Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion PoliNetwork.Graduatorie.Scraper/Utils/Web/Scraper.cs
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,10 @@ private IEnumerable<string> ScrapeHomepage()
{
HashSet<string> links = new();
var page = _web.Load(HomepageUrl).DocumentNode;

var slides = page.SelectNodes("//section[@id='copertina']//div[contains(@class, 'sp-slides')]/div");
if (slides == null) return links;

foreach (var slide in slides)
{
var h1 = slide.Descendants("h1");
Expand All @@ -61,8 +64,11 @@ private IEnumerable<string> ScrapeFuturiStudenti()
{
HashSet<string> links = new();
var page = _web.Load(FuturiStudentiUrl).DocumentNode;

var slides =
page.SelectNodes("//section[@id='newsNoThumb' or @id='news']//div[contains(@class, 'sp-slides')]/div");
if (slides == null) return links;

foreach (var slide in slides)
{
var h1 = slide.Descendants("h1");
Expand All @@ -88,7 +94,10 @@ private IEnumerable<string> ScrapeInEvidenza()
{
HashSet<string> links = new();
var page = _web.Load(InEvidenzaUrl).DocumentNode;

var liTags = page.SelectNodes("//div[@id='content']//li");
if (liTags == null) return links;

foreach (var li in liTags)
{
var h3 = li.GetElementsByTagName("h3");
Expand Down Expand Up @@ -181,4 +190,4 @@ private bool IsValidText(string text)
return null;
}
}
}
}