Question

我试图使用cheerio来运行这个简单的scrape代码，但我一直都会遇到错误...我真的不知道问题是什么？请帮我！

var request = require('request'),
cheerio = require('cheerio'),
url     = "https://www.amazon.com/review/top-reviewers/ref=cm_cr_tr_link_2?ie=UTF8&page=1",
isFloat = ['Customer Reviewer', 'Total Reviews', 'Helpful Votes', 'Percent Helpful'];
exclude = ['Rank'];

 require({url : url, time: true}, function (error, response, body) {
if (!error) {
    var $ = cheerio.load(body),
        result      = {},
        lastupdate  = $(".a-bordered a-horizontal-stripes a-align- center a-spacing-top-none a-size-small crDataGrid.negmargin_lblUpdate").text(),
        status      = "Succsess",
        message     = "All data collected",
        col         = [];

    result = {
        status  : status,
        message : message,
        data    : {
            lastupdate  : lastupdate,
            table       : [] 
        },
        elapsedTime : response.elapsedTime
    };

    $('.a-bordered.a-horizontal-stripes.a-align-center.a-spacing-top-none.a-size-small.crDataGrid.neg-margin').each(function(i,tr) {
        var row ={};
        switch(i) {
            case 0:
                $(tr).find('th').each(function (j,th) {
                    col.push($(th).text().trim());
                });
                break;
            default:
            $(tr).find('td').each(function (j, td) {
                if (exclude.indexOf(col[j]) !== -1) {
                    return true;
                }

                if (isFloat.indexOf(col[j]) !== -1) {
                    var match = $(td).text().trim().match(/[0-9,.]*/);
                    if (match !== null) {
                        row[col[j]] = parseFloat(match[0].replace(/,/g, '') );
                    } else {
                        row[col[j]] = parseFloat(match);
                    }
                } else {
                    row[col[j]] = $(td).text().trim();
                }
            });
            result.data.table.push(row);
            break;
        }
    });
    console.log(JSON.stringify(result));
  } else {
    console.log(JSON.stringify({status : "Failed", message : "We've encounted an error : " + error}));
  }
});

这样的控制台错误，请帮我解决一下我的代码

控制台日志

assert.js:85
  throw new assert.AssertionError({
 ^
  AssertionError: path must be a string
    at Module.require (module.js:496:3)
    at require (internal/module.js:20:19)
    at Object.<anonymous> (/home/fajrullah/Documents/Documents/pp/scraping/cek.js:7:1)
    at Module._compile (module.js:570:32)
    at Object.Module._extensions..js (module.js:579:10)
    at Module.load (module.js:487:32)
    at tryModuleLoad (module.js:446:12)
    at Function.Module._load (module.js:438:3)
    at Module.runMain (module.js:604:10)
    at run (bootstrap_node.js:394:7)

Answer 1

错误是您的require声明。它需要一个字符串，因为require是Node中的关键字。

我认为您打算使用request包，因此请将行更改为：

request({url : url, time: true}, function (error, response, body) {

另请注意您的错误消息说明哪一行导致了问题：

at Object.<anonymous> (/home/fajrullah/Documents/Documents/pp/scraping/cek.js:7:1)

请查看该行并确定您获得AssertionError: path must be a string

的原因

无法运行此nodejs代码以及如何调试它？

控制台日志

1 个答案: