Mercurial > hg > cc > cirrus_work
comparison bin/test_warc.py @ 52:e20c64917805
better debugging output
author | Henry S. Thompson <ht@inf.ed.ac.uk> |
---|---|
date | Fri, 07 Jul 2023 17:04:05 +0100 |
parents | 212da3fe3b19 |
children | 9837840f3328 |
comparison
equal
deleted
inserted
replaced
51:c0b4359dd26a | 52:e20c64917805 |
---|---|
7 | 7 |
8 def showme(wtype,buf,part): | 8 def showme(wtype,buf,part): |
9 # This should exactly reproduce a complete warc file if called | 9 # This should exactly reproduce a complete warc file if called |
10 # as per version 1 below | 10 # as per version 1 below |
11 if debug: | 11 if debug: |
12 OUT.write(b"%d\n%b"%(part,buf)) | 12 OUT.write(b"----start %d-----\n"%part) |
13 else: | 13 OUT.write(buf) |
14 OUT.write(buf) | 14 if buf[-1]!=10: |
15 if buf[-1]!=b'\n': | 15 OUT.write(b'\r\n') |
16 OUT.write(b'\r\n') | 16 if part==7: |
17 if part==7: | 17 OUT.write(b'\r\n') # to match complete file formatting |
18 OUT.write(b'\r\n') # to match complete file formatting | 18 if debug: |
19 OUT.write(b"----end %d-----\n"%part) | |
20 return OUT | |
19 | 21 |
20 # 1 warc.warc(sys.argv[1],showme,[b'response','warcinfo','request','metadata'],whole=True) | 22 # 1 |
23 warc.warc(sys.argv[1],showme,[b'response','warcinfo','request','metadata'],parts=int(sys.argv[2]),debug=debug) | |
21 | 24 |
22 # 2 | 25 # 2 |
23 warc.warc(sys.argv[1],showme,[b'response'],parts=int(sys.argv[2]),debug=debug) | 26 #warc.warc(sys.argv[1],showme,[b'warcinfo'],parts=int(sys.argv[2]),debug=debug) |