Mercurial > hg > cc > cirrus_work

comparison lib/python/plinks.py @ 120:1d1bd22124c0

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
moved from bin
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Thu, 28 Sep 2023 08:46:01 +0100
parents bin/plinks.py@38bab758e469
children
comparison
equal deleted inserted replaced
119:1d12b51c4d59 120:1d1bd22124c0
1 #!/usr/bin/env python3
2 import sys,pdfx,traceback,os
3 from datetime import datetime
4
5 def run(file):
6 try:
7 pdf=pdfx.PDFx(file)
8 links=pdf.get_references_as_dict()
9 if bool(links) and (links.get('scrape',False) or
10 links.get('annot',False)):
11 for k in links.keys():
12 for l in links[k]:
13 print("%s\t%s"%(k,l))
14 else:
15 print("None")
16 except Exception as e:
17 if str(e)=='Unexpected EOF':
18 print("%s:\t%s"%(datetime.now().isoformat(),e),file=sys.stderr)
19 print("badpdf")
20 else:
21 print("%s: "%(datetime.now().isoformat()),end='',file=sys.stderr)
22 traceback.print_exc(file=sys.stderr)
23
24 if sys.argv[1]=='-':
25 i=0
26 for l in sys.stdin:
27 print(i,file=sys.stderr)
28 i+=1
29 f=l.rstrip()
30 if os.path.getsize(f)==1048576: # truncated
31 print("truncated",file=sys.stderr)
32 print("truncated")
33 else:
34 run(f)
35 os.unlink(f)
36 else:
37 run(sys.argv[1])