如何在邮递员网站的HTML中提取产品名称

Question

我正在尝试验证产品是否已添加到移动网络视图结帐中。我尝试过Cheerios但没能从中得到太多好处。

在 HTML 响应中，我可以看到下面的脚本，其中包含产品信息，我想从电子商务数组内的该脚本中获取产品的名称 Short Sleeve Polo。提前致谢

<script>
    pageContext = {
       "currentPage":"shipping",
       "title":"Checkout",
       "type":"checkout",
       "ns":"checkout",
       "analytics":{
          "user":{
             "customerType":"New",
             "ecomStore":"Demandware",
             "userType":"regular user",
             "gender":"Female",
             "hasTransacted":false,
             "userEmailAddress":"[email protected]",
             "userId":"W05dds015457",
             "socialNetwork":""
          },
          "basket":{
             "ecommerce":[
                {
                   "name":"Short Sleeve Polo Shirt",
                   "id":"AA1s5083",
                   "variationid":"AA15s083001",
                   "isEdits":null,
                   "price":"10.00",
                   "brand":"Test",
                   "category":"variation-masters",
                   "variant":"Fresh Blue|3/4",
                   "quantity":1,
                   "position":0
                },
                {
                   "name":"Limited Edition Short Sleeve Polo Shirt",
                   "id":"AA15080",
                   "variationid":"AA15080007",
                   "isEdits":null,
                   "price":"12.00",
                   "brand":"Test",
                   "category":"kidswear",
                   "variant":"Dusky Jade|3/4",
                   "quantity":1,
                   "position":1
                }
             ]
          },
          "page":{
             "currencyCode":"GBP",
             "pageCategory":"shipping",
             "subCategory":"shipping",
             "pageName":"SiteGenesis Checkout",
             "pageDesc":"",
             "pageLocale":"en_GB",
             "pageCurrency":"GBP",
             "pageType":"shipping",
             "user":"regular user"
          }
       },
       "billingAllowed":false
    };
</script>

Answer 1

一种方法是获取脚本文本，定位变量的 JSON，解析它，然后最终像普通数组/对象一样定位您想要的值。

const cheerio = require('cheerio');
const $ = cheerio.load(html); // your html

const text = $('script')[0].text(); // TODO there might be multiple script tags

// get variable pageContext in the text
const matches = text.match(/pageContext = ([^;]*);/);

// removes any possible '\n' that show up and assign
// matches[1] (which now contains the json text) to a variable
var json = matches[1].replace(/\n/gi, '');

// parse the JSON that has been collected
var pageContext = JSON.parse(json);

// get both names from the ecommerce array items
var value1 = pageContext.analytics.basket.ecommerce[0].name;
var value2 = pageContext.analytics.basket.ecommerce[1].name;

参考： 使用 jQuery/cheerio 访问脚本标记中的变量