Add Youtube videos in Quanta articles

Some articles (especially the recent year-in-review ones) include a Youtube
video. The server-side rendered articles do not include the Youtube iframe,
but they do have a script that looks like

    <script type="text/javascript" data-reactid="6">
      window.__APOLLO_STATE__ = {
        ...
          youtube_id: "9uASADiYe_8",

We add a reformatting function that tries to detect obvious JavaScript code
that has a field or variable called youtube_id that has an 11-character
double-quoted value, and adds the referenced Youtube videos in the beginning of
the article. This is slightly more general than needed for Quanta, in the hope
that it could be useful for similar sites.

reader/rewrite/rewrite_functions.go

@@ -15,10 +15,11 @@ import (
 )
 
 var (
-	youtubeRegex  = regexp.MustCompile(`youtube\.com/watch\?v=(.*)`)
-	invidioRegex  = regexp.MustCompile(`https?:\/\/(.*)\/watch\?v=(.*)`)
-	imgRegex      = regexp.MustCompile(`<img [^>]+>`)
-	textLinkRegex = regexp.MustCompile(`(?mi)(\bhttps?:\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])`)
+	youtubeRegex   = regexp.MustCompile(`youtube\.com/watch\?v=(.*)`)
+	youtubeIdRegex = regexp.MustCompile(`youtube_id"?\s*[:=]\s*"([a-zA-Z0-9_-]{11})"`)
+	invidioRegex   = regexp.MustCompile(`https?:\/\/(.*)\/watch\?v=(.*)`)
+	imgRegex       = regexp.MustCompile(`<img [^>]+>`)
+	textLinkRegex  = regexp.MustCompile(`(?mi)(\bhttps?:\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])`)
 )
 
 func addImageTitle(entryURL, entryContent string) string {
@@ -219,6 +220,23 @@ func addYoutubeVideoUsingInvidiousPlayer(entryURL, entryContent string) string {
 	return entryContent
 }
 
+func addYoutubeVideoFromId(entryContent string) string {
+	matches := youtubeIdRegex.FindAllStringSubmatch(entryContent, -1)
+	if matches == nil {
+		return entryContent
+	}
+	sb := strings.Builder{}
+	for _, match := range matches {
+		if len(match) == 2 {
+			sb.WriteString(`<iframe width="650" height="350" frameborder="0" src="https://www.youtube-nocookie.com/embed/`)
+			sb.WriteString(match[1])
+			sb.WriteString(`" allowfullscreen></iframe><br>`)
+		}
+	}
+	sb.WriteString(entryContent)
+	return sb.String()
+}
+
 func addInvidiousVideo(entryURL, entryContent string) string {
 	matches := invidioRegex.FindStringSubmatch(entryURL)
 	if len(matches) == 3 {

reader/rewrite/rewriter.go

@@ -74,6 +74,8 @@ func applyRule(entryURL, entryContent string, rule rule) string {
 		entryContent = addInvidiousVideo(entryURL, entryContent)
 	case "add_youtube_video_using_invidious_player":
 		entryContent = addYoutubeVideoUsingInvidiousPlayer(entryURL, entryContent)
+	case "add_youtube_video_from_id":
+		entryContent = addYoutubeVideoFromId(entryContent)
 	case "add_pdf_download_link":
 		entryContent = addPDFLink(entryURL, entryContent)
 	case "nl2br":

reader/rewrite/rules.go

@@ -26,7 +26,7 @@ var predefinedRules = map[string]string{
 	"oglaf.com":              "add_image_title",
 	"optipess.com":           "add_image_title",
 	"peebleslab.com":         "add_image_title",
-	"quantamagazine.org":     `remove("h6:not(.byline,.post__title__kicker), #comments, .next-post__content, .footer__section, figure .outer--content")`,
+	"quantamagazine.org":     `add_youtube_video_from_id, remove("h6:not(.byline,.post__title__kicker), #comments, .next-post__content, .footer__section, figure .outer--content, script")`,
 	"sentfromthemoon.com":    "add_image_title",
 	"thedoghousediaries.com": "add_image_title",
 	"treelobsters.com":       "add_image_title",

reader/scraper/rules.go

@@ -33,7 +33,7 @@ var predefinedRules = map[string]string{
 	"osnews.com":           "div.newscontent1",
 	"phoronix.com":         "div.content",
 	"pseudo-sciences.org":  "#art_main",
-	"quantamagazine.org":   ".outer--content, figure",
+	"quantamagazine.org":   ".outer--content, figure, script",
 	"raywenderlich.com":    "article",
 	"slate.fr":             ".field-items",
 	"techcrunch.com":       "div.article-entry",