Skip to content

Commit

Permalink
Switch to Crawl 2024-42
Browse files Browse the repository at this point in the history
  • Loading branch information
centic9 committed Nov 9, 2024
1 parent 0cf8f5f commit 6bce5fe
Showing 1 changed file with 2 additions and 2 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,8 @@
public class DownloadURLIndex {
private static final Logger log = LoggerFactory.make();

// https://commoncrawl.org/connect/blog/
public static final String CURRENT_CRAWL = "CC-MAIN-2023-23";
// https://commoncrawl.org/blog/
public static final String CURRENT_CRAWL = "CC-MAIN-2024-42";
public static final File COMMON_CRAWL_FILE = new File("commoncrawl-" + CURRENT_CRAWL + ".txt");

private static final int START_INDEX = 0;
Expand Down

0 comments on commit 6bce5fe

Please sign in to comment.