# HG changeset patch # User Henry Thompson # Date 1692637580 14400 # Node ID c18c307cc3254a63dd2c791c4ff193f6c0ab3fe9 # Parent d92bd852771811b759efdfa5d658ab5dc254c962# Parent 120d90b47d74a37f7a5aadbe0a622758b62d6652 merge, including pointless fix wrt pq diff -r d92bd8527718 -r c18c307cc325 bin/lmh_warc.py --- a/bin/lmh_warc.py Sat Aug 19 16:33:23 2023 -0400 +++ b/bin/lmh_warc.py Mon Aug 21 13:06:20 2023 -0400 @@ -2,22 +2,32 @@ import re,warc,sys TUPAT=re.compile(b'^WARC-Target-URI: (.*?)\r',re.MULTILINE) +DPAT=re.compile(b'^WARC-Date: (.*?)\r',re.MULTILINE) LMPAT=re.compile(b'^Last-Modified: (.*?)\r',re.MULTILINE) +DTAB=bytearray(range(256)) +DDEL=b'TZ-:' + OUT=open(sys.stdout.fileno(),'wb') def showmeLMH(wtype,buf,part): - global URI + global URI, DATE if part==1: if (m:=TUPAT.search(buf)): URI=m[1] else: raise ValueError(b"No target URI in %s ??"%buf) + if (md:=DPAT.search(buf)): + DATE=md[1] + else: + raise ValueError(b"No date in %s ??"%buf) else: mm=LMPAT.search(buf) OUT.write(URI) if mm: OUT.write(b'\t') + OUT.write(DATE.translate(DTAB,DDEL)) + OUT.write(b'\t') OUT.write(mm[1]) OUT.write(b'\n') diff -r d92bd8527718 -r c18c307cc325 bin/sort_date.py