Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-24 05:18:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Minor: Better error handling in crawled domain reader

Browse Source
This commit is contained in:
Viktor Lofgren 2023-07-07 19:44:57 +02:00
parent 040bea1f75
commit 17db23c2c1
2 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
code/process-models/crawling-model/src/main/java/nu/marginalia/crawling/io/CrawledDomainReader.java
View File

@ -64,7 +64,7 @@ public class CrawledDomainReader {
return Optional.of(read(path)); return Optional.of(read(path));
} }
catch (Exception ex) { catch (Exception ex) {
logger.warn("Failed to read domain", ex); logger.warn("Failed to read domain " + path, ex);
return Optional.empty(); return Optional.empty();
} }
} }

2
code/tools/crawl-job-extractor/src/main/java/nu/marginalia/crawl/CrawlJobExtractorMain.java
View File

@ -1,6 +1,5 @@
package nu.marginalia.crawl; package nu.marginalia.crawl;
import com.zaxxer.hikari.HikariDataSource;
import nu.marginalia.crawling.model.spec.CrawlingSpecification; import nu.marginalia.crawling.model.spec.CrawlingSpecification;
import nu.marginalia.model.EdgeDomain; import nu.marginalia.model.EdgeDomain;
import nu.marginalia.db.DomainBlacklistImpl; import nu.marginalia.db.DomainBlacklistImpl;
@ -10,7 +9,6 @@ import nu.marginalia.service.module.DatabaseModule;
import java.io.IOException; import java.io.IOException;
import java.nio.file.Files; import java.nio.file.Files;
import java.nio.file.Path; import java.nio.file.Path;
import java.sql.SQLException;
import java.util.*; import java.util.*;
import java.util.stream.Stream; import java.util.stream.Stream;