Mercurial > hg > cc > cirrus_work
changeset 44:083229195d12
just count part length
| author | Henry S. Thompson <ht@inf.ed.ac.uk> |
|---|---|
| date | Wed, 05 Jul 2023 17:51:44 +0100 |
| parents | 69be1131bcc5 |
| children | 212da3fe3b19 |
| files | bin/count_warc.py |
| diffstat | 1 files changed, 17 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bin/count_warc.py Wed Jul 05 17:51:44 2023 +0100 @@ -0,0 +1,17 @@ +#!/usr/bin/env python3 +import warc,sys + +OUT=open(sys.stdout.fileno(),'wb') + +if (debug:=(sys.argv[1]=='-d')): + sys.argv.pop(1) + +def countme(wtype,buf,part): + if debug: + breakpoint() + OUT.write(b"%d\n"%len(buf)) + +#warc(showme,[b'response','warcinfo','request','metadata'],int(sys.argv[2])) +#warc(showme,[b'response'],whole=True) + +warc.warc(sys.argv[1],countme,[b'response'],parts=int(sys.argv[2]),debug=debug)