security-and-privacy/pdfparanoia
security-and-privacy
/
pdfparanoia
mirror of https://github.com/kanzure/pdfparanoia.git
1
0
Fork 0
Code Releases Activity

Fixed a few bugs so reading from stdin now works. Involves a potentially costly recast of file contents as StringIO.

This commit is contained in:
Cathal Garvey 2013-03-21 23:49:03 +00:00
parent 95e92420c9
commit db514ff744
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
bin/pdfparanoia
View File

@ -16,7 +16,7 @@ if __name__ == "__main__":
ArgP = argparse.ArgumentParser(description="pdfparanoia is a PDF watermark removal library for academic papers. Some publishers include private information like institution names, personal names, ip addresses, timestamps and other identifying information in watermarks on each page.")
ArgP.add_argument('in_pdf', nargs='?', type=argparse.FileType('rb'),
default=sys.stdin)
default='-') # argparse.FileType interprets "-" as Stdin.
ArgP.add_argument("-o", "--output", type=argparse.FileType('wb'),
default=sys.stdout)
ArgP.add_argument("-v", "--verbose", action="store_true", default=False,
@ -29,7 +29,9 @@ if __name__ == "__main__":
if Args.verbose: verbose = 1
if Args.more_verbose: verbose = 2
outputcontent = pdfparanoia.scrub(Args.in_pdf, verbose=verbose)
# I really don't like having to read a file only to cast as StringIO, but seems
# necessary to get reading from StdIn to play nicely with pdfparanoia.
outputcontent = pdfparanoia.scrub(StringIO(Args.in_pdf.read()), verbose=verbose)
Args.in_pdf.close()
Args.output.write(outputcontent)
if Args.output != sys.stdout: