diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeCommentsInfoItemExtractor.java b/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeCommentsInfoItemExtractor.java index 471cafd9c..1d447bd55 100644 --- a/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeCommentsInfoItemExtractor.java +++ b/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeCommentsInfoItemExtractor.java @@ -3,6 +3,7 @@ package org.schabi.newpipe.extractor.services.youtube.extractors; import org.schabi.newpipe.extractor.comments.CommentsInfoItemExtractor; import org.schabi.newpipe.extractor.exceptions.ParsingException; import org.schabi.newpipe.extractor.utils.JsonUtils; +import org.schabi.newpipe.extractor.utils.Utils; import com.grack.nanojson.JsonArray; import com.grack.nanojson.JsonObject; @@ -62,7 +63,9 @@ public class YoutubeCommentsInfoItemExtractor implements CommentsInfoItemExtract @Override public String getCommentText() throws ParsingException { try { - return YoutubeCommentsExtractor.getYoutubeText(JsonUtils.getObject(json, "contentText")); + String commentText = YoutubeCommentsExtractor.getYoutubeText(JsonUtils.getObject(json, "contentText")); + // youtube adds U+FEFF in some comments. eg. https://www.youtube.com/watch?v=Nj4F63E59io + return Utils.removeUTF8BOM(commentText); } catch (Exception e) { throw new ParsingException("Could not get comment text", e); } diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/utils/Utils.java b/extractor/src/main/java/org/schabi/newpipe/extractor/utils/Utils.java index d4b8db432..fde334fa7 100644 --- a/extractor/src/main/java/org/schabi/newpipe/extractor/utils/Utils.java +++ b/extractor/src/main/java/org/schabi/newpipe/extractor/utils/Utils.java @@ -1,13 +1,13 @@ package org.schabi.newpipe.extractor.utils; -import org.schabi.newpipe.extractor.exceptions.ParsingException; - import java.io.UnsupportedEncodingException; import java.net.MalformedURLException; import java.net.URL; import java.net.URLDecoder; import java.util.List; +import org.schabi.newpipe.extractor.exceptions.ParsingException; + public class Utils { private Utils() { @@ -120,4 +120,14 @@ public class Utils { throw e; } } + + public static String removeUTF8BOM(String s) { + if (s.startsWith("\uFEFF")) { + s = s.substring(1); + } + if (s.endsWith("\uFEFF")) { + s = s.substring(0, s.length()-1); + } + return s; + } } \ No newline at end of file