diff --git a/Jobs/cv-search-job/Services/HtmlJobSearcher.cs b/Jobs/cv-search-job/Services/HtmlJobSearcher.cs index 6c4cb78..a4e40f6 100644 --- a/Jobs/cv-search-job/Services/HtmlJobSearcher.cs +++ b/Jobs/cv-search-job/Services/HtmlJobSearcher.cs @@ -117,6 +117,10 @@ public sealed class HtmlJobSearcher continue; } + // Skip non-HTTP(S) URLs (e.g. file:// or javascript: that can appear in scraped HTML) + if (absoluteUri.Scheme != Uri.UriSchemeHttp && absoluteUri.Scheme != Uri.UriSchemeHttps) + continue; + var url = absoluteUri.GetLeftPart(UriPartial.Path); if (seen.Add(url)) results.Add(url);