Skip to content
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

Jump to bottom

ARD: ignore zdf entries #964

Merged
merged 1 commit into from
Mar 4, 2024
Merged

ARD: ignore zdf entries #964

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 29 additions & 6 deletions src/main/java/mServer/crawler/sender/ard/json/ArdTopicsLetterDeserializer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
import mServer.crawler.sender.base.JsonUtils;

import java.lang.reflect.Type;
import java.util.Arrays;
import java.util.HashSet;
import java.util.Optional;
import java.util.Set;
Expand All @@ -23,9 +24,13 @@ public class ArdTopicsLetterDeserializer implements JsonDeserializer<PaginationU
private static final String ELEMENT_TOTAL_ELEMENTS = "totalElements";
private static final String ELEMENT_PAGE_SIZE = "pageSize";
private static final String ELEMENT_PAGINATION = "pagination";
private static final String ELEMENT_PUBLICATION_SERVICE = "publicationService";
private static final String ATTRIBUTE_NAME = "name";

private static final String ATTRIBUTE_ID = "id";

private static final String[] IGNORED_SENDER = new String[] {"zdf", "kika", "3sat", "arte"};

@Override
public PaginationUrlDto deserialize(
final JsonElement jsonElement, final Type type, final JsonDeserializationContext context) {
Expand Down Expand Up @@ -79,13 +84,31 @@ private Set<CrawlerUrlDTO> parseTeaser(final JsonObject teaserObject) {
id = JsonUtils.getAttributeAsString(teaserObject, ATTRIBUTE_ID);
}

id.ifPresent(
nonNullId ->
results.add(
new CrawlerUrlDTO(
String.format(
ArdConstants.TOPIC_URL, nonNullId, ArdConstants.TOPIC_PAGE_SIZE))));
if (isRelevant(teaserObject)) {
id.ifPresent(
nonNullId ->
results.add(
new CrawlerUrlDTO(
String.format(
ArdConstants.TOPIC_URL, nonNullId, ArdConstants.TOPIC_PAGE_SIZE))));
}

return results;
}

private boolean isRelevant(final JsonObject teaserObject) {
if (teaserObject.has(ELEMENT_PUBLICATION_SERVICE)) {
final JsonObject publicationService =
teaserObject.get(ELEMENT_PUBLICATION_SERVICE).getAsJsonObject();
final Optional<String> attributeAsString =
JsonUtils.getAttributeAsString(publicationService, ATTRIBUTE_NAME);
if (attributeAsString.isPresent()) {

return !Arrays.stream(IGNORED_SENDER)
.anyMatch(sender -> sender.equalsIgnoreCase(attributeAsString.get()));
}
}

return true;
}
}
Loading