From 5e8a257ff873ac40e741272eb1fae829220f1ca4 Mon Sep 17 00:00:00 2001 From: "Arik Jones (aider)" Date: Mon, 30 Sep 2024 14:04:41 -0500 Subject: [PATCH] feat: implement links container selector for targeted scraping of linked content --- internal/scraper/scraper.go | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/internal/scraper/scraper.go b/internal/scraper/scraper.go index 1e145e5..54ab0a8 100644 --- a/internal/scraper/scraper.go +++ b/internal/scraper/scraper.go @@ -592,3 +592,14 @@ func ExtractContentWithCSS(content, includeSelector string, excludeSelectors []s logger.Printf("Extracted content length: %d\n", len(selectedContent)) return selectedContent, nil } +func resolveURL(href, base string) string { + parsedBase, err := url.Parse(base) + if err != nil { + return href + } + parsedHref, err := url.Parse(href) + if err != nil { + return href + } + return parsedBase.ResolveReference(parsedHref).String() +}