Merge branch 'master' into fix-yt-dlp-typo-too

.github/workflows/maven.yml

@@ -10,7 +10,7 @@ jobs:
   build:
     strategy:
       matrix:
-        jdk: [8, 11, 17, 19]
+        jdk: [8, 11, 17, 21]
     runs-on: ubuntu-latest
     timeout-minutes: 30
 

contrib/src/main/java/org/archive/modules/extractor/ExtractorYoutubeDL.java

@@ -63,8 +63,7 @@ import com.google.gson.stream.JsonReader;
 import com.google.gson.stream.JsonToken;
 
 /**
- * Extracts links to media by running youtube-dl in a subprocess. Runs only on
- * html.
+ * Extracts links to media by running yt-dlp in a subprocess. Runs only on html.
  *
  * <p>
  * Also implements {@link WARCRecordBuilder} to write youtube-dl json to the
@@ -436,11 +435,11 @@ public class ExtractorYoutubeDL extends Extractor
      */
     protected YoutubeDLResults runYoutubeDL(CrawlURI uri) {
         /*
-         * --format=best
-         *
-         * best: Select the best quality format represented by a single file
-         * with video and audio.
-         * https://github.com/ytdl-org/youtube-dl/blob/master/README.md#format-selection
+         * https://github.com/yt-dlp/yt-dlp#format-selection-examples
+         * updated for yt-dlp v.2023.07.06 and higher
+         * Download the best video with best vcodec no better than h264 and
+         * the best audio with best acodec no better than aac and
+         * with neither height nor width larger than 576.
          */
         ProcessBuilder pb = new ProcessBuilder("yt-dlp", "--ignore-config",
                 "--simulate", "--dump-single-json", "-S vcodec:h264,res:576,acodec:aac",

modules/pom.xml

@@ -30,12 +30,12 @@
 			<scope>compile</scope>
 		</dependency>
 		<dependency>
-			<groupId>org.codehaus.groovy</groupId>
+			<groupId>org.apache.groovy</groupId>
 			<artifactId>groovy-jsr223</artifactId>
 			<version>${groovy.version}</version>
 		</dependency>
 		<dependency>
-			<groupId>org.codehaus.groovy</groupId>
+			<groupId>org.apache.groovy</groupId>
 			<artifactId>groovy-templates</artifactId>
 			<version>${groovy.version}</version>
 		</dependency>
@@ -115,6 +115,6 @@
 	</build>
 	<properties>
 		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-		<groovy.version>3.0.13</groovy.version>
+		<groovy.version>4.0.15</groovy.version>
 	</properties>
 </project>