CypherpunkSamurai/NewPipeExtractor
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Faster iframe api based player extraction. (#694)

Browse source 
* Faster iframe api based player extraction.

Uses the IFrame API to reduce the required download to less than 1/50 of the size.

* Remove debug code.

* Extract to two methods.

* Add tests for player URL extraction.

* Add assertThat for tests.
This commit is contained in:
FireMasterK 2021-08-07 16:05:48 +05:30 committed by GitHub
parent 4b147863ec
commit 71b9fd0076
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 36 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/YoutubeJavaScriptExtractor.java
View file

@ -39,8 +39,13 @@ public class YoutubeJavaScriptExtractor {
@Nonnull
public static String extractJavaScriptCode(final String videoId) throws ParsingException {
if (cachedJavaScriptCode == null) {
final String playerJsUrl = YoutubeJavaScriptExtractor.cleanJavaScriptUrl(
YoutubeJavaScriptExtractor.extractJavaScriptUrl(videoId));
String url;
try {
url = YoutubeJavaScriptExtractor.extractJavaScriptUrl();
} catch (final Exception i) {
url = YoutubeJavaScriptExtractor.extractJavaScriptUrl(videoId);
}
final String playerJsUrl = YoutubeJavaScriptExtractor.cleanJavaScriptUrl(url);
cachedJavaScriptCode = YoutubeJavaScriptExtractor.downloadJavaScriptCode(playerJsUrl);
}
@ -68,7 +73,22 @@ public class YoutubeJavaScriptExtractor {
cachedJavaScriptCode = null;
}
private static String extractJavaScriptUrl(final String videoId) throws ParsingException {
public static String extractJavaScriptUrl() throws ParsingException {
try {
final String iframeUrl = "https://www.youtube.com/iframe_api";
final String iframeContent = NewPipe.getDownloader()
.get(iframeUrl, Localization.DEFAULT).responseBody();
final String hashPattern = "player\\\\\\/([a-z0-9]{8})\\\\\\/";
final String hash = Parser.matchGroup1(hashPattern, iframeContent);
return String.format("https://www.youtube.com/s/player/%s/player_ias.vflset/en_US/base.js", hash);
} catch (final Exception i) { }
throw new ParsingException("Iframe API did not provide YouTube player js url");
}
public static String extractJavaScriptUrl(final String videoId) throws ParsingException {
try {
final String embedUrl = "https://www.youtube.com/embed/" + videoId;
final String embedPageContent = NewPipe.getDownloader()
@ -90,9 +110,8 @@ public class YoutubeJavaScriptExtractor {
}
}
} catch (final Exception i) {
throw new ParsingException("Embedded info did not provide YouTube player js url");
}
} catch (final Exception i) { }
throw new ParsingException("Embedded info did not provide YouTube player js url");
}

13
extractor/src/test/java/org/schabi/newpipe/extractor/services/youtube/YoutubeJavaScriptExtractorTest.java
View file

@ -8,8 +8,7 @@ import org.schabi.newpipe.extractor.exceptions.ParsingException;
import java.io.IOException;
import static org.hamcrest.CoreMatchers.allOf;
import static org.hamcrest.CoreMatchers.containsString;
import static org.hamcrest.CoreMatchers.*;
import static org.hamcrest.MatcherAssert.assertThat;
public class YoutubeJavaScriptExtractorTest {
@ -19,6 +18,16 @@ public class YoutubeJavaScriptExtractorTest {
NewPipe.init(DownloaderTestImpl.getInstance());
}
@Test
public void testExtractJavaScriptUrlIframe() throws ParsingException {
assertThat(YoutubeJavaScriptExtractor.extractJavaScriptUrl(), endsWith("base.js"));
}
@Test
public void testExtractJavaScriptUrlEmbed() throws ParsingException {
assertThat(YoutubeJavaScriptExtractor.extractJavaScriptUrl("d4IGg5dqeO8"), endsWith("base.js"));
}
@Test
public void testExtractJavaScript__success() throws ParsingException {
String playerJsCode = YoutubeJavaScriptExtractor.extractJavaScriptCode("d4IGg5dqeO8");