Skip to content

Commit 2ee558f

Browse files
TobiGrTobiGr
authored
Merge pull request #237 from B0pol/fix_invidious_comments
Fix invidious comments
2 parents 5a259fc + 221e8dd commit 2ee558f

2 files changed

Lines changed: 43 additions & 88 deletions

File tree

‎extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/linkHandler/YoutubeCommentsLinkHandlerFactory.java‎

Lines changed: 10 additions & 74 deletions
Original file line numberDiff line numberDiff line change
@@ -1,18 +1,14 @@
11
package org.schabi.newpipe.extractor.services.youtube.linkHandler;
22

3-
import java.io.UnsupportedEncodingException;
4-
import java.net.URLDecoder;
5-
import java.util.List;
6-
73
import org.schabi.newpipe.extractor.exceptions.FoundAdException;
84
import org.schabi.newpipe.extractor.exceptions.ParsingException;
95
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandlerFactory;
10-
import org.schabi.newpipe.extractor.utils.Parser;
6+
7+
import java.util.List;
118

129
public class YoutubeCommentsLinkHandlerFactory extends ListLinkHandlerFactory {
1310

1411
private static final YoutubeCommentsLinkHandlerFactory instance = new YoutubeCommentsLinkHandlerFactory();
15-
private static final String ID_PATTERN = "([\\-a-zA-Z0-9_]{11})";
1612

1713
public static YoutubeCommentsLinkHandlerFactory getInstance() {
1814
return instance;
@@ -24,78 +20,18 @@ public String getUrl(String id) {
2420
}
2521

2622
@Override
27-
public String getId(String url) throws ParsingException, IllegalArgumentException {
28-
if (url.isEmpty()) {
29-
throw new IllegalArgumentException("The url parameter should not be empty");
30-
}
31-
32-
String id;
33-
String lowercaseUrl = url.toLowerCase();
34-
if (lowercaseUrl.contains("youtube")) {
35-
if (url.contains("attribution_link")) {
36-
try {
37-
String escapedQuery = Parser.matchGroup1("u=(.[^&|$]*)", url);
38-
String query = URLDecoder.decode(escapedQuery, "UTF-8");
39-
id = Parser.matchGroup1("v=" + ID_PATTERN, query);
40-
} catch (UnsupportedEncodingException uee) {
41-
throw new ParsingException("Could not parse attribution_link", uee);
42-
}
43-
} else if (url.contains("vnd.youtube")) {
44-
id = Parser.matchGroup1(ID_PATTERN, url);
45-
} else if (url.contains("embed")) {
46-
id = Parser.matchGroup1("embed/" + ID_PATTERN, url);
47-
} else if (url.contains("googleads")) {
48-
throw new FoundAdException("Error found add: " + url);
49-
} else {
50-
id = Parser.matchGroup1("[?&]v=" + ID_PATTERN, url);
51-
}
52-
} else if (lowercaseUrl.contains("youtu.be")) {
53-
if (url.contains("v=")) {
54-
id = Parser.matchGroup1("v=" + ID_PATTERN, url);
55-
} else {
56-
id = Parser.matchGroup1("[Yy][Oo][Uu][Tt][Uu]\\.[Bb][Ee]/" + ID_PATTERN, url);
57-
}
58-
} else if(lowercaseUrl.contains("hooktube")) {
59-
if(lowercaseUrl.contains("&v=")
60-
|| lowercaseUrl.contains("?v=")) {
61-
id = Parser.matchGroup1("[?&]v=" + ID_PATTERN, url);
62-
} else if (url.contains("/embed/")) {
63-
id = Parser.matchGroup1("embed/" + ID_PATTERN, url);
64-
} else if (url.contains("/v/")) {
65-
id = Parser.matchGroup1("v/" + ID_PATTERN, url);
66-
} else if (url.contains("/watch/")) {
67-
id = Parser.matchGroup1("watch/" + ID_PATTERN, url);
68-
} else {
69-
throw new ParsingException("Error no suitable url: " + url);
70-
}
71-
} else {
72-
throw new ParsingException("Error no suitable url: " + url);
73-
}
74-
75-
76-
if (!id.isEmpty()) {
77-
return id;
78-
} else {
79-
throw new ParsingException("Error could not parse url: " + url);
80-
}
23+
public String getId(String urlString) throws ParsingException, IllegalArgumentException {
24+
return YoutubeStreamLinkHandlerFactory.getInstance().getId(urlString); //we need the same id, avoids duplicate code
8125
}
8226

8327
@Override
8428
public boolean onAcceptUrl(final String url) throws FoundAdException {
85-
final String lowercaseUrl = url.toLowerCase();
86-
if (lowercaseUrl.contains("youtube")
87-
|| lowercaseUrl.contains("youtu.be")
88-
|| lowercaseUrl.contains("hooktube")) {
89-
// bad programming I know
90-
try {
91-
getId(url);
92-
return true;
93-
} catch (FoundAdException fe) {
94-
throw fe;
95-
} catch (ParsingException e) {
96-
return false;
97-
}
98-
} else {
29+
try {
30+
getId(url);
31+
return true;
32+
} catch (FoundAdException fe) {
33+
throw fe;
34+
} catch (ParsingException e) {
9935
return false;
10036
}
10137
}

‎extractor/src/test/java/org/schabi/newpipe/extractor/services/youtube/YoutubeCommentsExtractorTest.java‎

Lines changed: 33 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,6 @@
44
import org.junit.BeforeClass;
55
import org.junit.Test;
66
import org.schabi.newpipe.DownloaderTestImpl;
7-
import org.schabi.newpipe.DownloaderTestImpl;
87
import org.schabi.newpipe.extractor.ListExtractor.InfoItemsPage;
98
import org.schabi.newpipe.extractor.NewPipe;
109
import org.schabi.newpipe.extractor.comments.CommentsInfo;
@@ -21,17 +20,32 @@
2120

2221
public class YoutubeCommentsExtractorTest {
2322

24-
private static YoutubeCommentsExtractor extractor;
23+
private static final String urlYT = "https://www.youtube.com/watch?v=D00Au7k3i6o";
24+
private static final String urlInvidious = "https://invidio.us/watch?v=D00Au7k3i6o";
25+
private static final String urlInvidioush = "https://invidiou.sh/watch?v=D00Au7k3i6o";
26+
private static YoutubeCommentsExtractor extractorYT;
27+
private static YoutubeCommentsExtractor extractorInvidious;
28+
private static YoutubeCommentsExtractor extractorInvidioush;
2529

2630
@BeforeClass
2731
public static void setUp() throws Exception {
2832
NewPipe.init(DownloaderTestImpl.getInstance());
29-
extractor = (YoutubeCommentsExtractor) YouTube
30-
.getCommentsExtractor("https://www.youtube.com/watch?v=D00Au7k3i6o");
33+
extractorYT = (YoutubeCommentsExtractor) YouTube
34+
.getCommentsExtractor(urlYT);
35+
extractorInvidious = (YoutubeCommentsExtractor) YouTube
36+
.getCommentsExtractor(urlInvidious);
37+
extractorInvidioush = (YoutubeCommentsExtractor) YouTube
38+
.getCommentsExtractor(urlInvidioush);
3139
}
3240

3341
@Test
3442
public void testGetComments() throws IOException, ExtractionException {
43+
assertTrue(getCommentsHelper(extractorYT));
44+
assertTrue(getCommentsHelper(extractorInvidious));
45+
assertTrue(getCommentsHelper(extractorInvidioush));
46+
}
47+
48+
private boolean getCommentsHelper(YoutubeCommentsExtractor extractor) throws IOException, ExtractionException {
3549
boolean result;
3650
InfoItemsPage<CommentsInfoItem> comments = extractor.getInitialPage();
3751
result = findInComments(comments, "s1ck m3m3");
@@ -41,14 +55,20 @@ public void testGetComments() throws IOException, ExtractionException {
4155
result = findInComments(comments, "s1ck m3m3");
4256
}
4357

44-
assertTrue(result);
58+
return result;
4559
}
4660

4761
@Test
4862
public void testGetCommentsFromCommentsInfo() throws IOException, ExtractionException {
63+
assertTrue(getCommentsFromCommentsInfoHelper(urlYT));
64+
assertTrue(getCommentsFromCommentsInfoHelper(urlInvidious));
65+
assertTrue(getCommentsFromCommentsInfoHelper(urlInvidioush));
66+
}
67+
68+
private boolean getCommentsFromCommentsInfoHelper(String url) throws IOException, ExtractionException {
4969
boolean result = false;
50-
CommentsInfo commentsInfo = CommentsInfo.getInfo("https://www.youtube.com/watch?v=D00Au7k3i6o");
51-
assertTrue("what the fuck am i doing with my life".equals(commentsInfo.getName()));
70+
CommentsInfo commentsInfo = CommentsInfo.getInfo(url);
71+
assertEquals("what the fuck am i doing with my life", commentsInfo.getName());
5272
result = findInComments(commentsInfo.getRelatedItems(), "s1ck m3m3");
5373

5474
String nextPage = commentsInfo.getNextPageUrl();
@@ -57,16 +77,15 @@ public void testGetCommentsFromCommentsInfo() throws IOException, ExtractionExce
5777
result = findInComments(moreItems.getItems(), "s1ck m3m3");
5878
nextPage = moreItems.getNextPageUrl();
5979
}
60-
61-
assertTrue(result);
80+
return result;
6281
}
63-
82+
6483
@Test
6584
public void testGetCommentsAllData() throws IOException, ExtractionException {
66-
InfoItemsPage<CommentsInfoItem> comments = extractor.getInitialPage();
85+
InfoItemsPage<CommentsInfoItem> comments = extractorYT.getInitialPage();
6786

6887
DefaultTests.defaultTestListOfItems(YouTube.getServiceId(), comments.getItems(), comments.getErrors());
69-
for(CommentsInfoItem c: comments.getItems()) {
88+
for (CommentsInfoItem c : comments.getItems()) {
7089
assertFalse(StringUtil.isBlank(c.getAuthorEndpoint()));
7190
assertFalse(StringUtil.isBlank(c.getAuthorName()));
7291
assertFalse(StringUtil.isBlank(c.getAuthorThumbnail()));
@@ -86,8 +105,8 @@ private boolean findInComments(InfoItemsPage<CommentsInfoItem> comments, String
86105
}
87106

88107
private boolean findInComments(List<CommentsInfoItem> comments, String comment) {
89-
for(CommentsInfoItem c: comments) {
90-
if(c.getCommentText().contains(comment)) {
108+
for (CommentsInfoItem c : comments) {
109+
if (c.getCommentText().contains(comment)) {
91110
return true;
92111
}
93112
}

0 commit comments

Comments
 (0)