*评论中的更多详细信息
我正在使用cheerio.js抓取数据并显示在3个HTML表中。它可以正常工作,除了在显示抓取数据之前在第二张和第三张表中添加了这些空白行(第一张表有25行,第二张表有25行空白行,然后是25行数据。第三张表有50行空白行,然后是25行数据)。
我相信这是由于通过一个请求刮取了所有数据,而不是每个表进行了1次刮取。
这是我第一次抓取,所以我想知道是否有办法更改我的代码以解决此问题,或者我是否必须在每个表中有1个抓取请求(但这似乎效率不高)。
如果您想查看我的猫鼬图式,请告诉我。
用于显示数据的HTML表(使用ejs):
<table>
<tr>
<th>Environment</th>
<th>Store Name</th>
<th>Code Version</th>
</tr>
<% stores.forEach(function(store){ %>
<tr>
<td> <%= store.environment.QA1 %> </td>
<td> <%= store.store.QA1 %> </td>
<td> <%= store.version.QA1 %> </td>
</tr>
<% }); %>
</table>
cheerio.js抓取信息:
router.get("/scrape", function(req, res){
request("http://link-goes-here", function(error, response, html){
var $ = cheerio.load(html);
var QAStoreInfo = [];
var QA1StoreInfo = [];
$("body > table > tbody > tr > td:nth-child(1) > table").addClass("row");
$('.row > tbody > tr:contains("QA")').each(function(i, element){
var QAResult = {
"environment.QA" : $(this).children().next(),
"store.QA" : $(this).children().next().next(),
"version.QA" : $(this).children().next().next().next()
};
QAStoreInfo.push(QAResult);
Store.count({}, function(err, test){
if (test === 0) {
var QAEntry = new Store(QAResult);
QAEntry.save(function(err, doc){
if(err){
console.log(err);
}
});
}
});
});
/* QA1 */
$('.row > tbody > tr:contains("QA1")').each(function(i, element){
var QA1Result = {
"environment.QA1" : $(this).children().next(),
"store.QA1" : $(this).children().next().next(),
"version.QA1" : $(this).children().next().next().next()
};
QA1StoreInfo.push(QA1Result);
Store.count({}, function(err, test){
if (test === 0) {
var QA1Entry = new Store(QA1Result);
QA1Entry.save(function(err, doc){
if(err){
console.log(err);
}
});
}
});
});
猫鼬模式:
var storeSchema = new mongoose.Schema({
environment: {
QA: String,
QA1: String,
QA2: String
},
store: {
QA: String,
QA1: String,
QA2: String
},
version: {
QA: String,
QA1: String,
QA2: String
}
});
/ scrape调用后的mongoDB集合:
{ "_id" : ObjectId("5f0610fee9b4c35d74a83600"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " Omega QA " }, "version" : { "QA1" : " _2019.11_2019_11.2 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83601"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " Crescent Centre " }, "version" : { "QA1" : " _2020.06_2020_06.6 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83602"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " Cumberland " }, "version" : { "QA1" : " _2019.11_2019_11.2 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83603"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " East Denver " }, "version" : { "QA1" : " _2019.11_2019_11.2 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83604"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " Brookwood " }, "version" : { "QA1" : " _2019.11_2019_11.2 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83605"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " WheatRidge " }, "version" : { "QA1" : " _2019.11_2019_11.2 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83606"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " Aurora Centerpoint " }, "version" : { "QA1" : " _2020.06_2020_06.6 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83607"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " Castle Rock " }, "version" : { "QA1" : " _2020.06_2020_06.6 " }, "__v" : 0 }
{ "_id" : ObjectId("5f0610fee9b4c35d74a83608"), "environment" : { "QA1" : " QA1 " }, "store" : { "QA1" : " Conyers " }, "version" : { "QA1" : " _2020.06_2020_06.6 " }, "__v" : 0 }
答案 0 :(得分:1)
Store
集合包含具有以下架构的抓取文档:
{
"environment" : { "QA": <string> } ,
"store" : { "QA": <string> },
"version" : { "QA": <string> }
}
和
{
"environment" : { "QA1": <string> } ,
"store" : { "QA1": <string> },
"version" : { "QA1": <string> }
}
HTML表中的空行用于具有第一个架构的记录,其中
QA1
是undefined
,environment
和store
字段中的version
文档。
我建议将Store
文档的架构与以下文档统一:
{
"kind": "QA|QA1",
"environment" : <string> ,
"store" : <string> ,
"version" : <string>
}
然后更新您的抓取脚本以存储文档,如下所示:
//...
var QAResult = {
"kind": "QA",
"environment" : $(this).children().next(),
"store" : $(this).children().next().next(),
"version" : $(this).children().next().next().next()
};
QAStoreInfo.push(QAResult);
//...
var QA1Result = {
"kind": "QA1",
"environment" : $(this).children().next(),
"store" : $(this).children().next().next(),
"version" : $(this).children().next().next().next()
};
QA1StoreInfo.push(QA1Result);
forEach
模板中的ejs
循环可以如下更新:
<% stores.forEach(function(store){ %>
<tr>
<td> <%= store.environment %> </td>
<td> <%= store.store %> </td>
<td> <%= store.version %> </td>
</tr>
<% }); %>