1 files changed, 51 insertions, 0 deletions
diff --git a/whic.go b/whic.go
new file mode 100644
index 0000000..e8090b0
--- /dev/null
+++ b/whic.go
@@ -0,0 +1,51 @@
+package main
+
+import (
+	"fmt"
+	"log"
+	"strings"
+
+	"github.com/PuerkitoBio/goquery"
+	"github.com/gocolly/colly"
+)
+
+func ScrapeWhic() {
+	c := colly.NewCollector(
+		colly.AllowedDomains("whic.de"),
+	)
+
+	c.OnHTML("li.item", func(e *colly.HTMLElement) {
+		whisky_name := e.ChildAttr("a", "title")
+		whisky_url := e.ChildAttr("a", "href")
+		log.Println(whisky_name)
+		log.Println(whisky_url)
+
+		e.ForEach(".price-box", func(i int, e *colly.HTMLElement) {
+			e.ForEach(".old-price", func(i int, e *colly.HTMLElement) {
+				log.Println(e.ChildText(".price"))
+			})
+			e.ForEach(".special-price", func(i int, e *colly.HTMLElement) {
+				log.Println(e.ChildText(".price"))
+			})
+		})
+
+		/*
+		 * colly does not parse a <noscript>, thus we are reading the content and parse it as html.
+		 */
+		img_link_noisy := e.ChildText(".product-image")
+
+		doc, err := goquery.NewDocumentFromReader(strings.NewReader(img_link_noisy))
+		if err != nil {
+			log.Fatal(err)
+		}
+		log.Println(doc.Find("img").Attr("src"))
+
+		fmt.Println("")
+	})
+
+	c.Visit("https://whic.de/angebote")
+}
+
+func main() {
+	ScrapeWhic()
+}