Parsen einer Seite

[homecineplexx]

ich muss mich da wieder mal an euch wenden, ich bin fürs Parsen leider echt zu d***.
Vor allem das Skript von @liv-in-sky wäre da wahrscheinlich interessant zu erweitern.
Ich hätte gern von folgender Page link text die ersten 5 Ergebnisse von mir aus als Object in einem Datenpunkt zb so

{'id': 'Jet-Hornerstrasse xy', 'Diesel':'1,999|15.03|07:05', 'Benzin:1,899|15:03|07:05'}

Dann könnte ich damit arbeiten. Gibts da was einfaches? vor allem mitn Parser möcht ich das nicht unbedingt machen, da ichs gern per Scheduler dann allo 0,30 Minuten einer Stunde holen möchte.

Danke glg

[liv-in-sky]

@homecineplexx

kennst du tankerkönig adapter ?

[homecineplexx]

@liv-in-sky said in Parsen einer Seite:

kennst du tankerkönig adapter ?

jaaa, ist der auch für Österreich?

[Homoran]

@homecineplexx sagte in Parsen einer Seite:

für Österreich?

das hatte ich bei den Preisen schon befürchtet

[homecineplexx]

@homoran said in Parsen einer Seite:

@homecineplexx sagte in Parsen einer Seite:

für Österreich?

das hatte ich bei den Preisen schon befürchtet

ist ja auch legitim

[liv-in-sky]

@homecineplexx

frag doch mal da nach, ob das noch aktuell ist https://forum.iobroker.net/topic/20314/skripten-des-e-control-spritpreisrechners/281 da sind die österreicher unter sich

bevor wir hier alles neu erfinden

[homecineplexx]

@liv-in-sky said in Parsen einer Seite:

@homecineplexx

frag doch mal da nach, ob das noch aktuell ist https://forum.iobroker.net/topic/20314/skripten-des-e-control-spritpreisrechners/281 da sind die österreicher unter sich

bevor wir hier alles neu erfinden

super, dankeschön...mach ich doch glatt!

[liv-in-sky]

@homecineplexx

ODER

habe leider noch ein problem mit den umlauten

[homecineplexx]

@liv-in-sky said in Parsen einer Seite:

@homecineplexx

ODER

habe leider noch ein problem mit den umlauten

na das sieht schon sehr fein aus

[liv-in-sky]

@homecineplexx

mit richtigen umlauten - vergiß nicht, du musst axios und cheerio unter zusätzlichen npm modulen in der javascript instanz haben - und mache die abfragen nicht zu oft - manche seiten mögen das nicht !

widget:

Spoiler

[{"tpl":"i-vis-jsontable","data":{"g_fixed":false,"g_visibility":false,"g_css_font_text":false,"g_css_background":false,"g_css_shadow_padding":false,"g_css_border":false,"g_gestures":false,"g_signals":false,"g_last_change":false,"visibility-cond":"==","visibility-val":1,"visibility-groups-action":"hide","iTblRowLimit":"5","iTableRefreshRate":"0","iTblSortOrder":"asc","iColCount":"2","iColShow1":"true","iTblHeadTextAlign1":"center","iTblTextAlign1":"left","iTblCellFormat1":"normal","iTblCellImageSize1":"200","iTblCellBooleanCheckbox1":"false","iTblCellBooleanColorFalse1":"#ff0000","iTblCellBooleanColorTrue1":"#00ff00","iTblCellNumberDecimals1":"2","iTblCellNumberDecimalSeperator1":".","iTblCellNumberThousandSeperator1":",","iTblCellThresholdsDp1":"","iTblCellThresholdsText1":"","iOpacityAll":"1","iTblRowEvenColor":"#e1efef","iTblRowUnevenColor":"#f6f8f8","iTblHeaderColor":"#59a5d4","iRowSpacing":"10","iTblRowEvenTextColor":"#000","iTblRowUnevenTextColor":"#000","iTblHeaderTextColor":"#000","iBorderSize":"0","iBorderStyleLeft":"none","iBorderStyleRight":"none","iBorderStyleUp":"none","iBorderStyleDown":"none","iBorderColor":"#ffffff","signals-cond-0":"==","signals-val-0":true,"signals-icon-0":"/vis/signals/lowbattery.png","signals-icon-size-0":0,"signals-blink-0":false,"signals-horz-0":0,"signals-vert-0":0,"signals-hide-edit-0":false,"signals-cond-1":"==","signals-val-1":true,"signals-icon-1":"/vis/signals/lowbattery.png","signals-icon-size-1":0,"signals-blink-1":false,"signals-horz-1":0,"signals-vert-1":0,"signals-hide-edit-1":false,"signals-cond-2":"==","signals-val-2":true,"signals-icon-2":"/vis/signals/lowbattery.png","signals-icon-size-2":0,"signals-blink-2":false,"signals-horz-2":0,"signals-vert-2":0,"signals-hide-edit-2":false,"lc-type":"last-change","lc-is-interval":true,"lc-is-moment":false,"lc-format":"","lc-position-vert":"top","lc-position-horz":"right","lc-offset-vert":0,"lc-offset-horz":0,"lc-font-size":"12px","lc-font-family":"","lc-font-style":"","lc-bkg-color":"","lc-color":"","lc-border-width":"0","lc-border-style":"","lc-border-color":"","lc-border-radius":10,"lc-zindex":0,"oid":"0_userdata.0.SpritpreiseAUT.5erPack","iColShow2":"true","iTblHeadTextAlign2":"center","iTblTextAlign2":"center","iTblCellFormat2":"normal","iTblCellImageSize2":"200","iTblCellBooleanCheckbox2":"false","iTblCellBooleanColorFalse2":"#ff0000","iTblCellBooleanColorTrue2":"#00ff00","iTblCellNumberDecimals2":"2","iTblCellNumberDecimalSeperator2":".","iTblCellNumberThousandSeperator2":",","iTblCellThresholdsDp2":"","iTblCellThresholdsText2":"","iTblShowHead":true,"iColName1":"Tankstelle","iColName2":"Preise"},"style":{"left":"757px","top":"472px","width":"662px","height":"221px"},"widgetSet":"vis-inventwo"}]

script:

Spoiler

const cheerio = require('cheerio');

const axios=require('axios');



let jsonArr;
let myDPunkt='0_userdata.0.SpritpreiseAUT.5erPack';


if(!existsState(myDPunkt))  createState(myDPunkt, "", { name: "kommt aus Webseite",type:'string' }); 

let mySchedule1="  3 */6 * * * "; // alle 6 stunden bei minute 3

doStuff()
holeDaten();
 schedule(mySchedule1,  function () {
 let myVarVar=mathRandomInt(1, 30);
// log("startet ");
 setTimeout(function() {          // variert die sekunden der abfrage, damit nicht immer die selbe ip zur absolut selben zeit eine abfrage stellt ))
  //   log("jetzt "+myVarVar);
     holeDaten();

 }, myVarVar*1000);
 });


function mathRandomInt(a, b) {
 if (a > b) {
   // Swap a and b to ensure a is smaller.
   var c = a;
   a = b;
   b = c;
 }
 return Math.floor(Math.random() * (b - a + 1) + a);
}

async function holeDaten() { 
   log("Hole Wetterdaten aus Koeln")
   await axios.get('https://spritvergleich.at/suche?suchwort=Stockerau', {
                   headers: { 'User-Agent':`Mozilla/5.0 (X11; CrOS x86_64 8172.45.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.64 Safari/537.36` },
                   responseType:'arraybuffer',
                   reponseEncoding: 'binary'
}).then((result) => {
        // log("1----"+result.data);
   //     log(result.data.toString('latin1'))
    
       // const decoder = new TextDecoder("iso_8859-2");
            const $ = cheerio.load(result.data.toString('latin1'))
                              const list5 = $('*')
                                                 .find("[class*=sp2]")                 //find("[class*=re]")  //find('.table_wert_1a')
                                                 .toArray()
                                                 .map(element => { return $(element).text()}); log(list5.length +"---"+list5)
                                               //  for (let z=0;z<list5.length;z++){log(list5[z])}
          
                              const list6 = $('*')
                                                 .find(".price")                 //find("[class*=re]")  //find('.table_wert_1a')
                                                 .toArray()
                                                 .map(element => { return $(element).text()}); //log(list6.length +"-----"+list6)
                        //  log(list5[5])
      
//} 


let myJsonSprit=[]
for (let sprit=0; sprit<6;sprit++){
myJsonSprit.push({
"tankstelle": list5[sprit+1].replace(/\n/g,"").replace(/\t/g,""),
"preis":list6[sprit]


})
}
log(JSON.stringify(myJsonSprit))
setState(myDPunkt,JSON.stringify(myJsonSprit))




       }).catch((error) => {
           return error;
       })}

async function doStuff() {
  
   
    if (!(await existsStateAsync("0_userdata.0.KoelnWetter.BerichtLang"))) {
       await createStateAsync("0_userdata.0.KoelnWetter.BerichtLang",{type: "string", name: "Bericht ausführlich", role: "value", read: true, write: true, } ); }
    if (!(await existsStateAsync("0_userdata.0.KoelnWetter.BerichtKurz"))) {
       await createStateAsync("0_userdata.0.KoelnWetter.BerichtKurz",{type: "string", name: "Bericht ausführlich", role: "value", read: true, write: true, } ); }
    if (!(await existsStateAsync("0_userdata.0.KoelnWetter.UV2Start"))) {
       await createStateAsync("0_userdata.0.KoelnWetter.UV2Start",{type: "string", name: "UV2Start", role: "value", read: true, write: true, } ); } 
    if (!(await existsStateAsync("0_userdata.0.KoelnWetter.UV2End"))) {
       await createStateAsync("0_userdata.0.KoelnWetter.UV2End",{type: "string", name: "UV2End", role: "value", read: true, write: true, } ); }           
    if (!(await existsStateAsync("0_userdata.0.KoelnWetter.Mond2End"))) {
       await createStateAsync("0_userdata.0.KoelnWetter.Mond2End",{type: "string", name: "Mond2End", role: "value", read: true, write: true, } ); }
    if (!(await existsStateAsync("0_userdata.0.KoelnWetter.Mond2Start"))) {
       await createStateAsync("0_userdata.0.KoelnWetter.Mond2Start",{type: "string", name: "Mond2Start", role: "value", read: true, write: true, } ); }  
    if (!(await existsStateAsync("0_userdata.0.KoelnWetter.MondGrad"))) {
       await createStateAsync("0_userdata.0.KoelnWetter.MondGrad",{type: "string", name: "MondGrad", role: "value", read: true, write: true, } ); }      



}

[Wannseesprinter]

Habe ebenfalls eine interne Website, von der ich gerne ein paar Werte parsen möchte. Leider steige ich bei Regex immer noch nicht voll durch. Sorry!

Bräuchte die markierten Werte als Zahl/String:

Der HTML Body

Spoiler

`<!DOCTYPE html>
<html>
<head>
<meta name="viewport" content="width=device-width,initial-scale=1.0" />
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<title>ZERO controller | www.elgrispower.com</title>
<link href="/css/jquery.dataTables.min.css" type="text/css" rel="stylesheet" />
<link href="/css/style.css" type="text/css" rel="stylesheet" />
</head>
<body>
<div class="wrapper">
<header>
<div class="header">
<div class="container">
<div class="logo">
<a href="/index.shtm"><img src="/images/logo.jpg" alt="Logo" /></img></a>
</div>

<div class="right-header">
<h2>elgris ZERO</h2>
<p id = "firmware_version"></p>
<div id = "notification_bar" style="float:right">
<div class="notification">
<img src = '/images/error_small.png' alt="E" title="Errors" ></img>
<div id = "errors" class = "errors">: 0</div>

</div>
<div class = "notification">
	<img src = '/images/warning_small.jpg' alt="W" title="Warnings" ></img>
	<div id = "warnings" class = "errors">: 0</div>
</div>
<div class = "notification">
	<img src = '/images/info_small.png' alt="I" title="Information" ></img>
	<div id = "info" class = "errors">: 0</div>
</div>

</div>
</div>
<div class="clr"></div>
</div>
</div>
</header>
<div class="header-menu">
<div class="container">
<div id="nav-trigger">
<span>Menu <img src="images/menu_list.png" class="menu_list" /></img></span>
</div>
<nav id="nav-main">
<ul>
<li><a href="/index.shtm">Home </a></li>
<li>
<div class="sub-menu">
<span class="sub-menu-span">Settings</span>
<div class="sub-menu-content">
<a href="/setting.shtm">General </a>
<a href="/inverter.shtm">Inverter </a>
<a href="/ecloud.shtm">elgris cloud</a>
<a href="/mqtt.shtm">MQTT</a>
<a href="/ftp_client.htm">FTP Push</a>
</div>
</div>
</li>
<li>
<div class="sub-menu">
<span class="sub-menu-span">Monitoring</span>
<div class="sub-menu-content">
<a href="/chart.shtm">Datalogger</a>
<a href="/live_chart.shtm">Live Chart</a>
<a href="/performance.html">Performance</a>
</div>
</div>
</li>
</ul>
</nav>

<nav id="nav-mobile"></nav>

</div>
</div>
<div class="setting">
<div class="container">
<div class="power">
<h1 class="text-center">Inverter Settings</h1>
<div class="col-100">
<div class="colum">
<div class="form-group">
<div class="col-30">
<div class="form-box">
</div>
</div>
<div class="col-30">
<div class="form-box">
<input name="" type="button" class="btn_sub top-25" value="Add Inverter" onclick = "addRow()"/>
</div>
</div>
<div class="col-30">
<input name="" type="submit" class="btn_sub top-25" id="save_settings" value="Save Settings" />
</div>
</div>
<div class="form-group">
<div id="inverterTableContainer">
<table id = "inverterTable">
<tr>
<th>#</th>
<th>Brand</th>
<th>Type</th>
<th>IP address</th>
<th>Port/ID</th>
<th>Serial number</th>
<th>Rated</th>
<th>Output</th>
<th>Energy</th>
<th>Delete</th>
<th>Status</th>
</tr>
</table>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
<table width="100%" class="display" id="table"></table>
<footer>
<div class='footer'>
<p class='copyright'>copyright 2004-2019 <a href='http://www.elgrispower.com'>elgris GmbH</a> Germany. All rights reserved.</p>
</div>
</footer>
</div>
<script type="text/javascript" src="/js/jquery.min.js"></script>
<script type="text/javascript" src="/js/jquery.dataTables.js"></script>
<script type="text/javascript" src="/js/settings.js"></script>
<script type="text/javascript" src="/js/inverter.js"></script>
<script type="text/javascript" src="/js/jquery.jeditable.js"></script>
<script type="text/javascript" src="/js/jquery.jeditable.masked.js"></script>
<script type="text/javascript" src="/js/jquery.jeditable.charcounter.js"></script>
<script type="text/javascript" src="/js/jquery.maskedinput.js"></script>
<script type="text/javascript" src="/js/jquery.charcounter.js"></script>
</body>
</html>

Ich hoffe, ihr habt einen Plan

Danke euch!