Mercurial > hg > cc > cirrus_work
view bin/count_warc.py @ 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 | |
children |
line wrap: on
line source
#!/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)