0].strip(),
                    'belong': colorful_text('??', Fore.CYAN)
                })
            except (IndexError, ValueError) as e:
                error()
        return search_results