Allow CDATA; do not parse script childs as raw content

README.md

@@ -2,7 +2,7 @@
 
 A Go port of Mozilla [Readability.js](https://github.com/mozilla/readability), an algorithm based on heuristics (e.g. link density, text similarity, number of images, etc.) that [just somehow work well](https://stackoverflow.com/a/4240037) and powers the [Firefox Reader View](https://support.mozilla.org/kb/firefox-reader-view-clutter-free-web-pages) offering a distraction-free reading experience for articles, blog posts, and other text-heavy web pages by removing ads, GDPR-compliant cookie banners and other unsolicited junk.
 
-This port uses only the minimal DOM parser bundled with the original lib, resorting to the Go stdlib (`net/html`) in case of a failure. The source code is aligned with the latest commit ([97db40b](https://github.com/mozilla/readability/commit/97db40ba035a2de5e42d1ac7437893cf0da31d76)) on the main branch.
+The source code is aligned with the latest commit ([97db40b](https://github.com/mozilla/readability/commit/97db40ba035a2de5e42d1ac7437893cf0da31d76)) on the main branch.
 
 
 ## A Bit of History

cmd/readability/readability.go

@@ -4,13 +4,17 @@ import (
 	"flag"
 	"fmt"
 	"io"
+	"log/slog"
 	"net/http"
 	"os"
 
 	"github.com/giulianopz/go-readability"
 )
 
-var output string
+var (
+	output  string
+	verbose bool
+)
 
 func handle(err error) {
 	if err != nil {
@@ -27,10 +31,15 @@ func main() {
 
 	flag.StringVar(&output, "output", "text", "the result output format: 'text' or 'html'")
 	flag.StringVar(&output, "o", "text", "the result output format: 'text' or 'html'")
+	flag.BoolVar(&verbose, "verbose", false, "enable logs")
+	flag.BoolVar(&verbose, "v", false, "enable logs")
 	flag.Parse()
 
-	url := flag.Arg(0)
+	if !verbose {
+		slog.SetDefault(slog.New(slog.NewTextHandler(io.Discard, nil)))
+	}
 
+	url := flag.Arg(0)
 	if url == "" {
 		exit("missing url")
 	}
@@ -41,14 +50,14 @@ func main() {
 	bs, err := io.ReadAll(resp.Body)
 	handle(err)
 
-	parser, err := readability.New(string(bs), url, readability.LogLevel(-1))
+	parser, err := readability.New(string(bs), url)
 	handle(err)
 
 	res, err := parser.Parse()
 	handle(err)
 
 	if output == "html" {
-		fmt.Print(res.Content)
+		fmt.Print(res.HTMLContent)
 	} else {
 		fmt.Print(res.TextContent)
 	}