Mercurial > hg > cc > cirrus_work
view bin/test_warc.py @ 47:b59f49909bda
sic
| author | Henry S. Thompson <ht@inf.ed.ac.uk> |
|---|---|
| date | Thu, 06 Jul 2023 10:19:02 +0100 |
| parents | 212da3fe3b19 |
| children | e20c64917805 |
line wrap: on
line source
import warc,sys OUT=open(sys.stdout.fileno(),'wb') if (debug:=(sys.argv[1]=='-d')): sys.argv.pop(1) def showme(wtype,buf,part): # This should exactly reproduce a complete warc file if called # as per version 1 below if debug: OUT.write(b"%d\n%b"%(part,buf)) else: OUT.write(buf) if buf[-1]!=b'\n': OUT.write(b'\r\n') if part==7: OUT.write(b'\r\n') # to match complete file formatting # 1 warc.warc(sys.argv[1],showme,[b'response','warcinfo','request','metadata'],whole=True) # 2 warc.warc(sys.argv[1],showme,[b'response'],parts=int(sys.argv[2]),debug=debug)
