Merge pull request #2390 from jump-oss/fix/feed-discovery-redirect

Fix feed discovery after HTML redirects
This commit is contained in:
Jérémie Panzer
2026-11-13 08:25:01 +01:00
committed by GitHub
2 changed files with 39 additions and 1 deletions

View File

@@ -66,7 +66,10 @@ public class FeedFetcher {
} catch (FeedParsingException e) {
if (extractFeedUrlFromHtml) {
String extractedUrl =
extractFeedUrl(urlProviders, feedUrl, new String(result.content(), StandardCharsets.UTF_8));
extractFeedUrl(
urlProviders,
result.urlAfterRedirect(),
new String(result.content(), StandardCharsets.UTF_8));
if (StringUtils.isNotBlank(extractedUrl)) {
feedUrl = extractedUrl;

View File

@@ -9,15 +9,19 @@ import com.commafeed.backend.feed.parser.FeedParser;
import com.commafeed.backend.feed.parser.FeedParser.FeedParsingException;
import com.commafeed.backend.feed.parser.FeedParserResult;
import com.commafeed.backend.urlprovider.FeedURLProvider;
import com.commafeed.backend.urlprovider.InPageReferenceFeedURLProvider;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.extension.ExtendWith;
import org.junit.jupiter.params.ParameterizedTest;
import org.junit.jupiter.params.provider.CsvSource;
import org.mockito.Mock;
import org.mockito.Mockito;
import org.mockito.junit.jupiter.MockitoExtension;
import java.nio.charset.StandardCharsets;
import java.time.Duration;
import java.time.Instant;
import java.util.List;
@@ -59,6 +63,37 @@ class FeedFetcherTest {
Assertions.assertEquals("title", result.feed().title());
}
@ParameterizedTest
@CsvSource({
"https://example.com/blog/, feed.xml, https://example.com/blog/feed.xml",
"https://other.example.com/blog/, feed.xml, https://other.example.com/blog/feed.xml",
"https://other.example.com/blog/, /feed.xml, https://other.example.com/feed.xml",
"https://example.com/blog/, https://feeds.example.com/rss, https://feeds.example.com/rss"
})
void findsUrlInRedirectedPage(String redirectedUrl, String href, String expectedFeedUrl) throws Exception {
String originalUrl = "https://example.com/start";
byte[] html =
"<html><head><link type='application/rss+xml' href='%s'></head></html>"
.formatted(href)
.getBytes(StandardCharsets.UTF_8);
Mockito.when(getter.get(HttpGetter.HttpRequest.builder(originalUrl).build()))
.thenReturn(new HttpResult(html, "text/html", null, null, redirectedUrl, Duration.ZERO));
Mockito.when(parser.parse(redirectedUrl, html)).thenThrow(new FeedParsingException("invalid feed"));
byte[] feed = "feed".getBytes(StandardCharsets.UTF_8);
Mockito.when(getter.get(HttpGetter.HttpRequest.builder(expectedFeedUrl).build()))
.thenReturn(new HttpResult(feed, "application/rss+xml", null, null, expectedFeedUrl, Duration.ZERO));
FeedParserResult parsedFeed = new FeedParserResult("title", "link", "iconUrl", null, null, null, null);
Mockito.when(parser.parse(expectedFeedUrl, feed)).thenReturn(parsedFeed);
FeedFetcher redirectedFetcher = new FeedFetcher(parser, getter, List.of(new InPageReferenceFeedURLProvider()));
FeedFetcherResult result = redirectedFetcher.fetch(originalUrl, true, null, null, null, null);
Assertions.assertEquals(parsedFeed, result.feed());
Assertions.assertEquals(expectedFeedUrl, result.urlAfterRedirect());
Mockito.verify(getter).get(HttpGetter.HttpRequest.builder(expectedFeedUrl).build());
}
@Test
void updatesHeaderWhenContentDitNotChange() throws Exception {
String url = "https://aaa.com";