Skip to content

ExtractorYoutubeDL: skip YouTube super resolution videos #708

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mistydemeo wants to merge 2 commits into
base: master
Choose a base branch
from
Open

ExtractorYoutubeDL: skip YouTube super resolution videos #708

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
49d6c5d
ExtractorYoutubeDL: skip YouTube super resolution videos
mistydemeo Jan 30, 2026
3e19a24
ExtractorYoutubeDL: configuration for skipping -sr
mistydemeo Jan 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 34 additions & 1 deletion contrib/src/main/java/org/archive/modules/extractor/ExtractorYoutubeDL.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,6 +207,19 @@ public void setProcessArguments(List<String> processArguments) {
kp.put("processArguments", processArguments);
}

{
setSkipSuperResolution(false);
}
public boolean getSkipSuperResolution() {
return (Boolean) kp.get("skipSuperResolution");
}
/**
* Whether or not to download Super Resolution upscaled videos.
*/
public void setSkipSuperResolution(boolean skipSuperResolution) {
kp.put("skipSuperResolution",skipSuperResolution);
}

@Override
public void start() {
if (!isRunning) {
Expand Down Expand Up @@ -420,6 +433,11 @@ public void write(int b) throws IOException {}
*/
protected void streamYdlOutput(InputStream in, YoutubeDLResults results) throws IOException {
TeedInputStream tee = new TeedInputStream(in, results.jsonFile);
// Since we read objects a single field at a time, we can't
// skip the entire object in one action; this lets us track
// whether we should ignore subsequent fields from the same
// object.
boolean skipObject = false;
try (JsonReader jsonReader = new JsonReader(new InputStreamReader(tee, "UTF-8"))) {
while (true) {
JsonToken nextToken = jsonReader.peek();
Expand All @@ -440,6 +458,7 @@ protected void streamYdlOutput(InputStream in, YoutubeDLResults results) throws
return;
case END_OBJECT:
jsonReader.endObject();
skipObject = false;
break;
case NAME:
jsonReader.nextName();
Expand All @@ -451,8 +470,22 @@ protected void streamYdlOutput(InputStream in, YoutubeDLResults results) throws
jsonReader.nextString();
break;
case STRING:
if (skipObject) {
break;
}

String value = jsonReader.nextString();
if ("$.url".equals(jsonReader.getPath())
// Format IDs ending with -sr are YouTube "Super Resolution"
// upscaled videos; if requested, avoid downloading these in
// favour of the original files.
// https://alexwlchan.net/til/2025/ignore-ai-scaled-videos/
if ("$.format_id".equals(jsonReader.getPath())
|| jsonReader.getPath().matches("^\\$\\.entries\\[\\d+\\]\\.format_id$")) {
if (value.endsWith("-sr") && getSkipSuperResolution()) {
skipObject = true;
break;
}
} else if ("$.url".equals(jsonReader.getPath())
|| jsonReader.getPath().matches("^\\$\\.entries\\[\\d+\\]\\.url$")) {
results.videoUrls.add(value);
} else if ("$.webpage_url".equals(jsonReader.getPath())
Expand Down