Created
May 2, 2012 05:52
-
-
Save informationsea/2574216 to your computer and use it in GitHub Desktop.
Rename PDF by meta data
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python2.7 | |
import argparse | |
import pyPdf | |
import os | |
import os.path | |
def _main(): | |
parser = argparse.ArgumentParser(description='rename PDF files') | |
parser.add_argument('pdf', nargs='+', type=argparse.FileType('rb')) | |
parser.add_argument('--format', default='{date} - {title}.pdf', help='default:%(default)s') | |
options = parser.parse_args() | |
for f in options.pdf: | |
try: | |
pdfinfo = pyPdf.PdfFileReader(f).getDocumentInfo() | |
infodict = {'title': pdfinfo.title, | |
'author': pdfinfo.author, | |
'subject': pdfinfo.subject, | |
'date': pdfinfo['/ModDate'][2:8]} | |
# print infodict | |
newfilename = options.format.format(**infodict) | |
newfilename = newfilename.replace(':', ' ') | |
newfilename = newfilename.replace('/', ' ') | |
newfilename = newfilename.replace('\\', ' ') | |
newfilename = newfilename.replace('|', ' ') | |
newfilename = newfilename.replace('*', '+') | |
newfilename = newfilename.replace('?', '.') | |
newfilename = newfilename.replace('"', '\'') | |
newfilename = newfilename.replace('\n', ' ') | |
if f.name == newfilename: | |
print 'No rename', newfilename | |
continue | |
if os.path.exists(newfilename): | |
print 'ERROR', 'name conflict', newfilename, f.name | |
continue | |
os.rename(f.name, newfilename) | |
print 'Rename', newfilename | |
except: | |
print 'Some error' | |
if __name__ == '__main__': | |
_main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment