This file contains 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
using System; | |
using System.IO; | |
using System.Linq; | |
using System.Threading.Tasks; | |
using HtmlAgilityPack; | |
namespace AmazonPriceCheck | |
{ | |
public class AmazonUkStoreParser : IHtmlParser | |
{ | |
public string GetItemCodeFromUrl(string url) | |
{ | |
var itemCode = url.Substring(url.IndexOf("/dp/") + 4); | |
itemCode = itemCode.Substring(0, itemCode.IndexOf("/")); | |
return itemCode; | |
} | |
public decimal GetPriceForUrl(string url) | |
{ | |
decimal thePrice = -1; | |
if (string.IsNullOrEmpty(url)) | |
{ | |
return -1; | |
} | |
if (!url.Contains(".co.uk")) | |
{ | |
return -1; | |
} | |
if (!url.Contains("amazon.co.uk")) | |
{ | |
return -1; | |
} | |
var pageString = HttpUtils.GetHtmlFromUrl(url); | |
thePrice = ParseDocumentForPrice(pageString); | |
return thePrice; | |
} | |
private decimal ParseDocumentForPrice(string pageString) | |
{ | |
var document = new HtmlDocument(); | |
document.LoadHtml(pageString); | |
var nodes = document.DocumentNode.SelectNodes( | |
"/html/body/div[@id='a-page'][1]" | |
+ "/div[@id='dp'][1]" | |
+ "/div[@id='dp-container'][1]" | |
+ "/div[@id='centerCol'][1]" | |
+ "/div[@id='desktop_unifiedPrice'][1]" | |
+ "/div[@id='unifiedPrice_feature_div'][1]" | |
+ "/div[@id='price'][1]" | |
+ "/table" | |
+ "/tr[@id='priceblock_ourprice_row'][1]" | |
+ "/td[2]" | |
+ "/span[@id='priceblock_ourprice']"); | |
var formattedNode = nodes.First().InnerHtml; | |
formattedNode = formattedNode.Replace(" ", ""); | |
formattedNode = formattedNode.Replace("\n", ""); | |
formattedNode = formattedNode.Replace("£", ""); | |
decimal price = -1; | |
Decimal.TryParse(formattedNode, out price); | |
return price; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment