Last active
August 29, 2015 14:21
-
-
Save maggocnx/e4df0f3178613fe7f60e to your computer and use it in GitHub Desktop.
Scraping Amazon Orders German
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var casper = require('casper').create({ pageSettings: { webSecurityEnabled: false }}); | |
casper.userAgent('Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)'); | |
var numberOfOrders = 0; | |
casper.on('remote.message', function(msg) { | |
if(msg.indexOf(">")== 0){ | |
this.echo(msg); | |
} | |
}) | |
var loginUrl = "https://www.amazon.de/ap/signin/275-8205473-8265603?_encoding=UTF8&openid.assoc_handle=deflex&openid.claimed_id=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&openid.identity=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&openid.mode=checkid_setup&openid.ns=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0&openid.ns.pape=http%3A%2F%2Fspecs.openid.net%2Fextensions%2Fpape%2F1.0&openid.pape.max_auth_age=0&openid.return_to=https%3A%2F%2Fwww.amazon.de%2Fgp%2Fcss%2Fhomepage.html%3Fie%3DUTF8%26ref_%3Dnav_yam_ya" | |
casper.start(loginUrl, function() { | |
this.echo(this.getTitle()); | |
this.fill('form#ap_signin_form', { | |
email : "[email protected]", | |
password : "manila" | |
}, true) | |
}); | |
// casper.then(function(){ | |
// casper.download("https://amazon.de/gp/css/order/static-display/get-legal-invoice.html/ref=oh_aui_legal_invoice?ie=UTF8&orderId=304-2959266-4413936", "./invoices/invoice.pdf") | |
// }) | |
casper.then(function(){ | |
casper.open("https://www.amazon.de/gp/css/order-history/ref=nav_gno_yam_yrdrs"); | |
}) | |
casper.then(function(){ | |
casper.capture("capture.png") | |
}) | |
// casper.then(getPageOrders); | |
casper.run(function() { | |
this.echo('Done.').exit(); | |
}); | |
function getPageOrders() { | |
casper.page.injectJs("./jquery.min.js"); | |
casper.page.injectJs("./moment.min.js"); | |
var orders = this.evaluate(parsePage); | |
var nextLink = "li.a-last > a"; | |
if (casper.visible(nextLink)) { | |
casper.thenClick(nextLink); | |
casper.then(getPageOrders); | |
numberOfOrders++; | |
} else { | |
casper.echo("END " + numberOfOrders) | |
} | |
} | |
function parsePage(){ | |
var host; | |
var orderBoxes = $(".a-box-group"); | |
var filters = []; | |
var filterNames = ["M. Grieb"] | |
var sellerRegex = /seller=[a-zA-Z0-9]*/; | |
moment.locale("de-DE") | |
$.each(orderBoxes, function(index, orderBox){ | |
var order; | |
var $orderBox = $(orderBox); | |
var orderDetails = $orderBox.find(".value"); | |
var orderId = $.trim($(orderDetails[3]).text()) | |
var productBoxes = $orderBox.find(".a-fixed-left-grid-inner"); | |
var orderDate = $.trim($(orderDetails[0]).text()); | |
var order = { | |
id : orderId, | |
price : parseFloat($.trim($(orderDetails[1]).text()).replace("EUR ", "").replace(",", ".")), | |
orderedBy : $.trim($(orderDetails[2]).text()), | |
date : parseInt(moment(orderDate, "DD. MMMM YYYY").format("X")) * 1000 | |
}; | |
console.log("> " + order.id); | |
order.products = []; | |
$.each(productBoxes, function(index, productBox){ | |
// console.log("> xxx" + order.id); | |
$productBox = $(productBox); | |
var img = $productBox.find("img") | |
var imgUrl =$(img[0]).attr("src"); | |
var fields = $productBox.find(".a-link-normal"); | |
var nameEl = $(fields[1]); | |
var sellerEl = $(fields[2]); | |
var sellerUrl = sellerEl.attr("href"); | |
product = { | |
name : $.trim(nameEl.text()), | |
imgUrl : imgUrl, | |
url : nameEl.attr("href"), | |
sellerName : $.trim(sellerEl.text()), | |
sellerUrl : sellerUrl, | |
orderId : order.id, | |
notes : "", | |
status : "open" | |
} | |
if(productBoxes.length > 1 ){ | |
product.price = "0.0" | |
} | |
else{ | |
product.price = order.price; | |
} | |
if(sellerUrl){ | |
product.sellerId = sellerUrl.match(sellerRegex)[0].replace("seller=", ""); | |
} | |
else{ | |
// AmazonOrder | |
} | |
console.log("> " + product.name.substring(0,50) + "\t\t" + product.price) | |
order.products.push(order); | |
}); | |
orders.push = order; | |
return orders; | |
}); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment