Scrape Content from a Shopping Website
We select a shopping site to scrape the content from it
As you can see from the image, we have a left bar that contains links for the site's product categories
So our first step is to investigate the site HTML, and plan how we wish to scrape it.
The fashion site categories have sub categories (Men, Women, Kids)
<li class="menu-item" data-id="">
<a href="https://domain.com/fashion-by-/" class="main-category">
<i class="cat-icon osh-font-fashion"></i> <span class="nav-subTxt">FASHION </span> <i class="osh-font-light-arrow-left"></i><i class="osh-font-light-arrow-right"></i>
</a> <div class="navLayerWrapper" style="width: 633px; display: none;"><div class="submenu"><div class="column"><div class="categories"><a class="category" href="https://domain.com/fashion-by-/?sort=newest&dir=desc&viewType=gridView3">New Arrivals !</a> </div><div class="categories"><a class="category" href="https://domain.com/men-fashion/">Men</a> <a class="subcategory" href="https://domain.com/mens-shoes/">Shoes</a> <a class="subcategory" href="https://domain.com/mens-clothing/">Clothing</a> <a class="subcategory" href="https://domain.com/mens-accessories/">Accessories</a> </div><div class="categories"><a class="category" href="https://domain.com/women-fashion/">Women</a> <a class="subcategory" href="https://domain.com/womens-shoes/">Shoes</a> <a class="subcategory" href="https://domain.com/womens-clothing/">Clothing</a> <a class="subcategory" href="https://domain.com/womens-accessories/">Accessories</a> </div><div class="categories"><a class="category" href="https://domain.com/girls-boys-fashion/">Kids</a> <a class="subcategory" href="https://domain.com/boys-fashion/">Boys</a> <a class="subcategory" href="https://domain.com/girls/">Girls</a> </div><div class="categories"><a class="category" href="https://domain.com/maternity-clothes/">Maternity Clothes</a> </div></div><div class="column"><div class="categories"> <span class="category defaultCursor">Men Best Sellers</span> <a class="subcategory" href="https://domain.com/mens-casual-shoes/">Casual Shoes</a> <a class="subcategory" href="https://domain.com/mens-sneakers/">Sneakers</a> <a class="subcategory" href="https://domain.com/mens-t-shirts/">T-shirts</a> <a class="subcategory" href="https://domain.com/mens-polos/">Polos</a> </div><div class="categories"> <span class="category defaultCursor">Women Best Sellers</span> <a class="subcategory" href="https://domain.com/womens-sandals/">Sandals</a> <a class="subcategory" href="https://domain.com/womens-sneakers/">Sneakers</a> <a class="subcategory" href="https://domain.com/women-dresses/">Dresses</a> <a class="subcategory" href="https://domain.com/women-tops/">Tops</a> </div><div class="categories"><a class="category" href="https://domain.com/womens-curvy-clothing/">Women's Curvy Clothing</a> </div><div class="categories"><a class="category" href="https://domain.com/fashion-bundles/v/">Fashion Bundles</a> </div><div class="categories"><a class="category" href="https://domain.com/hijab-fashion/">Hijab Fashion</a> </div></div><div class="column"><div class="categories"><a class="category" href="https://domain.com/brands/fashion-by-/">SEE ALL BRANDS</a> <a class="subcategory" href="https://domain.com/adidas/">Adidas</a> <a class="subcategory" href="https://domain.com/converse/">Converse</a> <a class="subcategory" href="https://domain.com/ravin/">Ravin</a> <a class="subcategory" href="https://domain.com/dejavu/">Dejavu</a> <a class="subcategory" href="https://domain.com/agu/">Agu</a> <a class="subcategory" href="https://domain.com/activ/">Activ</a> <a class="subcategory" href="https://domain.com/oxford--bellini--tie-house--milano/">Tie House</a> <a class="subcategory" href="https://domain.com/shoe-room/">Shoe Room</a> <a class="subcategory" href="https://domain.com/town-team/">Town Team</a> </div></div></div></div>
</li><li class="menu-item" data-id="">
<a href="https://domain.com/fashion-by-/" class="main-category">
<i class="cat-icon osh-font-fashion"></i> <span class="nav-subTxt">FASHION </span> <i class="osh-font-light-arrow-left"></i><i class="osh-font-light-arrow-right"></i>
</a> <div class="navLayerWrapper" style="width: 633px; display: none;"><div class="submenu"><div class="column"><div class="categories"><a class="category" href="https://domain.com/fashion-by-/?sort=newest&dir=desc&viewType=gridView3">New Arrivals !</a> </div><div class="categories"><a class="category" href="https://domain.com/men-fashion/">Men</a> <a class="subcategory" href="https://domain.com/mens-shoes/">Shoes</a> <a class="subcategory" href="https://domain.com/mens-clothing/">Clothing</a> <a class="subcategory" href="https://domain.com/mens-accessories/">Accessories</a> </div><div class="categories"><a class="category" href="https://domain.com/women-fashion/">Women</a> <a class="subcategory" href="https://domain.com/womens-shoes/">Shoes</a> <a class="subcategory" href="https://domain.com/womens-clothing/">Clothing</a> <a class="subcategory" href="https://domain.com/womens-accessories/">Accessories</a> </div><div class="categories"><a class="category" href="https://domain.com/girls-boys-fashion/">Kids</a> <a class="subcategory" href="https://domain.com/boys-fashion/">Boys</a> <a class="subcategory" href="https://domain.com/girls/">Girls</a> </div><div class="categories"><a class="category" href="https://domain.com/maternity-clothes/">Maternity Clothes</a> </div></div><div class="column"><div class="categories"> <span class="category defaultCursor">Men Best Sellers</span> <a class="subcategory" href="https://domain.com/mens-casual-shoes/">Casual Shoes</a> <a class="subcategory" href="https://domain.com/mens-sneakers/">Sneakers</a> <a class="subcategory" href="https://domain.com/mens-t-shirts/">T-shirts</a> <a class="subcategory" href="https://domain.com/mens-polos/">Polos</a> </div><div class="categories"> <span class="category defaultCursor">Women Best Sellers</span> <a class="subcategory" href="https://domain.com/womens-sandals/">Sandals</a> <a class="subcategory" href="https://domain.com/womens-sneakers/">Sneakers</a> <a class="subcategory" href="https://domain.com/women-dresses/">Dresses</a> <a class="subcategory" href="https://domain.com/women-tops/">Tops</a> </div><div class="categories"><a class="category" href="https://domain.com/womens-curvy-clothing/">Women's Curvy Clothing</a> </div><div class="categories"><a class="category" href="https://domain.com/fashion-bundles/v/">Fashion Bundles</a> </div><div class="categories"><a class="category" href="https://domain.com/hijab-fashion/">Hijab Fashion</a> </div></div><div class="column"><div class="categories"><a class="category" href="https://domain.com/brands/fashion-by-/">SEE ALL BRANDS</a> <a class="subcategory" href="https://domain.com/adidas/">Adidas</a> <a class="subcategory" href="https://domain.com/converse/">Converse</a> <a class="subcategory" href="https://domain.com/ravin/">Ravin</a> <a class="subcategory" href="https://domain.com/dejavu/">Dejavu</a> <a class="subcategory" href="https://domain.com/agu/">Agu</a> <a class="subcategory" href="https://domain.com/activ/">Activ</a> <a class="subcategory" href="https://domain.com/oxford--bellini--tie-house--milano/">Tie House</a> <a class="subcategory" href="https://domain.com/shoe-room/">Shoe Room</a> <a class="subcategory" href="https://domain.com/town-team/">Town Team</a> </div></div></div></div>
</li>HTML
Let's set up a project
- Create a new Console App or Add new folder for our new sample with name “ShoppingSiteSample”
- Add new class with the name “ShoppingScraper”
- The first step will be to scrape the site categories and its sub categories
Let’s create a Categories Model:
public class Category
{
/// <summary>
/// Gets or sets the name.
/// </summary>
/// <value>
/// The name.
/// </value>
public string Name { get; set; }
/// <summary>
/// Gets or sets the URL.
/// </summary>
/// <value>
/// The URL.
/// </value>
public string URL { get; set; }
/// <summary>
/// Gets or sets the sub categories.
/// </summary>
/// <value>
/// The sub categories.
/// </value>
public List<Category> SubCategories { get; set; }
}public class Category
{
/// <summary>
/// Gets or sets the name.
/// </summary>
/// <value>
/// The name.
/// </value>
public string Name { get; set; }
/// <summary>
/// Gets or sets the URL.
/// </summary>
/// <value>
/// The URL.
/// </value>
public string URL { get; set; }
/// <summary>
/// Gets or sets the sub categories.
/// </summary>
/// <value>
/// The sub categories.
/// </value>
public List<Category> SubCategories { get; set; }
}Public Class Category
''' <summary>
''' Gets or sets the name.
''' </summary>
''' <value>
''' The name.
''' </value>
Public Property Name() As String
''' <summary>
''' Gets or sets the URL.
''' </summary>
''' <value>
''' The URL.
''' </value>
Public Property URL() As String
''' <summary>
''' Gets or sets the sub categories.
''' </summary>
''' <value>
''' The sub categories.
''' </value>
Public Property SubCategories() As List(Of Category)
End ClassVB C#
Now let’s build our scrape logic
public class ShoppingScraper : WebScraper { /// <summary> /// Override this method initialize your web-scraper. /// Important tasks will be to Request at least one start url... and set allowed/banned domain or url patterns. /// </summary> public override void Init() { License.LicenseKey = "LicenseKey"; this.LoggingLevel = WebScraper.LogLevel.All; this.WorkingDirectory = AppSetting.GetAppRoot() + @"\ShoppingSiteSample\Output\"; this.Request("www.webSite.com", Parse); } /// <summary> /// Override this method to create the default Response handler for your web scraper. /// If you have multiple page types, you can add additional similar methods. /// </summary> /// <param name="response">The http Response object to parse</param> public override void Parse(Response response) { var categoryList = new List<Category>(); foreach (var Links in response.Css("#menuFixed > ul > li > a ")) { var cat = new Category(); cat.URL = Links.Attributes ["href"]; cat.Name = Links.InnerText; categoryList.Add(cat); } Scrape(categoryList, "Shopping.Jsonl"); } }public class ShoppingScraper : WebScraper { /// <summary> /// Override this method initialize your web-scraper. /// Important tasks will be to Request at least one start url... and set allowed/banned domain or url patterns. /// </summary> public override void Init() { License.LicenseKey = "LicenseKey"; this.LoggingLevel = WebScraper.LogLevel.All; this.WorkingDirectory = AppSetting.GetAppRoot() + @"\ShoppingSiteSample\Output\"; this.Request("www.webSite.com", Parse); } /// <summary> /// Override this method to create the default Response handler for your web scraper. /// If you have multiple page types, you can add additional similar methods. /// </summary> /// <param name="response">The http Response object to parse</param> public override void Parse(Response response) { var categoryList = new List<Category>(); foreach (var Links in response.Css("#menuFixed > ul > li > a ")) { var cat = new Category(); cat.URL = Links.Attributes ["href"]; cat.Name = Links.InnerText; categoryList.Add(cat); } Scrape(categoryList, "Shopping.Jsonl"); } }Public Class ShoppingScraper Inherits WebScraper ''' <summary> ''' Override this method initialize your web-scraper. ''' Important tasks will be to Request at least one start url... and set allowed/banned domain or url patterns. ''' </summary> Public Overrides Sub Init() License.LicenseKey = "LicenseKey" Me.LoggingLevel = WebScraper.LogLevel.All Me.WorkingDirectory = AppSetting.GetAppRoot() & "\ShoppingSiteSample\Output\" Me.Request("www.webSite.com", AddressOf Parse) End Sub ''' <summary> ''' Override this method to create the default Response handler for your web scraper. ''' If you have multiple page types, you can add additional similar methods. ''' </summary> ''' <param name="response">The http Response object to parse</param> Public Overrides Sub Parse(ByVal response As Response) Dim categoryList = New List(Of Category)() For Each Links In response.Css("#menuFixed > ul > li > a ") Dim cat = New Category() cat.URL = Links.Attributes ("href") cat.Name = Links.InnerText categoryList.Add(cat) Next Links Scrape(categoryList, "Shopping.Jsonl") End Sub End ClassVB C#
Scraping links from the menu
Let’s update our code to scrape the Main Categories and all its sub links
public override void Parse(Response response)
{
// List of Categories Links (Root)
var categoryList = new List<Category>();
foreach (var li in response.Css("#menuFixed > ul > li"))
{
// List Of Main Links
foreach (var Links in li.Css("a"))
{
var cat = new Category();
cat.URL = Links.Attributes ["href"];
cat.Name = Links.InnerText;
cat.SubCategories = new List<Category>();
// List of Sub Catgories Links
foreach (var subCategory in li.Css("a [class=subcategory]"))
{
var subcat = new Category();
subcat.URL = Links.Attributes ["href"];
subcat.Name = Links.InnerText;
// Check If Link Exist Before
if (cat.SubCategories.Find(c=>c.Name== subcat.Name && c.URL == subcat.URL) == null)
{
// Add Sublinks
cat.SubCategories.Add(subcat);
}
}
// Add Categories
categoryList.Add(cat);
}
}
Scrape(categoryList, "Shopping.Jsonl");
}public override void Parse(Response response)
{
// List of Categories Links (Root)
var categoryList = new List<Category>();
foreach (var li in response.Css("#menuFixed > ul > li"))
{
// List Of Main Links
foreach (var Links in li.Css("a"))
{
var cat = new Category();
cat.URL = Links.Attributes ["href"];
cat.Name = Links.InnerText;
cat.SubCategories = new List<Category>();
// List of Sub Catgories Links
foreach (var subCategory in li.Css("a [class=subcategory]"))
{
var subcat = new Category();
subcat.URL = Links.Attributes ["href"];
subcat.Name = Links.InnerText;
// Check If Link Exist Before
if (cat.SubCategories.Find(c=>c.Name== subcat.Name && c.URL == subcat.URL) == null)
{
// Add Sublinks
cat.SubCategories.Add(subcat);
}
}
// Add Categories
categoryList.Add(cat);
}
}
Scrape(categoryList, "Shopping.Jsonl");
}Public Overrides Sub Parse(ByVal response As Response)
' List of Categories Links (Root)
Dim categoryList = New List(Of Category)()
For Each li In response.Css("#menuFixed > ul > li")
' List Of Main Links
For Each Links In li.Css("a")
Dim cat = New Category()
cat.URL = Links.Attributes ("href")
cat.Name = Links.InnerText
cat.SubCategories = New List(Of Category)()
' List of Sub Catgories Links
For Each subCategory In li.Css("a [class=subcategory]")
Dim subcat = New Category()
subcat.URL = Links.Attributes ("href")
subcat.Name = Links.InnerText
' Check If Link Exist Before
If cat.SubCategories.Find(Function(c) c.Name= subcat.Name AndAlso c.URL = subcat.URL) Is Nothing Then
' Add Sublinks
cat.SubCategories.Add(subcat)
End If
Next subCategory
' Add Categories
categoryList.Add(cat)
Next Links
Next li
Scrape(categoryList, "Shopping.Jsonl")
End SubVB C#
Now we have links to all site categories, let’s start scraping the products within each category
Let’s navigate to any category and check the content.
Let’s see its code
<section class="products">
<div class="sku -gallery -validate-size " data-sku="AG249FA0T2PSGNAFAMZ" ft-product-sizes="41,42,43,44,45" ft-product-color="Multicolour">
<a class="link" href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html">
<div class="image-wrapper default-state">
<img class="lazy image -loaded" alt="Bundle Of 2 Sneakers - Black &amp; Navy Blue" data-image-vertical="1" width="210" height="262" src="https://static.WebSite.com/p/agu-6208-488356-1-catalog_grid_3.jpg" data-sku="AG249FA0T2PSGNAFAMZ" data-src="https://static.WebSite.com/p/agu-6208-488356-1-catalog_grid_3.jpg" data-placeholder="placeholder_m_1.jpg"><noscript><img src="https://static.WebSite.com/p/agu-6208-488356-1-catalog_grid_3.jpg" width="210" height="262" class="image" /></noscript>
</div> <h2 class="title">
<span class="brand ">Agu </span>
<span class="name" dir="ltr">Bundle Of 2 Sneakers - Black & Navy Blue</span>
</h2><div class="price-container clearfix">
<span class="price-box">
<span class="price">
<span data-currency-iso="EGP">EGP</span>
<span dir="ltr" data-price="299">299</span>
</span> <span class="price -old -no-special"></span>
</span>
</div><div class="rating-stars"><div class="stars-container"><div class="stars" style="width: 62%"></div></div> <div class="total-ratings">(30)</div> </div> <span class="shop-first-logo-container"><img src="http://www.WebSite.com/images/local/logos/shop_first/ShoppingSite/logo_normal.png" data-src="http://www.WebSite.com/images/local/logos/shop_first/ShoppingSite/logo_normal.png" class="lazy shop-first-logo-img -mbxs -loaded"> </span>
<span class="osh-icon -ShoppingSite-local shop_local--logo -block -mbs -mts"></span>
<div class="list -sizes" data-selected-sku="">
<span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=41">41</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=42">42</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=43">43</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=44">44</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=45">45</span>
</div>
</a>
</div>
<div class="sku -gallery -validate-size " data-sku="LE047FA01SRK4NAFAMZ" ft-product-sizes="110,115,120,125,130,135" ft-product-color="Black">
<a class="link" href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html">
<div class="image-wrapper default-state"><img class="lazy image -loaded" alt="Genuine Leather Belt - Black" data-image-vertical="1" width="210" height="262" src="https://static.WebSite.com/p/leather-shop-1831-030217-1-catalog_grid_3.jpg" data-sku="LE047FA01SRK4NAFAMZ" data-src="https://static.WebSite.com/p/leather-shop-1831-030217-1-catalog_grid_3.jpg" data-placeholder="placeholder_m_1.jpg"><noscript><img src="https://static.WebSite.com/p/leather-shop-1831-030217-1-catalog_grid_3.jpg" width="210" height="262" class="image" /></noscript></div>
<h2 class="title"><span class="brand ">Leather Shop </span> <span class="name" dir="ltr">Genuine Leather Belt - Black</span></h2><div class="price-container clearfix">
<span class="sale-flag-percent">-29%</span> <span class="price-box"> <span class="price"><span data-currency-iso="EGP">EGP</span> <span dir="ltr" data-price="96">96</span> </span> <span class="price -old "><span data-currency-iso="EGP">EGP</span> <span dir="ltr" data-price="135">135</span> </span> </span>
</div><div class="rating-stars"><div class="stars-container"><div class="stars" style="width: 100%"></div></div> <div class="total-ratings">(1)</div> </div>
<span class="osh-icon -ShoppingSite-local shop_local--logo -block -mbs -mts"></span> <div class="list -sizes" data-selected-sku="">
<span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=110">110</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=115">115</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=120">120</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=125">125</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=130">130</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=135">135</span>
</div>
</a>
</div>
</section><section class="products">
<div class="sku -gallery -validate-size " data-sku="AG249FA0T2PSGNAFAMZ" ft-product-sizes="41,42,43,44,45" ft-product-color="Multicolour">
<a class="link" href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html">
<div class="image-wrapper default-state">
<img class="lazy image -loaded" alt="Bundle Of 2 Sneakers - Black &amp; Navy Blue" data-image-vertical="1" width="210" height="262" src="https://static.WebSite.com/p/agu-6208-488356-1-catalog_grid_3.jpg" data-sku="AG249FA0T2PSGNAFAMZ" data-src="https://static.WebSite.com/p/agu-6208-488356-1-catalog_grid_3.jpg" data-placeholder="placeholder_m_1.jpg"><noscript><img src="https://static.WebSite.com/p/agu-6208-488356-1-catalog_grid_3.jpg" width="210" height="262" class="image" /></noscript>
</div> <h2 class="title">
<span class="brand ">Agu </span>
<span class="name" dir="ltr">Bundle Of 2 Sneakers - Black & Navy Blue</span>
</h2><div class="price-container clearfix">
<span class="price-box">
<span class="price">
<span data-currency-iso="EGP">EGP</span>
<span dir="ltr" data-price="299">299</span>
</span> <span class="price -old -no-special"></span>
</span>
</div><div class="rating-stars"><div class="stars-container"><div class="stars" style="width: 62%"></div></div> <div class="total-ratings">(30)</div> </div> <span class="shop-first-logo-container"><img src="http://www.WebSite.com/images/local/logos/shop_first/ShoppingSite/logo_normal.png" data-src="http://www.WebSite.com/images/local/logos/shop_first/ShoppingSite/logo_normal.png" class="lazy shop-first-logo-img -mbxs -loaded"> </span>
<span class="osh-icon -ShoppingSite-local shop_local--logo -block -mbs -mts"></span>
<div class="list -sizes" data-selected-sku="">
<span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=41">41</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=42">42</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=43">43</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=44">44</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/agu-bundle-of-2-sneakers-black-navy-blue-653884.html?size=45">45</span>
</div>
</a>
</div>
<div class="sku -gallery -validate-size " data-sku="LE047FA01SRK4NAFAMZ" ft-product-sizes="110,115,120,125,130,135" ft-product-color="Black">
<a class="link" href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html">
<div class="image-wrapper default-state"><img class="lazy image -loaded" alt="Genuine Leather Belt - Black" data-image-vertical="1" width="210" height="262" src="https://static.WebSite.com/p/leather-shop-1831-030217-1-catalog_grid_3.jpg" data-sku="LE047FA01SRK4NAFAMZ" data-src="https://static.WebSite.com/p/leather-shop-1831-030217-1-catalog_grid_3.jpg" data-placeholder="placeholder_m_1.jpg"><noscript><img src="https://static.WebSite.com/p/leather-shop-1831-030217-1-catalog_grid_3.jpg" width="210" height="262" class="image" /></noscript></div>
<h2 class="title"><span class="brand ">Leather Shop </span> <span class="name" dir="ltr">Genuine Leather Belt - Black</span></h2><div class="price-container clearfix">
<span class="sale-flag-percent">-29%</span> <span class="price-box"> <span class="price"><span data-currency-iso="EGP">EGP</span> <span dir="ltr" data-price="96">96</span> </span> <span class="price -old "><span data-currency-iso="EGP">EGP</span> <span dir="ltr" data-price="135">135</span> </span> </span>
</div><div class="rating-stars"><div class="stars-container"><div class="stars" style="width: 100%"></div></div> <div class="total-ratings">(1)</div> </div>
<span class="osh-icon -ShoppingSite-local shop_local--logo -block -mbs -mts"></span> <div class="list -sizes" data-selected-sku="">
<span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=110">110</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=115">115</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=120">120</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=125">125</span> <span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=130">130</span>
<span class="js-link sku-size" data-href="http://www.WebSite.com/leather-shop-genuine-leather-belt-black-712030.html?size=135">135</span>
</div>
</a>
</div>
</section>HTML
Let’s build our product model for this content.
public class Product
{
/// <summary>
/// Gets or sets the name.
/// </summary>
/// <value>
/// The name.
/// </value>
public string Name { get; set; }
/// <summary>
/// Gets or sets the price.
/// </summary>
/// <value>
/// The price.
/// </value>
public string Price { get; set; }
/// <summary>
/// Gets or sets the image.
/// </summary>
/// <value>
/// The image.
/// </value>
public string Image { get; set; }
}public class Product
{
/// <summary>
/// Gets or sets the name.
/// </summary>
/// <value>
/// The name.
/// </value>
public string Name { get; set; }
/// <summary>
/// Gets or sets the price.
/// </summary>
/// <value>
/// The price.
/// </value>
public string Price { get; set; }
/// <summary>
/// Gets or sets the image.
/// </summary>
/// <value>
/// The image.
/// </value>
public string Image { get; set; }
}Public Class Product
''' <summary>
''' Gets or sets the name.
''' </summary>
''' <value>
''' The name.
''' </value>
Public Property Name() As String
''' <summary>
''' Gets or sets the price.
''' </summary>
''' <value>
''' The price.
''' </value>
Public Property Price() As String
''' <summary>
''' Gets or sets the image.
''' </summary>
''' <value>
''' The image.
''' </value>
Public Property Image() As String
End ClassVB C#
To scrape category pages, we add a new scrape method:
public void ParseCatgory(Response response)
{
// List of Products Links (Root)
var productList = new List<Product>();
foreach (var Links in response.Css("body > main > section.osh-content > section.products > div > a"))
{
var product = new Product();
product.Name = Links.InnerText;
product.Image = Links.Css("div.image-wrapper.default-state > img")[0].Attributes ["src"];
productList.Add(product);
}
Scrape(productList, "Products.Jsonl");
}public void ParseCatgory(Response response)
{
// List of Products Links (Root)
var productList = new List<Product>();
foreach (var Links in response.Css("body > main > section.osh-content > section.products > div > a"))
{
var product = new Product();
product.Name = Links.InnerText;
product.Image = Links.Css("div.image-wrapper.default-state > img")[0].Attributes ["src"];
productList.Add(product);
}
Scrape(productList, "Products.Jsonl");
}Public Sub ParseCatgory(ByVal response As Response)
' List of Products Links (Root)
Dim productList = New List(Of Product)()
For Each Links In response.Css("body > main > section.osh-content > section.products > div > a")
Dim product As New Product()
product.Name = Links.InnerText
product.Image = Links.Css("div.image-wrapper.default-state > img")(0).Attributes ("src")
productList.Add(product)
Next Links
Scrape(productList, "Products.Jsonl")
End SubVB C#
