Middlewares refactored to multiple files in middleware package.

Extractors removed as they introduce complexity to scraper. Both in learning and developing.

middleware/parse_html.go

@@ -0,0 +1,18 @@
+package middleware
+
+import (
+	"bytes"
+	"github.com/PuerkitoBio/goquery"
+	"github.com/geziyor/geziyor/client"
+)
+
+// ParseHTML parses response if response is HTML
+type ParseHTML struct {
+	ParseHTMLDisabled bool
+}
+
+func (p *ParseHTML) ProcessResponse(r *client.Response) {
+	if !p.ParseHTMLDisabled && r.IsHTML() {
+		r.HTMLDoc, _ = goquery.NewDocumentFromReader(bytes.NewReader(r.Body))
+	}
+}