Merge pull request #144 from yausername/fixCommentUrl

fix comment url

Author: theScrabi

extractor/src/main/java/org/schabi/newpipe/extractor/StreamingService.java

@@ -308,11 +308,11 @@ public final LinkType getLinkTypeByUrl(String url) throws ParsingException {
         LinkHandlerFactory cH = getChannelLHFactory();
         LinkHandlerFactory pH = getPlaylistLHFactory();
 
-        if (sH.acceptUrl(url)) {
+        if (sH != null && sH.acceptUrl(url)) {
             return LinkType.STREAM;
-        } else if (cH.acceptUrl(url)) {
+        } else if (cH != null && cH.acceptUrl(url)) {
             return LinkType.CHANNEL;
-        } else if (pH.acceptUrl(url)) {
+        } else if (pH != null && pH.acceptUrl(url)) {
             return LinkType.PLAYLIST;
         } else {
             return LinkType.NONE;

extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeCommentsExtractor.java

@@ -107,11 +107,11 @@ public InfoItemsPage<CommentsInfoItem> getPage(String pageUrl) throws IOExceptio
             throw new ParsingException("Could not parse json data for comments", e);
         }
         CommentsInfoItemsCollector collector = new CommentsInfoItemsCollector(getServiceId());
-        collectCommentsFrom(collector, ajaxJson, pageUrl);
+        collectCommentsFrom(collector, ajaxJson);
         return new InfoItemsPage<>(collector, getNextPageUrl(ajaxJson));
     }
 
-    private void collectCommentsFrom(CommentsInfoItemsCollector collector, JsonObject ajaxJson, String pageUrl) throws ParsingException {
+    private void collectCommentsFrom(CommentsInfoItemsCollector collector, JsonObject ajaxJson) throws ParsingException {
 
         JsonArray contents;
         try {
@@ -130,7 +130,7 @@ private void collectCommentsFrom(CommentsInfoItemsCollector collector, JsonObjec
 
         for(Object c: comments) {
             if(c instanceof JsonObject) {
-                CommentsInfoItemExtractor extractor = new YoutubeCommentsInfoItemExtractor((JsonObject) c, pageUrl);
+                CommentsInfoItemExtractor extractor = new YoutubeCommentsInfoItemExtractor((JsonObject) c, getUrl());
                 collector.commit(extractor);
             }
         }

extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeCommentsInfoItemExtractor.java

@@ -3,6 +3,7 @@
 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 Integer getLikeCount() throws ParsingException {
     @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<feff>
+            return Utils.removeUTF8BOM(commentText);
         } catch (Exception e) {
             throw new ParsingException("Could not get comment text", e);
         }

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 static URL stringToURL(String url) throws MalformedURLException {
             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;
+    }
 }