Strip inline scripts from reader body extraction

Datawrapper embed resizers (and other inline scripts) were leaking into
reader mode as literal text. Two extraction paths were affected:

- parser.go extractContentText/extractLede stripped only script tags via
  htmlTagRe, leaving the JS body behind. This is the path that usually
  wins for feeds shipping full content:encoded (e.g. Politico).
- article.go goquery paths call .Text(), which concatenates script source.

Both now drop whole <script>/<style>/<noscript> elements before pulling
text. Paywall detection (JSON-LD) still runs before the goquery strip.

internal/ingestion/parser.go

@@ -46,6 +46,12 @@ var (
 	wsRe      = regexp.MustCompile(`\s+`)
 	imgSrcRe  = regexp.MustCompile(`(?i)<img[^>]+src=["']([^"']+)["']`)
 
+	// nonContentElemRe strips whole <script>/<style>/<noscript> elements —
+	// tags AND their text — before the generic tag strip runs. htmlTagRe alone
+	// removes only the tags, which would leave inline JavaScript (e.g. a
+	// Datawrapper embed resizer) as literal text in reader mode.
+	nonContentElemRe = regexp.MustCompile(`(?is)<script\b[^>]*>.*?</script\s*>|<style\b[^>]*>.*?</style\s*>|<noscript\b[^>]*>.*?</noscript\s*>`)
+
 	// Used by extractContentText to preserve paragraph structure when turning
 	// content:encoded HTML into plain text.
 	blockCloseRe  = regexp.MustCompile(`(?i)</(p|div|li|h[1-6]|blockquote|article|section|figure|figcaption|ul|ol|table|tr|pre)>`)
@@ -149,6 +155,9 @@ func extractLede(desc string) string {
 	if desc == "" {
 		return ""
 	}
+	// Drop <script>/<style>/<noscript> (tags and their inner text) before the
+	// generic tag strip, which would otherwise leave the inner text behind.
+	desc = nonContentElemRe.ReplaceAllString(desc, " ")
 	// Replace tags with a space so adjacent blocks like </p><p> don't fuse words.
 	text := htmlTagRe.ReplaceAllString(desc, " ")
 	text = html.UnescapeString(text)
@@ -165,7 +174,11 @@ func extractContentText(raw string) string {
 	if strings.TrimSpace(raw) == "" {
 		return ""
 	}
-	s := brRe.ReplaceAllString(raw, "\n")
+	// Remove <script>/<style>/<noscript> elements whole (tags + inner text)
+	// first — otherwise htmlTagRe below strips only the tags and leaves inline
+	// JavaScript (e.g. a Datawrapper embed resizer) as literal reader text.
+	s := nonContentElemRe.ReplaceAllString(raw, "\n")
+	s = brRe.ReplaceAllString(s, "\n")
 	s = blockCloseRe.ReplaceAllString(s, "\n\n")
 	s = htmlTagRe.ReplaceAllString(s, "")
 	s = html.UnescapeString(s)