From bb5ad49face622b301739ccba9161a86d5adb32f Mon Sep 17 00:00:00 2001
From: yausername <13ritvik@gmail.com>
Date: Sat, 16 Nov 2019 03:20:35 +0530
Subject: [PATCH] fix html comments

---
 .../extractors/PeertubeCommentsInfoItemExtractor.java    | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/services/peertube/extractors/PeertubeCommentsInfoItemExtractor.java b/extractor/src/main/java/org/schabi/newpipe/extractor/services/peertube/extractors/PeertubeCommentsInfoItemExtractor.java
index 1e6df770..cfe3e6aa 100644
--- a/extractor/src/main/java/org/schabi/newpipe/extractor/services/peertube/extractors/PeertubeCommentsInfoItemExtractor.java
+++ b/extractor/src/main/java/org/schabi/newpipe/extractor/services/peertube/extractors/PeertubeCommentsInfoItemExtractor.java
@@ -5,6 +5,8 @@ import java.text.ParseException;
 import java.text.SimpleDateFormat;
 import java.util.Locale;
 
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
 import org.schabi.newpipe.extractor.ServiceList;
 import org.schabi.newpipe.extractor.comments.CommentsInfoItemExtractor;
 import org.schabi.newpipe.extractor.exceptions.ParsingException;
@@ -59,7 +61,12 @@ public class PeertubeCommentsInfoItemExtractor implements CommentsInfoItemExtrac
     @Override
     public String getCommentText() throws ParsingException {
         String htmlText = JsonUtils.getString(item, "text");
-        return htmlText.replaceAll("(?s)<[^>]*>(\\s*<[^>]*>)*", "");
+        try {
+            Document doc = Jsoup.parse(htmlText);
+            return doc.body().text();
+        }catch(Exception e) {
+            return htmlText.replaceAll("(?s)<[^>]*>(\\s*<[^>]*>)*", "");
+        }
     }
 
     @Override