循环遍历数据并创建一个数组并输出为json文件

Question

我想循环使用cheerio

抓取的数据

示例输入数据：

11 aug 2017
    Arsenal - Leicester City
12 aug 2017 
    Watford - Liverpool
    Crystal Palace - Huddersfield Town
    Everton - Stoke City

我想要创建的最终结果是json文件：

{
    "fixtureDate": [
        {
            "homeTeam": "Arsenal",
            "awayTeam": "Leicester City",
            "matchDate": " 11 aug 2017 "
        },
        {
            "homeTeam": "Watford",
            "awayTeam": "Liverpool",
            "matchDate": " 12 aug 2017 "
        },
        {
            "homeTeam": "Crystal Palace",
            "awayTeam": "Huddersfield Town",
            "matchDate": " 12 aug 2017 "
        },
        {
            "homeTeam": "Everton",
            "awayTeam": "Stoke City",
            "matchDate": " 12 aug 2017 "
        },  

我现在需要遍历数据并创建数组的代码：

// loop trough the data
for(var i=0; i<json.matchDate.length; i++){
    output.fixtureDate[i] = {
        matchDate : json.matchDate[i], 
        homeTeam : json.homeTeam[i],
        awayTeam : json.awayTeam[i],              
        matchTime : json.matchTime[i]
    }

}  

但结果不正确，因为I ++是日期 请参阅下面的当前结果（请参阅matchDate）：

{
    "fixtureDate": [
        {
            "homeTeam": "Arsenal",
            "awayTeam": "Leicester City",
            "matchDate": " 11 aug 2017 "
        },
        {
            "homeTeam": "Watford",
            "awayTeam": "Liverpool",
            "matchDate": " 12 aug 2017 "
        },
        {
            "homeTeam": "Crystal Palace",
            "awayTeam": "Huddersfield Town",
            "matchDate": " 13 aug 2017 "
        },
        {
            "homeTeam": "Everton",
            "awayTeam": "Stoke City",
            "matchDate": " 14 aug 2017 "
        },  

如何循环数据并创建正确的数组？

到目前为止我创建的完整代码：

var cheerio = require('cheerio');
var request = require('request');
var fs = require('fs');

var url = 'FIXTURES LINK'; 

request(url, function (error, response, html) {

  if (!error && response.statusCode == 200) {

    var $ = cheerio.load(html);  

    // create json structure in an array with the scraped data
    var json = {
      homeTeam : [],
      awayTeam : [],
      matchTime : [],
      matchDate : []       
    };
    output = {
      fixtureDate : []
    };    


    // create homeTeam value from website
    $('.fm-fixtures__list li .fm-fixture .fm-fixture__team--home .fm-fixture__team__name').each(function(){
      json.homeTeam.push($(this).text());
    });

    // create awayTeam value from website
    $('.fm-fixtures__list li .fm-fixture .fm-fixture__team--away .fm-fixture__team__name').each(function(){
      json.awayTeam.push($(this).text());
    });   

    // create matchTime value from website
    $('.fm-fixtures__list li .fm-fixture .fm-fixture__status .match-status').each(function(){
      json.matchTime.push($(this).text());
    }); 

    // create matchDate value from website
    $('.fm-fixtures__list li .fm-fixtures__date').each(function(){
      json.matchDate.push($(this).text());
    });                       


    // loop trough the data
    for(var i=0; i<json.homeTeam.length; i++){
        output.fixtureDate[i] = {
            matchDate : json.matchDate[i], 
            homeTeam : json.homeTeam[i],
            awayTeam : json.awayTeam[i],              
            matchTime : json.matchTime[i]
        }

    }  

    // create a json output and print in the console
    var scrape = JSON.stringify(output, null, 4);
    console.log(scrape);

    // create a json file 
    fs.writeFile('fixtures.json', JSON.stringify(output, null, 4), function(err){
        console.log('File successfully written to folder!');
    })            

  } // end if error
}); // end request function

Answer 1

由于匹配未按日期分组（在HTML中），因此您必须抓取每个匹配项，并检查它是否具有日期标签。如果是这样，请使用其日期并将其推送到阵列。如果没有，请使用上次使用的日期作为该匹配的日期，如下所示：

注意：您也可以在1个循环中执行此操作，而不是多个循环并创建多个数组然后组合它们。

// create matchDate value from website
var json = {
  "fixtureDate": []
};
var lastDate = "";
$('.fm-fixtures__list li').each(function(){
  var matchContainer = $(this);
  var homeTeam = matchContainer.find(".fm-fixture__team--home .fm-fixture__team__name").text().trim();
  var awayTeam = matchContainer.find(".fm-fixture__team--away .fm-fixture__team__name").text().trim();
  var matchDateContainer = matchContainer.find(".fm-fixtures__date__label");
  var matchDate = "";
  if (matchDateContainer.length){
    lastDate = matchDateContainer.text().trim();
  }
  matchDate = lastDate;
  json.fixtureDate.push({homeTeam: homeTeam, awayTeam: awayTeam, matchDate: matchDate});
}); 

console.log(json);

<script src="https://ajax.googleapis.com/ajax/libs/jquery/2.1.1/jquery.min.js"></script>
<ul class="fm-fixtures__list" data-reactid="1432">
  <li data-reactid="1433">
    <a href="/livescores/2522743" data-reactid="1434">
      <div class="fm-fixtures__date" data-reactid="1435"><span class="fm-fixtures__date__label" data-reactid="1436"><!-- react-text: 1437 -->August 11, 2017 <!-- /react-text --><!-- react-text: 1438 --> <!-- /react-text --></span></div>
      <div class="fm-fixture" data-reactid="1439">
        <div class="fm-fixture__time" data-reactid="1440"></div>
        <div class="fm-fixture__team fm-fixture__team--home" data-reactid="1441">
          <p class="fm-fixture__team__name" data-reactid="1442">Arsenal</p>
          <div class="fm-fixture__team__logo" data-reactid="1443">
            <div class="fm-image  fm-image--loading" data-reactid="1444"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/9825.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Arsenal" data-reactid="1445"></div>
          </div>
        </div>
        <div class="fm-fixture__status" data-reactid="1446"><span class="match-status" data-reactid="1447"><!-- react-text: 1448 --> <!-- /react-text --><!-- react-text: 1449 -->4 : 3<!-- /react-text --><!-- react-text: 1450 --> <!-- /react-text --></span></div>
        <div class="fm-fixture__team fm-fixture__team--away"
          data-reactid="1451">
          <div class="fm-fixture__team__logo" data-reactid="1452">
            <div class="fm-image  fm-image--loading" data-reactid="1453"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/8197.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Leicester City" data-reactid="1454"></div>
          </div>
          <p class="fm-fixture__team__name" data-reactid="1455">Leicester City</p>
        </div>
      </div>
    </a>
  </li>
  <li data-reactid="1456">
    <a href="/livescores/2522751" data-reactid="1457">
      <div class="fm-fixtures__date" data-reactid="1458"><span class="fm-fixtures__date__label" data-reactid="1459"><!-- react-text: 1460 -->August 12, 2017 <!-- /react-text --><!-- react-text: 1461 --> <!-- /react-text --></span></div>
      <div class="fm-fixture" data-reactid="1462">
        <div class="fm-fixture__time" data-reactid="1463"></div>
        <div class="fm-fixture__team fm-fixture__team--home" data-reactid="1464">
          <p class="fm-fixture__team__name" data-reactid="1465">Watford</p>
          <div class="fm-fixture__team__logo" data-reactid="1466">
            <div class="fm-image  fm-image--loading" data-reactid="1467"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/9817.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Watford" data-reactid="1468"></div>
          </div>
        </div>
        <div class="fm-fixture__status" data-reactid="1469"><span class="match-status" data-reactid="1470"><!-- react-text: 1471 --> <!-- /react-text --><!-- react-text: 1472 -->3 : 3<!-- /react-text --><!-- react-text: 1473 --> <!-- /react-text --></span></div>
        <div class="fm-fixture__team fm-fixture__team--away"
          data-reactid="1474">
          <div class="fm-fixture__team__logo" data-reactid="1475">
            <div class="fm-image  fm-image--loading" data-reactid="1476"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/8650.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Liverpool" data-reactid="1477"></div>
          </div>
          <p class="fm-fixture__team__name" data-reactid="1478">Liverpool</p>
        </div>
      </div>
    </a>
  </li>
  <li data-reactid="1536">
    <a href="/livescores/2522746" data-reactid="1537">
      <div class="fm-fixture" data-reactid="1538">
        <div class="fm-fixture__time" data-reactid="1539"></div>
        <div class="fm-fixture__team fm-fixture__team--home" data-reactid="1540">
          <p class="fm-fixture__team__name" data-reactid="1541">Crystal Palace</p>
          <div class="fm-fixture__team__logo" data-reactid="1542">
            <div class="fm-image  fm-image--loading" data-reactid="1543"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/9826.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Crystal Palace" data-reactid="1544"></div>
          </div>
        </div>
        <div class="fm-fixture__status" data-reactid="1545"><span class="match-status" data-reactid="1546"><!-- react-text: 1547 --> <!-- /react-text --><!-- react-text: 1548 -->0 : 3<!-- /react-text --><!-- react-text: 1549 --> <!-- /react-text --></span></div>
        <div class="fm-fixture__team fm-fixture__team--away"
          data-reactid="1550">
          <div class="fm-fixture__team__logo" data-reactid="1551">
            <div class="fm-image  fm-image--loading" data-reactid="1552"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/9796.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Huddersfield Town" data-reactid="1553"></div>
          </div>
          <p class="fm-fixture__team__name" data-reactid="1554">Huddersfield Town</p>
        </div>
      </div>
    </a>
  </li>
  <li data-reactid="1479">
    <a href="/livescores/2522747" data-reactid="1480">
      <div class="fm-fixture" data-reactid="1481">
        <div class="fm-fixture__time" data-reactid="1482"></div>
        <div class="fm-fixture__team fm-fixture__team--home" data-reactid="1483">
          <p class="fm-fixture__team__name" data-reactid="1484">Everton</p>
          <div class="fm-fixture__team__logo" data-reactid="1485">
            <div class="fm-image  fm-image--loading" data-reactid="1486"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/8668.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Everton" data-reactid="1487"></div>
          </div>
        </div>
        <div class="fm-fixture__status" data-reactid="1488"><span class="match-status" data-reactid="1489"><!-- react-text: 1490 --> <!-- /react-text --><!-- react-text: 1491 -->1 : 0<!-- /react-text --><!-- react-text: 1492 --> <!-- /react-text --></span></div>
        <div class="fm-fixture__team fm-fixture__team--away"
          data-reactid="1493">
          <div class="fm-fixture__team__logo" data-reactid="1494">
            <div class="fm-image  fm-image--loading" data-reactid="1495"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/10194.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="Stoke City" data-reactid="1496"></div>
          </div>
          <p class="fm-fixture__team__name" data-reactid="1497">Stoke City</p>
        </div>
      </div>
    </a>
  </li>
  <li data-reactid="1498">
    <a href="/livescores/2522752" data-reactid="1499">
      <div class="fm-fixture" data-reactid="1500">
        <div class="fm-fixture__time" data-reactid="1501"></div>
        <div class="fm-fixture__team fm-fixture__team--home" data-reactid="1502">
          <p class="fm-fixture__team__name" data-reactid="1503">West Bromwich Albion</p>
          <div class="fm-fixture__team__logo" data-reactid="1504">
            <div class="fm-image  fm-image--loading" data-reactid="1505"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/8659.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="West Bromwich Albion" data-reactid="1506"></div>
          </div>
        </div>
        <div class="fm-fixture__status" data-reactid="1507"><span class="match-status" data-reactid="1508"><!-- react-text: 1509 --> <!-- /react-text --><!-- react-text: 1510 -->1 : 0<!-- /react-text --><!-- react-text: 1511 --> <!-- /react-text --></span></div>
        <div class="fm-fixture__team fm-fixture__team--away"
          data-reactid="1512">
          <div class="fm-fixture__team__logo" data-reactid="1513">
            <div class="fm-image  fm-image--loading" data-reactid="1514"><img src="https://images.fotmob.com/image_resources/logo/teamlogo/8678.png" class="fm-image__wrapper fm-team-logo fm-team-logo--small" alt="AFC Bournemouth" data-reactid="1515"></div>
          </div>
          <p class="fm-fixture__team__name" data-reactid="1516">AFC Bournemouth</p>
        </div>
      </div>
    </a>
  </li>
</ul>

Answer 2

这样做：

var cheerio = require('cheerio');
var request = require('request');
var fs = require('fs');

var url = "https://www.fotmob.com/leagues/47/matches/" 

request(url, function (error, response, html) {

  if (!error && response.statusCode == 200) {

    var $ = cheerio.load(html);  

    let matchDate;

    let jsonArray = $('#app-view > div.fm-wrapper > section > div.fm-content > section ul > li').map(function(i, el) {
        // this === el
        let htmlLi = $(this).html();
        $ = cheerio.load(htmlLi);
    let home = $('div.fm-fixture > div.fm-fixture__team.fm-fixture__team--home > p').text() || 'emptyRes';
    let away = $('div.fm-fixture > div.fm-fixture__team.fm-fixture__team--away > p').text();
    let status = $('div > div.fm-fixture__status > span').text();
    let date = $('.fm-fixtures__date__label').text() || "useSameDate";

    if (date != "useSameDate"){
        matchDate = date;
    }

    if (home == "emptyRes"){
        return;
    }

        let matchDataObj = {
            matchDate : matchDate,
            homeTeam : home,
            awayTeam: away,
            matchStatus: status

        }
        // console.log(matchDataObj)
        return matchDataObj;
      }).toArray();

    var JsonData = {
        fixtureDate : jsonArray
    };

    // create a json file 
    fs.writeFile('fixtures.json', JSON.stringify(JsonData, null, 4), function(err){
        console.log('File successfully written to folder!');
    })            

  } // end if error
}); // end request function

fixtures.json的输出为：

{
    "fixtureDate": [
        {
            "matchDate": "August 11, 2017  ",
            "homeTeam": "Arsenal",
            "awayTeam": "Leicester City",
            "matchStatus": " 4 : 3 "
        },
        {
            "matchDate": "August 12, 2017  ",
            "homeTeam": "Watford",
            "awayTeam": "Liverpool",
            "matchStatus": " 3 : 3 "
        },
        {
            "matchDate": "August 12, 2017  ",
            "homeTeam": "Crystal Palace",
            "awayTeam": "Huddersfield Town",
            "matchStatus": " 0 : 3 "
        },
        {
            "matchDate": "August 12, 2017  ",
            "homeTeam": "Everton",
            "awayTeam": "Stoke City",
            "matchStatus": " 1 : 0 "
        },
        {
            "matchDate": "August 12, 2017  ",
            "homeTeam": "West Bromwich Albion",
            "awayTeam": "AFC Bournemouth",
            "matchStatus": " 1 : 0 "
        },
        {
            "matchDate": "August 12, 2017  ",
            "homeTeam": "Chelsea",
            "awayTeam": "Burnley",
            "matchStatus": " 2 : 3 "
        },
        {
            "matchDate": "August 12, 2017  ",
            "homeTeam": "Southampton",
            "awayTeam": "Swansea City",
            "matchStatus": " 0 : 0 "
        },
        {
            "matchDate": "August 12, 2017  ",
            "homeTeam": "Brighton & Hove Albion",
            "awayTeam": "Manchester City",
            "matchStatus": " 0 : 2 "
        },
        {
            "matchDate": "August 13, 2017  ",
            "homeTeam": "Newcastle United",
            "awayTeam": "Tottenham Hotspur",
            "matchStatus": " 0 : 2 "
        },
        {
            "matchDate": "August 13, 2017  ",
            "homeTeam": "Manchester United",
            "awayTeam": "West Ham United",
            "matchStatus": " 4 : 0 "
        },
        {
            "matchDate": "August 19, 2017  ",
            "homeTeam": "Swansea City",
            "awayTeam": "Manchester United",
            "matchStatus": " 0 : 4 "
        },
        {
            "matchDate": "August 19, 2017  ",
            "homeTeam": "Leicester City",
            "awayTeam": "Brighton & Hove Albion",
            "matchStatus": " 2 : 0 "
        },
        {
            "matchDate": "August 19, 2017  ",
            "homeTeam": "Burnley",
            "awayTeam": "West Bromwich Albion",
            "matchStatus": " 0 : 1 "
        },
        {
            "matchDate": "August 19, 2017  ",
            "homeTeam": "Liverpool",
            "awayTeam": "Crystal Palace",
            "matchStatus": " 1 : 0 "
        },
        {
            "matchDate": "August 19, 2017  ",
            "homeTeam": "AFC Bournemouth",
            "awayTeam": "Watford",
            "matchStatus": " 0 : 2 "
        },
        {
            "matchDate": "August 19, 2017  ",
            "homeTeam": "Southampton",
            "awayTeam": "West Ham United",
            "matchStatus": " 3 : 2 "
        },
        {
            "matchDate": "August 19, 2017  ",
            "homeTeam": "Stoke City",
            "awayTeam": "Arsenal",
            "matchStatus": " 1 : 0 "
        },
        {
            "matchDate": "August 20, 2017  ",
            "homeTeam": "Huddersfield Town",
            "awayTeam": "Newcastle United",
            "matchStatus": " 1 : 0 "
        },
        {
            "matchDate": "August 20, 2017  ",
            "homeTeam": "Tottenham Hotspur",
            "awayTeam": "Chelsea",
            "matchStatus": " 1 : 2 "
        },
        {
            "matchDate": "August 21, 2017  ",
            "homeTeam": "Manchester City",
            "awayTeam": "Everton",
            "matchStatus": " 1 : 1 "
        },
        {
            "matchDate": "August 26, 2017  ",
            "homeTeam": "AFC Bournemouth",
            "awayTeam": "Manchester City",
            "matchStatus": " 1 : 2 "
        },
        {
            "matchDate": "August 26, 2017  ",
            "homeTeam": "Huddersfield Town",
            "awayTeam": "Southampton",
            "matchStatus": " 0 : 0 "
        },
        {
            "matchDate": "August 26, 2017  ",
            "homeTeam": "Newcastle United",
            "awayTeam": "West Ham United",
            "matchStatus": " 3 : 0 "
        }, ...]}