Mercurial > hg > cc > cirrus_work
changeset 340:af5ee299cbbe trim
use WARC.REQ for URI for crawldiagnostics too
| author | Henry S. Thompson <ht@inf.ed.ac.uk> |
|---|---|
| date | Wed, 04 Mar 2026 21:11:38 +0000 |
| parents | a2918f19d9ed |
| children | 6d0e29e22b12 |
| files | lib/python/cc/lmh/warc2cdb.py |
| diffstat | 1 files changed, 1 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- a/lib/python/cc/lmh/warc2cdb.py Mon Mar 02 16:14:17 2026 +0000 +++ b/lib/python/cc/lmh/warc2cdb.py Wed Mar 04 21:11:38 2026 +0000 @@ -138,7 +138,7 @@ if subdir in ['warc','robotstxt']: warc.warc(infile_name,LMHline,[warc.REQ,warc.RESP],parts=3) elif subdir == 'crawldiagnostics': - warc.warc(infile_name,LMHline,[warc.RESP, warc.REVISIT],parts=3) + warc.warc(infile_name,LMHline,[warc.REQ,warc.RESP, warc.REVISIT],parts=3) else: print('bogus type %s'%subdir,file=sys.stderr) exit(1)
