view bin/count_warc.py @ 102:e606c609f813

reinstate better check to start queuing, check for missed match leading to potential runaway
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Tue, 12 Sep 2023 12:14:04 +0100 (17 months ago)
parents 083229195d12
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)