Skip to content

Give the caller the possibility to access the actual effective URL used for fetching a resource #1982

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

Draft
lfoppiano wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Give the caller the possibility to access the actual effective URL used for fetching a resource #1982

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5c0dc82
feat: make request URL available to the caller. This could be useful …
lfoppiano Jun 17, 2026
918e951
chore: reformat
lfoppiano Jun 22, 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
11 changes: 11 additions & 0 deletions core/src/main/java/org/apache/stormcrawler/protocol/ProtocolResponse.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@

package org.apache.stormcrawler.protocol;

import java.net.URL;
import org.apache.stormcrawler.Metadata;

public class ProtocolResponse {
Expand Down Expand Up @@ -81,11 +82,17 @@ public enum TrimmedContentReason {
private final byte[] content;
private final int statusCode;
private final Metadata metadata;
private final URL url;

public ProtocolResponse(byte[] c, int s, Metadata md) {
this(c, s, md, null);
}

public ProtocolResponse(byte[] c, int s, Metadata md, URL url) {
content = c;
statusCode = s;
metadata = md == null ? new Metadata() : md;
this.url = url;
}

public byte[] getContent() {
Expand All @@ -99,4 +106,8 @@ public int getStatusCode() {
public Metadata getMetadata() {
return metadata;
}

public URL getUrl() {
return url;
}
}
5 changes: 3 additions & 2 deletions core/src/main/java/org/apache/stormcrawler/protocol/file/FileResponse.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,14 +44,15 @@ public class FileResponse {
private byte[] content;
private int statusCode;
private final Metadata metadata;
private final URL url;

public FileResponse(String u, Metadata md, FileProtocol fileProtocol) throws IOException {

metadata = new Metadata();
content = new byte[0];
statusCode = HttpStatus.SC_INTERNAL_SERVER_ERROR;

URL url = URLUtil.toURL(u);
this.url = URLUtil.toURL(u);

if (!url.getPath().equals(url.getFile())) {
LOG.warn("url.getPath() != url.getFile(): {}.", url);
Expand Down Expand Up @@ -125,7 +126,7 @@ public FileResponse(String u, Metadata md, FileProtocol fileProtocol) throws IOE
}

public ProtocolResponse toProtocolResponse() {
return new ProtocolResponse(content, statusCode, metadata);
return new ProtocolResponse(content, statusCode, metadata, this.url);
}

private void getFileAsHttpResponse(File file) {
Expand Down
3 changes: 2 additions & 1 deletion core/src/main/java/org/apache/stormcrawler/protocol/okhttp/HttpProtocol.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -520,7 +520,8 @@ public ProtocolResponse getProtocolOutput(String url, final Metadata metadata)
responsemetadata.setValue("metrics.dns.resolution.msec", dnsResolution.toString());
}

return new ProtocolResponse(bytes, response.code(), responsemetadata);
return new ProtocolResponse(
bytes, response.code(), responsemetadata, request.url().url());
}
}

Expand Down
4 changes: 3 additions & 1 deletion ...al/playwright/src/main/java/org/apache/stormcrawler/protocol/playwright/HttpProtocol.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@
import org.apache.stormcrawler.protocol.Protocol;
import org.apache.stormcrawler.protocol.ProtocolResponse;
import org.apache.stormcrawler.util.ConfUtils;
import org.apache.stormcrawler.util.URLUtil;
import org.slf4j.LoggerFactory;

public class HttpProtocol extends AbstractHttpProtocol {
Expand Down Expand Up @@ -318,7 +319,8 @@ public ProtocolResponse getProtocolOutput(String url, Metadata md) throws Except

responseMetaData.addValue(MD_KEY_END, Instant.now().toString());

return new ProtocolResponse(content, status.get(), responseMetaData);
return new ProtocolResponse(
content, status.get(), responseMetaData, URLUtil.toURL(url));

} finally {
if (isTracing && responseMetaData.getFirstValue(MD_TRACE) == null) {
Expand Down