ytdlp: add dubbed audio streams

internetarchive · Sep 10, 2024 · 5178cb3 · 5178cb3
1 parent 59c402f
commit 5178cb3
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/internal/pkg/crawl/dependencies/ytdlp/ytdlp.go b/internal/pkg/crawl/dependencies/ytdlp/ytdlp.go
@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"os/exec"
 	"strconv"
+	"strings"
 )
 
 func GetJSON(port int) (URLs []string, rawJSON string, HTTPHeaders HTTPHeaders, err error) {
@@ -56,6 +57,13 @@ func GetJSON(port int) (URLs []string, rawJSON string, HTTPHeaders HTTPHeaders,
 		}
 	}
 
+	// Get all dubbed audio URLs
+	for _, audio := range video.Formats {
+		if strings.Contains(audio.FormatNote, "dubbed") {
+			URLs = append(URLs, audio.URL, audio.URL+"&video_id="+video.ID)
+		}
+	}
+
 	// write output to a .json file (debug)
 	// err = ioutil.WriteFile("output.json", []byte(output), 0644)
 	// if err != nil {

diff --git a/internal/pkg/crawl/sitespecific/youtube/youtube_test.go b/internal/pkg/crawl/sitespecific/youtube/youtube_test.go
@@ -25,7 +25,7 @@ func TestParse(t *testing.T) {
 	}
 
 	// Check the number of URLs
-	expected := 148
+	expected := 204
 	if len(URLs) != expected {
 		t.Fatalf("Expected %d URLs, got %d", expected, len(URLs))
 	}