Merge branch 'dev' of https://github.com/TeamNewPipe/NewPipeExtractor into dev

Isira-Seneviratne · Isira-Seneviratne · commit b2d0c098a3e4 · 2020-11-01T06:27:59.000+05:30
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/StreamingService.java b/extractor/src/main/java/org/schabi/newpipe/extractor/StreamingService.java
@@ -16,6 +16,7 @@
 import org.schabi.newpipe.extractor.stream.StreamExtractor;
 import org.schabi.newpipe.extractor.subscription.SubscriptionExtractor;
 import org.schabi.newpipe.extractor.suggestion.SuggestionExtractor;
+import org.schabi.newpipe.extractor.utils.Utils;
 
 import javax.annotation.Nullable;
 import java.util.Collections;
@@ -277,18 +278,19 @@ public CommentsExtractor getCommentsExtractor(String url) throws ExtractionExcep
      * Figures out where the link is pointing to (a channel, a video, a playlist, etc.)
      * @param url the url on which it should be decided of which link type it is
      * @return the link type of url
-     * @throws ParsingException
      */
-    public final LinkType getLinkTypeByUrl(String url) throws ParsingException {
-        LinkHandlerFactory sH = getStreamLHFactory();
-        LinkHandlerFactory cH = getChannelLHFactory();
-        LinkHandlerFactory pH = getPlaylistLHFactory();
+    public final LinkType getLinkTypeByUrl(final String url) throws ParsingException {
+        final String polishedUrl = Utils.followGoogleRedirectIfNeeded(url);
 
-        if (sH != null && sH.acceptUrl(url)) {
+        final LinkHandlerFactory sH = getStreamLHFactory();
+        final LinkHandlerFactory cH = getChannelLHFactory();
+        final LinkHandlerFactory pH = getPlaylistLHFactory();
+
+        if (sH != null && sH.acceptUrl(polishedUrl)) {
             return LinkType.STREAM;
-        } else if (cH != null && cH.acceptUrl(url)) {
+        } else if (cH != null && cH.acceptUrl(polishedUrl)) {
             return LinkType.CHANNEL;
-        } else if (pH != null && pH.acceptUrl(url)) {
+        } else if (pH != null && pH.acceptUrl(polishedUrl)) {
             return LinkType.PLAYLIST;
         } else {
             return LinkType.NONE;
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/linkhandler/LinkHandlerFactory.java b/extractor/src/main/java/org/schabi/newpipe/extractor/linkhandler/LinkHandlerFactory.java
@@ -42,12 +42,29 @@ public String getUrl(String id, String baseUrl) throws ParsingException {
     // Logic
     ///////////////////////////////////
 
-    public LinkHandler fromUrl(String url) throws ParsingException {
-        if (url == null) throw new IllegalArgumentException("url can not be null");
-        final String baseUrl = Utils.getBaseUrl(url);
-        return fromUrl(url, baseUrl);
+    /**
+     * Builds a {@link LinkHandler} from a url.<br>
+     * Be sure to call {@link Utils#followGoogleRedirectIfNeeded(String)} on the url if overriding
+     * this function.
+     * @param url the url to extract path and id from
+     * @return a {@link LinkHandler} complete with information
+     */
+    public LinkHandler fromUrl(final String url) throws ParsingException {
+        final String polishedUrl = Utils.followGoogleRedirectIfNeeded(url);
+        final String baseUrl = Utils.getBaseUrl(polishedUrl);
+        return fromUrl(polishedUrl, baseUrl);
     }
 
+    /**
+     * Builds a {@link LinkHandler} from a url and a base url. The url is expected to be already
+     * polished from google search redirects (otherwise how could {@code baseUrl} have been
+     * extracted?).<br>
+     * So do not call {@link Utils#followGoogleRedirectIfNeeded(String)} on the url if overriding
+     * this function, since that should be done in {@link #fromUrl(String)}.
+     * @param url the url without google search redirects to extract id from
+     * @param baseUrl the base url
+     * @return a {@link LinkHandler} complete with information
+     */
     public LinkHandler fromUrl(String url, String baseUrl) throws ParsingException {
         if (url == null) throw new IllegalArgumentException("url can not be null");
         if (!acceptUrl(url)) {
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/linkhandler/ListLinkHandlerFactory.java b/extractor/src/main/java/org/schabi/newpipe/extractor/linkhandler/ListLinkHandlerFactory.java
@@ -31,9 +31,10 @@ public String getUrl(String id, List<String> contentFilter, String sortFilter, S
     ///////////////////////////////////
 
     @Override
-    public ListLinkHandler fromUrl(String url) throws ParsingException {
-        String baseUrl = Utils.getBaseUrl(url);
-        return fromUrl(url, baseUrl);
+    public ListLinkHandler fromUrl(final String url) throws ParsingException {
+        final String polishedUrl = Utils.followGoogleRedirectIfNeeded(url);
+        final String baseUrl = Utils.getBaseUrl(polishedUrl);
+        return fromUrl(polishedUrl, baseUrl);
     }
 
     @Override
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/services/soundcloud/SoundcloudParsingHelper.java b/extractor/src/main/java/org/schabi/newpipe/extractor/services/soundcloud/SoundcloudParsingHelper.java
@@ -25,6 +25,8 @@
 
 import javax.annotation.Nonnull;
 import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
 import java.net.URLEncoder;
 import java.text.ParseException;
 import java.text.SimpleDateFormat;
@@ -148,12 +150,21 @@ public static String resolveUrlWithEmbedPlayer(String apiUrl) throws IOException
      *
      * @return the resolved id
      */
-    public static String resolveIdWithEmbedPlayer(String url) throws IOException, ReCaptchaException, ParsingException {
+    public static String resolveIdWithEmbedPlayer(String urlString) throws IOException, ReCaptchaException, ParsingException {
+        // Remove the tailing slash from URLs due to issues with the SoundCloud API
+        if (urlString.charAt(urlString.length() -1) == '/') urlString = urlString.substring(0, urlString.length()-1);
+
+        URL url;
+        try {
+            url = Utils.stringToURL(urlString);
+        } catch (MalformedURLException e){
+            throw new IllegalArgumentException("The given URL is not valid");
+        }
 
         String response = NewPipe.getDownloader().get("https://w.soundcloud.com/player/?url="
-                + URLEncoder.encode(url, "UTF-8"), SoundCloud.getLocalization()).responseBody();
+                + URLEncoder.encode(url.toString(), "UTF-8"), SoundCloud.getLocalization()).responseBody();
         // handle playlists / sets different and get playlist id via uir field in JSON
-        if (url.contains("sets") && !url.endsWith("sets") && !url.endsWith("sets/"))
+        if (url.getPath().contains("/sets/") && !url.getPath().endsWith("/sets"))
             return Parser.matchGroup1("\"uri\":\\s*\"https:\\/\\/api\\.soundcloud\\.com\\/playlists\\/((\\d)*?)\"", response);
         return Parser.matchGroup1(",\"id\":(([^}\\n])*?),", response);
     }
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/services/soundcloud/linkHandler/SoundcloudStreamLinkHandlerFactory.java b/extractor/src/main/java/org/schabi/newpipe/extractor/services/soundcloud/linkHandler/SoundcloudStreamLinkHandlerFactory.java
@@ -30,8 +30,6 @@ public String getUrl(String id) throws ParsingException {
     @Override
     public String getId(String url) throws ParsingException {
         Utils.checkUrl(URL_PATTERN, url);
-        // Remove the tailing slash from URLs due to issues with the SoundCloud API
-        if (url.charAt(url.length() -1) == '/') url = url.substring(0, url.length()-1);
 
         try {
             return SoundcloudParsingHelper.resolveIdWithEmbedPlayer(url);
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/YoutubeParsingHelper.java b/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/YoutubeParsingHelper.java
@@ -55,12 +55,6 @@ public class YoutubeParsingHelper {
     private YoutubeParsingHelper() {
     }
 
-    /**
-     * The official youtube app supports intents in this format, where after the ':' is the videoId.
-     * Accordingly there are other apps sharing streams in this format.
-     */
-    public final static String BASE_YOUTUBE_INTENT_URL = "vnd.youtube";
-
     private static final String HARDCODED_CLIENT_VERSION = "2.20200214.04.00";
     private static String clientVersion;
 
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/linkHandler/YoutubeCommentsLinkHandlerFactory.java b/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/linkHandler/YoutubeCommentsLinkHandlerFactory.java
@@ -1,10 +1,7 @@
 package org.schabi.newpipe.extractor.services.youtube.linkHandler;
 
-import static org.schabi.newpipe.extractor.services.youtube.YoutubeParsingHelper.BASE_YOUTUBE_INTENT_URL;
-
 import org.schabi.newpipe.extractor.exceptions.FoundAdException;
 import org.schabi.newpipe.extractor.exceptions.ParsingException;
-import org.schabi.newpipe.extractor.linkhandler.ListLinkHandler;
 import org.schabi.newpipe.extractor.linkhandler.ListLinkHandlerFactory;
 
 import java.util.List;
@@ -17,15 +14,6 @@ public static YoutubeCommentsLinkHandlerFactory getInstance() {
         return instance;
     }
 
-    @Override
-    public ListLinkHandler fromUrl(String url) throws ParsingException {
-        if (url.startsWith(BASE_YOUTUBE_INTENT_URL)){
-            return super.fromUrl(url, BASE_YOUTUBE_INTENT_URL);
-        } else {
-            return super.fromUrl(url);
-        }
-    }
-
     @Override
     public String getUrl(String id) {
         return "https://m.youtube.com/watch?v=" + id;
diff --git a/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/linkHandler/YoutubeStreamLinkHandlerFactory.java b/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/linkHandler/YoutubeStreamLinkHandlerFactory.java
@@ -2,7 +2,6 @@
 
 import org.schabi.newpipe.extractor.exceptions.FoundAdException;
 import org.schabi.newpipe.extractor.exceptions.ParsingException;
-import org.schabi.newpipe.extractor.linkhandler.LinkHandler;
 import org.schabi.newpipe.extractor.linkhandler.LinkHandlerFactory;
 import org.schabi.newpipe.extractor.services.youtube.YoutubeParsingHelper;
 import org.schabi.newpipe.extractor.utils.Utils;
@@ -15,8 +14,6 @@
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
-import static org.schabi.newpipe.extractor.services.youtube.YoutubeParsingHelper.BASE_YOUTUBE_INTENT_URL;
-
 /*
  * Created by Christian Schabesberger on 02.02.16.
  *
@@ -67,15 +64,6 @@ private static String assertIsId(@Nullable final String id) throws ParsingExcept
         }
     }
 
-    @Override
-    public LinkHandler fromUrl(String url) throws ParsingException {
-        if (url.startsWith(BASE_YOUTUBE_INTENT_URL)) {
-            return super.fromUrl(url, BASE_YOUTUBE_INTENT_URL);
-        } else {
-            return super.fromUrl(url);
-        }
-    }
-
     @Override
     public String getUrl(String id) {
         return "https://www.youtube.com/watch?v=" + id;
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
@@ -181,14 +181,39 @@ public static String removeUTF8BOM(String s) {
         return s;
     }
 
-    public static String getBaseUrl(String url) throws ParsingException {
-        URL uri;
+    public static String getBaseUrl(final String url) throws ParsingException {
         try {
-            uri = stringToURL(url);
-        } catch (MalformedURLException e) {
+            final URL uri = stringToURL(url);
+            return uri.getProtocol() + "://" + uri.getAuthority();
+        } catch (final MalformedURLException e) {
+            final String message = e.getMessage();
+            if (message.startsWith("unknown protocol: ")) {
+                // return just the protocol (e.g. vnd.youtube)
+                return message.substring("unknown protocol: ".length());
+            }
+
             throw new ParsingException("Malformed url: " + url, e);
         }
-        return uri.getProtocol() + "://" + uri.getAuthority();
+    }
+
+    /**
+     * If the provided url is a Google search redirect, then the actual url is extracted from the
+     * {@code url=} query value and returned, otherwise the original url is returned.
+     * @param url the url which can possibly be a Google search redirect
+     * @return an url with no Google search redirects
+     */
+    public static String followGoogleRedirectIfNeeded(final String url) {
+        // if the url is a redirect from a Google search, extract the actual url
+        try {
+            final URL decoded = Utils.stringToURL(url);
+            if (decoded.getHost().contains("google") && decoded.getPath().equals("/url")) {
+                return URLDecoder.decode(Parser.matchGroup1("&url=([^&]+)(?:&|$)", url), "UTF-8");
+            }
+        } catch (final Exception ignored) {
+        }
+
+        // url is not a google search redirect
+        return url;
     }
 
     public static boolean isNullOrEmpty(final String str) {
diff --git a/extractor/src/test/java/org/schabi/newpipe/extractor/NewPipeTest.java b/extractor/src/test/java/org/schabi/newpipe/extractor/NewPipeTest.java
@@ -6,6 +6,7 @@
 
 import static org.junit.Assert.*;
 import static org.schabi.newpipe.extractor.NewPipe.getServiceByUrl;
+import static org.schabi.newpipe.extractor.ServiceList.SoundCloud;
 import static org.schabi.newpipe.extractor.ServiceList.YouTube;
 
 public class NewPipeTest {
@@ -39,8 +40,10 @@ public void getServiceWithUrl() throws Exception {
         assertEquals(getServiceByUrl("https://www.youtube.com/watch?v=_r6CgaFNAGg"), YouTube);
         assertEquals(getServiceByUrl("https://www.youtube.com/channel/UCi2bIyFtz-JdI-ou8kaqsqg"), YouTube);
         assertEquals(getServiceByUrl("https://www.youtube.com/playlist?list=PLRqwX-V7Uu6ZiZxtDDRCi6uhfTH4FilpH"), YouTube);
+        assertEquals(getServiceByUrl("https://www.google.it/url?sa=t&rct=j&q=&esrc=s&cd=&cad=rja&uact=8&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DHu80uDzh8RY&source=video"), YouTube);
 
-        assertNotEquals(getServiceByUrl("https://soundcloud.com/pegboardnerds"), YouTube);
+        assertEquals(getServiceByUrl("https://soundcloud.com/pegboardnerds"), SoundCloud);
+        assertEquals(getServiceByUrl("https://www.google.com/url?sa=t&url=https%3A%2F%2Fsoundcloud.com%2Fciaoproduction&rct=j&q=&esrc=s&source=web&cd="), SoundCloud);
     }
 
     @Test
diff --git a/extractor/src/test/java/org/schabi/newpipe/extractor/services/soundcloud/SoundcloudStreamLinkHandlerFactoryTest.java b/extractor/src/test/java/org/schabi/newpipe/extractor/services/soundcloud/SoundcloudStreamLinkHandlerFactoryTest.java
@@ -53,13 +53,15 @@ public void getId() throws Exception {
         assertEquals("309689103", linkHandler.fromUrl("https://soundcloud.com/liluzivert/15-ysl").getId());
         assertEquals("309689082", linkHandler.fromUrl("https://www.soundcloud.com/liluzivert/15-luv-scars-ko").getId());
         assertEquals("309689035", linkHandler.fromUrl("http://soundcloud.com/liluzivert/15-boring-shit").getId());
+        assertEquals("259273264", linkHandler.fromUrl("https://soundcloud.com/liluzivert/ps-qs-produced-by-don-cannon/").getId());
         assertEquals("294488599", linkHandler.fromUrl("http://www.soundcloud.com/liluzivert/secure-the-bag-produced-by-glohan-beats").getId());
         assertEquals("294488438", linkHandler.fromUrl("HtTpS://sOuNdClOuD.cOm/LiLuZiVeRt/In-O4-pRoDuCeD-bY-dP-bEaTz").getId());
         assertEquals("294488147", linkHandler.fromUrl("https://soundcloud.com/liluzivert/fresh-produced-by-zaytoven#t=69").getId());
         assertEquals("294487876", linkHandler.fromUrl("https://soundcloud.com/liluzivert/threesome-produced-by-zaytoven#t=1:09").getId());
         assertEquals("294487684", linkHandler.fromUrl("https://soundcloud.com/liluzivert/blonde-brigitte-produced-manny-fresh#t=1:9").getId());
         assertEquals("294487428", linkHandler.fromUrl("https://soundcloud.com/liluzivert/today-produced-by-c-note#t=1m9s").getId());
         assertEquals("294487157", linkHandler.fromUrl("https://soundcloud.com/liluzivert/changed-my-phone-produced-by-c-note#t=1m09s").getId());
+        assertEquals("44556776", linkHandler.fromUrl("https://soundcloud.com/kechuspider-sets-1/last-days").getId());
     }
 
 
diff --git a/extractor/src/test/java/org/schabi/newpipe/extractor/utils/UtilsTest.java b/extractor/src/test/java/org/schabi/newpipe/extractor/utils/UtilsTest.java
@@ -21,4 +21,28 @@ public void testMixedNumberWordToLong() throws ParsingException {
     public void testJoin() {
         assertEquals("some,random,stuff", Utils.join(",", Arrays.asList("some", "random", "stuff")));
     }
+
+    @Test
+    public void testGetBaseUrl() throws ParsingException {
+        assertEquals("https://www.youtube.com", Utils.getBaseUrl("https://www.youtube.com/watch?v=Hu80uDzh8RY"));
+        assertEquals("vnd.youtube", Utils.getBaseUrl("vnd.youtube://www.youtube.com/watch?v=jZViOEv90dI"));
+        assertEquals("vnd.youtube", Utils.getBaseUrl("vnd.youtube:jZViOEv90dI"));
+        assertEquals("vnd.youtube", Utils.getBaseUrl("vnd.youtube://n8X9_MgEdCg"));
+        assertEquals("https://music.youtube.com", Utils.getBaseUrl("https://music.youtube.com/watch?v=O0EDx9WAelc"));
+    }
+
+    @Test
+    public void testFollowGoogleRedirect() {
+        assertEquals("https://www.youtube.com/watch?v=Hu80uDzh8RY",
+                Utils.followGoogleRedirectIfNeeded("https://www.google.it/url?sa=t&rct=j&q=&esrc=s&cd=&cad=rja&uact=8&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DHu80uDzh8RY&source=video"));
+        assertEquals("https://www.youtube.com/watch?v=0b6cFWG45kA",
+                Utils.followGoogleRedirectIfNeeded("https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=video&cd=&cad=rja&uact=8&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3D0b6cFWG45kA"));
+        assertEquals("https://soundcloud.com/ciaoproduction",
+                Utils.followGoogleRedirectIfNeeded("https://www.google.com/url?sa=t&url=https%3A%2F%2Fsoundcloud.com%2Fciaoproduction&rct=j&q=&esrc=s&source=web&cd="));
+
+        assertEquals("https://www.youtube.com/watch?v=Hu80uDzh8RY&param=xyz",
+                Utils.followGoogleRedirectIfNeeded("https://www.youtube.com/watch?v=Hu80uDzh8RY&param=xyz"));
+        assertEquals("https://www.youtube.com/watch?v=Hu80uDzh8RY&url=hello",
+                Utils.followGoogleRedirectIfNeeded("https://www.youtube.com/watch?v=Hu80uDzh8RY&url=hello"));
+    }
 }
