# HG changeset patch # User Henry S. Thompson # Date 1688575904 -3600 # Node ID 083229195d129e6263b4e7ebea1da81df1a1376b # Parent 69be1131bcc52ab0109a5e7be67008dcb4a13b6a just count part length diff -r 69be1131bcc5 -r 083229195d12 bin/count_warc.py --- /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)