access the 'd' element from an SVG object with casperjs - javascript

I am a very beginer in javascript/phantomjs/casperjs (like only several days of learning) but I am stuck with this svg graph I am trying to scrap data from.
I am trying to access the d="M20,331.37,331.37,21.40...." element from an SVG object using a casperjs code, and write in the console and a txt file (or CSV). I try the following code:
var casper = require('casper').create({
pageSettings: {
loadImages: true,
loadPlugins: true,
userAgent: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36'
}
});
//First step is to open baidu.html
casper.start().thenOpen("file:///baidu.html", function() {
console.log("Baidu website opened");
this.wait(6000);
});
casper.then(function() {
var dataFromGraph = this.getElementsAttribute(require('casper').selectXPath('//*[#id="trend"]/svg/path[6]'),"d");
this.echo(dataFromGraph);
require('fs').write("data_graph.txt", dataFromGraph,'w');
});
casper.run();
But nothing worked. I get NULL element or empty result.
This is all the other code I try:
var dataFromGraph = this.fetchText(require('casper').selectXPath('//*[#id="trend"]/svg/path[6]/d'));
var dataFromGraph = this.getElementsAttribute(require('casper').selectXPath('//*[#id="trend"]/svg/path[6]'),"d") //,"d")
var dataFromGraph = this.getElementInfo(require('casper').selectXPath('//*[#id="trend"]/svg/path[6]'))
var dataFromGraph = this.fetchText("#trend > svg > path");
I have the Xpath and the selector of the object but I am not sure how to acces it. Here is a picture of the element I want to scrap.
As the website I want to scrap need a password, this is the HTML file that I save from it https://ufile.io/5y9g2.
The element I want to scrap is the data behind the graph here.
Any help would be very appreciated.

I reworked your script a bit and now it works. Check the snippet below.
var fs = require('fs');
var casper = require('casper').create();
casper.start().thenOpen("http://localhost:8001/baidu.html", function() {
console.log("Baidu website opened");
});
casper.then(function() {
var graphData = this.evaluate(function() {
return document.querySelector('#trend > svg > path:nth-child(11)').getAttribute('d')
});
this.echo(graphData);
fs.write("data_graph.txt", graphData,'w');
});
casper.run();
Hope that helps!

Related

How to get JSON objects embedded in HTML page result of JS running by PhantomJS and pass them to java code?

I use JS script code that described in this answer, but I don't want to save html result page in html file. I want to extract Json object from <div class="rg_meta"> and pass them to Java code.
In searching, I find using "document", but I get undefined error. I am newbie in PhantomJS and working with JSON in Java.
var page = require('webpage').create();
var fs = require('fs');
var system = require('system');
var url = "";
var searchParameter = "";
var count=0;
if (system.args.length === 4) {
url=system.args[1];
searchParameter=system.args[2];
count=system.args[3];
}
if(url==="" || searchParameter===""){
phantom.exit();
}
page.settings.userAgent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.120 Safari/537.36';
page.zoomFactor = 0.1;
page.viewportSize = {
width: 1920,
height: 1080
};
var divCount="-1";
var topPosition=0;
var unchangedCounter=0;
page.open(url, function(status) {
console.log("Status: " + status);
if(status === "success") {
window.setInterval(function() {
var newDivCount = page.evaluate(function() {
var divs = document.querySelectorAll(".rg_di.rg_bx.rg_el.ivg-i");
return divs[divs.length-1].getAttribute("data-ri");
});
topPosition = topPosition + 1080;
page.scrollPosition = {
top: topPosition,
left: 0
};
if(newDivCount===divCount){
page.evaluate(function() {
var elems=document.getElementByClassName("rg_meta");
console.log(elems.length);
var button = document.querySelector("#smb");
if(!(typeof button === "undefined")) {
button.click();
console.log('Clicked');
return true;
}else{
return false;
}
});
if(parseInt(unchangedCounter,10) === parseInt(count,10)){
/* var path = searchParameter+'.html';
fs.write('seedHtml/'+path, page.content, 'w');
console.log('printing html');*/
phantom.exit();
}else{
unchangedCounter=unchangedCounter+1;
}
}else{
unchangedCounter=0;
}
divCount = newDivCount;
}, 500);
}else{
phantom.exit();
}
});
HTML5 data Attributes
Fortunately, HTML5 introduces custom data attributes.
<div id="msglist" data-user="bob" data-list-size="5" data-maxage="180"></div>
Custom data attributes:
are strings — you can store anything which can be string encoded, such as JSON. Type conversion must be handled in JavaScript.
should only be used when no suitable HTML5 element or attribute exists.
JavaScript Parsing #1:
Every browser will let you fetch and modify data- attributes using the getAttribute and setAttribute methods, e.g.
var msglist = document.getElementById("msglist");
var show = msglist.getAttribute("data-list-size");
msglist.setAttribute("data-list-size", show+3);
It works, but should only be used as a fallback for older browsers.
JavaScript Parsing #2:
Since version 1.4.3, jQuery’s data() method has parsed HTML5 data attributes. You don’t need to specify the data- prefix so the equivalent code can be written:
var msglist = $("#msglist");
var show = msglist.data("list-size");
msglist.data("list-size", show+3);
Hope it helps!!!

How to click a button ajax via casperjs?

This is my code. It run ok, it access site, and fill zipcode ok. But i dont know why it cant click button "GO" . What wrong in my code ? Thank you
Site is: https://www.az.aaa.com/membership/gift-membership-form?promocode=zumz0
Thank you !
var casper = require("casper").create();
var mouse = require("mouse").create(casper);
var casper = require('casper').create({
verbose: true,
logLevel: 'debug', // debug, info, warning, error
clientScripts: ["includes/jquery.min.js"],
pageSettings:{
loadImages: true,
loadPlugins: false,
userAgent: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'
}
}
);
var fs = require('fs');
//var password = casper.cli.get(1);
function strip_tags(str) {
str = str.toString();
return str.replace(/<\/?[^>]+>/gi, '');
}
casper.start().thenOpen("https://www.az.aaa.com/membership/gift-membership-form?promocode=zumz0", function(){
console.log("1. Access Site");
});
casper.waitForSelector('#edit-zipcode', function(){
console.log("2. Box Zipcode Found ! ");
this.capture('site_box_zipcode.png');
});
casper.then(function(){
fs.write("debug_zipcode.html", this.getPageContent(), 'w');
});
casper.then(function(){
console.log("3. Filling Form Zipcode")
this.evaluate(function(){
$('#edit-zipcode').attr('value', '86322');
$('#edit-tqs1-submit').click();
//document.getElementById("edit-zipcode").value='86322';
//document.getElementById("edit-tqs1-submit").click();
});
//this.mouse.rightclick('button.col-xs-12 col-md-1 product-button js-product-button pull-right');
})
//
casper.then(function(){
this.wait(7000);//Wait a bit so page loads (there are a lot of ajax calls and that is why we are waiting 6 seconds)
this.capture('Afterpostzipcode.png');
console.log("4. Finish Capture Picture");
});
casper.then(function(){
fs.write("debug_fl.html", this.get, 'w');
});
casper.run();

CasperJS - NodeList.length return 0

I tried to extract data from some webpages using CasperJS, I have tried adding this.wait(5000) inside getDetails(), but I don't know why direktoriNodeList.length always return 0
PhantomJS : 2.0.0
CasperJS : 1.1.0-beta3
//casperjs --proxy=127.0.0.1:9050 --proxy-type=socks5 axa-mandiri.casper.js
var casper = require("casper").create({
verbose: true,
logLevel: "info",
pageSettings: {
loadImages: false, //The script is much faster when this field is set to false
loadPlugins: false,
userAgent: "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.71 Safari/537.36"
}
});
var utils = require('utils');
var currentPage = 1;
var hospitals = [];
var url = 'https://www.axa-mandiri.co.id/direktori/rumah-sakit/';//Type your url
casper.start(url);//Start CasperJS
casper.waitForSelector('#main-direktori', processPage, stopScript);//Wait until content loads and then process the page
casper.run(function() {
utils.dump(hospitals);
this.exit();
});
function getDetails(){
/*
In this function you can put anything you want in order to extract your data from the website.
NOTE: This function is executed in page context, and will should be called as parameter to Casper's evaluate function.
*/
.
console.log("getDetails " + currentPage);
var details = [];
var direktoriNodeList = document.querySelectorAll("ul#main-direktori li.direktori-list");
console.log("direktoriNodeList.length " + direktoriNodeList.length);
utils.dump(direktoriNodeList);
for (var i = 0; i < direktoriNodeList.length; i++) {
console.log("querySelectorAll " + i);
var detail = {
name : direktoriNodeList[i].querySelector("div.details strong").textContent.replace(/\n/g, ''),
phone : direktoriNodeList[i].querySelector("div.details span:nth-child(1)").textContent.replace(/\n/g, ''),
map : direktoriNodeList[i].querySelector("div.map-details a.get-direction").getAttribute("href")
};
details.push(detail);
}
/*
[].forEach.call(document.querySelectorAll("ul#main-direktori li.direktori-list"), function(elem) {
console.log("querySelectorAll");
var detail = {
name : elem.querySelector("div.details strong").textContent.replace(/\n/g, ''),
phone : elem.querySelector("div.details span:nth-child(1)").textContent.replace(/\n/g, ''),
map : elem.querySelector("div.map-details a.get-direction").getAttribute("href")
};
details.push(detail);
});
*/
return JSON.stringify(details);
}
function stopScript() {
utils.dump(hospitals);
console.log("Exiting...");
this.exit();
};
function processPage() {
//your function which will do data scraping from the page. If you need to extract data from tables, from divs write your logic in this function
hospitals = hospitals.concat(this.evaluate(getDetails()));
//If there is no nextButton on the page, then exit a script because we hit the last page
if (this.exists("a.nextpostslink") == false) {
stopScript();
}
//Click on the next button
this.thenClick("a.nextpostslink").then(function() {
currentPage++;
this.waitForSelector("#main-direktori", processPage, stopScript);
});
};
casper.evaluate(fn, ...) expects a function, not an array. Change
hospitals = hospitals.concat(this.evaluate(getDetails()));
to
hospitals = hospitals.concat(this.evaluate(getDetails));
The problem here is that you're executing the function in the outer context instead of passing it into the page context. Don't forget to register to the "remote.message" event to see console.log() calls from the page context:
casper.on("remote.message", function(msg){
this.echo("remote> " + msg);
});

Select option from dropdown and submit request using nodejs

I am working on nodejs for scrapping a website and I am very new to nodejs.The website initial page is a popup in which one has to select option from selectbox and submit only then later pages can be browsed.this has to be done for first time and then it will be stored as cookie for later use.
I am able to get html page of popup but I am not able to select option from selectbox and submit request.
Here is my Code
var express = require('express');
var request=require('request');
var cheerio=require('cheerio');
var j = request.jar();
//var cookie = request.cookie();
j.setCookie("city_id=1; path=/; domain=.bigbasket.com", 'http://bigbasket.com/', function(error, cookie) {
//console.log("error"+error.message);
console.log("cookie "+cookie);
});
var app=express();
app.get('/', function(req, res){
console.log("hi");
var sessionVal = req.session;
request({uri:'http://bigbasket.com/',
headers:{'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.81 Safari/537.36' ,
'content-type':'application/x-www-form-urlencoded; charset=UTF-8',
'connection':'keep-alive'},
jar:j},
function(err, response, body) {
// console.log("err "+err.message);
console.log("header"+JSON.stringify(response.headers));
console.log("status"+response.statusCode);
console.log("cookie "+response.cookie);
console.log(body);
var $=cheerio.load(body,{xmlMode: true});
console.log($);
var $selectBox= $('select').filter('.selectboxdiv');
console.log($selectBox.text());
response.end;
});
});
app.listen('8081')
console.log('Magic happens on port 8081');
exports = module.exports = app;
I am able to get select box options through below code :
var $selectBox= $('select').filter('.selectboxdiv');
console.log($selectBox.text());
But I am not able to select that option and submit.I have to select city from dropdown menu and submit request so that I could scrape data from upcoming webpages.
EDIT:
What do you see if you use 'req.body.NAME_OF_YOUR_DROPDOWN_HERE'? Maybe you can see the selected option then?

Phantomjs check for response headers and then execute something

I have the following RequestURL.js file.
var webPage = require('webpage');
var system = require('system');
var page = webPage.create();
page.customHeaders = {"pragma": "akamai-x-feo-trace"};
page.settings.userAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36"
if (system.args.length === 1) {
console.log('Try to pass some args when invoking this script!');
} else {
page.open(system.args[1], function (status) {
var content = page.content;
console.log(content);
phantom.exit();
});
}
Now I execute this as phantomjs --ignore-ssl-errors=yes --ssl-protocol=any RequestURL.js #my_url_here > body.html
Now I have a parser written in python that takes body.html and executes it. Now before that I want the page source to get generated only if the response contains the following header.
X-Akamai-FEO-State:TRANSFORMING
Is there a way to modify my RequestURL.js to get there.
It is expected that page.onResourceReceived is triggered before the page.onLoadFinished callback of page.open().
var transforming = false;
page.onResourceReceived = function(response){
if (response.url === system.args[1]) { // TODO handle redirects if necessary
response.headers.forEach(function(header){
if(header.name === 'X-Akamai-FEO-State') {
transforming = header.value === 'TRANSFORMING';
}
});
}
};
page.open(system.args[1], function (status) {
if (transforming) {
console.log(page.content);
}
phantom.exit();
});

Categories

Resources