【原创】淘宝关键词搜索爬取与解析

    def get_brand(self):
        """
        根据关键词获取品牌列表
        """
        headers = {
            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
            "Accept-Language": "zh-CN,zh;q=0.9",
            "Cache-Control": "no-cache",
            "Connection": "keep-alive",
            "Pragma": "no-cache",
            "Referer": "https://s.taobao.com/search?q=^%^E7^%^AC^%^94^%^E8^%^AE^%^B0^%^E6^%^9C^%^AC^%^E7^%^94^%^B5^%^E8^%^84^%^91&imgfile=&js=1&stats_click=search_radio_tmall^%^3A1&initiative_id=staobaoz_20230127&tab=mall&ie=utf8&bcoffset=0&p4ppushleft=^%^2C44&style=grid&s=0",
            "Sec-Fetch-Dest": "document",
            "Sec-Fetch-Mode": "navigate",
            "Sec-Fetch-Site": "same-origin",
            "Sec-Fetch-User": "?1",
            "Upgrade-Insecure-Requests": "1",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36",
            "sec-ch-ua": "^\\^Not_A",
            "sec-ch-ua-mobile": "?0",
            "sec-ch-ua-platform": "^\\^Windows^^",
        }
        cookies = {
            "cookie2": "1c1f03c4df47307258a30c65ce1db555",
        }
        url = "https://s.taobao.com/search"
        params = {
            "q": self.word,
            "imgfile": "",
            "js": "1",
            "stats_click": "search_radio_tmall^%^3A1",
            "initiative_id": "staobaoz_20230127",
            "tab": "mall",
            "ie": "utf8",
            "style": "grid"
        }
        # response = requests.get(url, headers=headers, params=params)
        response = self._parse_url(url=url, headers=headers, params=params)
        if not response:
            yield None
        # print(response.text)
        res = re.findall(r'g_page_config = (.*?)};', response.text, re.M | re.S)
        if not res:
            yield None
        datas = jsonpath.jsonpath(json.loads(res[0] + "}"), "$..sub")
        if not datas:
            yield None
        for data in datas[0]:
            yield data

    def get_products(self, ppath, page):
        """
        获取商品列表 根据销量排序
        ppath：品牌代码
        page：翻页
        """
        headers = {
            "Accept": "*/*",
            "Accept-Language": "zh-CN,zh;q=0.9",
            "Cache-Control": "no-cache",
            "Connection": "keep-alive",
            "Pragma": "no-cache",
            "Referer": "https://s.taobao.com/search?q=^%^E7^%^AC^%^94^%^E8^%^AE^%^B0^%^E6^%^9C^%^AC^%^E7^%^94^%^B5^%^E8^%^84^%^91&imgfile=&js=1&style=grid&stats_click=search_radio_tmall^%^3A1&initiative_id=staobaoz_20230127&tab=mall&ie=utf8&bcoffset=0&p4ppushleft=^%^2C44&cps=yes&ppath=20000^%^3A11119&sort=sale-desc&s=44",
            "Sec-Fetch-Dest": "script",
            "Sec-Fetch-Mode": "no-cors",
            "Sec-Fetch-Site": "same-origin",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36",
            "sec-ch-ua": "^\\^Not_A",
            "sec-ch-ua-mobile": "?0",
            "sec-ch-ua-platform": "^\\^Windows^^",
        }
        url = "https://s.taobao.com/search"
        params = {
            "data-key": "s",
            "data-value": page,
            "ajax": "true",
            "_ksTS": "1674837683322_2012",
            "callback": "jsonp2013",
            "q": self.word,
            "imgfile": "",
            "js": "1",
            "style": "grid",
            "stats_click": "search_radio_tmall^%^3A1",
            "initiative_id": "staobaoz_20230127",
            "tab": "mall",
            "ie": "utf8",
            "bcoffset": "0",
            "p4ppushleft": "^%^2C44",
            "cps": "yes",
            "ppath": ppath,
            "sort": "sale-desc",
            "s": ''
        }
        # 第一页的时候请求参数不一样
        if page == 1:
            params['data-value'] = '0,1'
            params['data-key'] = 's,ps'
            params['s'] = (int(page) - 1) * 44
        else:
            params['data-value'] = int(page) * 44
            params['s'] = (int(page)-1) * 44
        response = requests.get(url, headers=headers, params=params)
        return response.text