Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-23 13:09:00 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

(crawler) Properly enqueue links from the root document in the crawler

Browse Source
This commit is contained in:
Viktor Lofgren 2024-10-05 17:55:59 +02:00
parent eb60ddb729
commit 01a16ff388
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
code/processes/crawling-process/java/nu/marginalia/crawl/CrawlerMain.java
View File

@ -222,7 +222,7 @@ public class CrawlerMain extends ProcessMainClass {
WarcArchiverIf warcArchiver = warcArchiverFactory.get(outputDir); WarcArchiverIf warcArchiver = warcArchiverFactory.get(outputDir);
AnchorTagsSource anchorTagsSource = anchorTagsSourceFactory.create(List.of(new EdgeDomain(targetDomainName))) AnchorTagsSource anchorTagsSource = anchorTagsSourceFactory.create(List.of(new EdgeDomain(targetDomainName)))
) { ) {
var spec = new CrawlSpecProvider.CrawlSpecRecord(targetDomainName, 1000, null); var spec = new CrawlSpecProvider.CrawlSpecRecord(targetDomainName, 1000, List.of());
var task = new CrawlTask(spec, anchorTagsSource, outputDir, warcArchiver, workLog); var task = new CrawlTask(spec, anchorTagsSource, outputDir, warcArchiver, workLog);
task.run(); task.run();
} }