Moves crawler to designated directory.

1 files changed, 64 insertions, 0 deletions

diff --git a/crawler/shop_whic.go b/crawler/shop_whic.go
new file mode 100644
index 0000000..896b1fb
--- /dev/null
+++ b/crawler/shop_whic.go
@@ -0,0 +1,64 @@
+package main
+
+import (
+	"log"
+	"strings"
+
+	"github.com/PuerkitoBio/goquery"
+	"github.com/gocolly/colly"
+)
+
+func ScrapeWhic(shop Shop) []Angebot {
+	Whiskys := []Angebot{}
+
+	c := colly.NewCollector(
+		colly.AllowedDomains("whic.de"),
+	)
+
+	c.OnHTML("li.item", func(e *colly.HTMLElement) {
+		W := Angebot{}
+
+		whisky_name := e.ChildAttr("a", "title")
+		whisky_url := e.ChildAttr("a", "href")
+
+		W.Name = whisky_name
+		W.Url = whisky_url
+
+		var err error
+
+		e.ForEach(".price-box", func(i int, e *colly.HTMLElement) {
+			e.ForEach(".old-price", func(i int, e *colly.HTMLElement) {
+				W.Original_price, err = sanitize_price(e.ChildText(".price"))
+				if err != nil {
+					log.Fatal(err)
+				}
+			})
+			e.ForEach(".special-price", func(i int, e *colly.HTMLElement) {
+				W.Discounted_price, err = sanitize_price(e.ChildText(".price"))
+				if err != nil {
+					log.Fatal(err)
+				}
+			})
+		})
+
+		/*
+		 * 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)
+		}
+		W.Image_url, _ = doc.Find("img").Attr("src")
+
+		W.Shop = shop.Id
+		W.Spirit_type = "Whisky"
+
+		Whiskys = append(Whiskys, W)
+	})
+
+	c.Visit("https://whic.de/angebote")
+
+	return Whiskys
+}