lib/librarian/bin/genslugs.py

   1 #!/usr/bin/env python
   2 # -*- coding: utf-8 -*-
   3 import os
   4 import optparse
   5
   6 from lxml import etree
   7 from librarian import html
   8 from slughifi import slughifi
   9
  10
  11 BOOK_URL = 'http://wolnelektury.pl/katalog/lektura/'
  12
  13
  14 if __name__ == '__main__':
  15     # Parse commandline arguments
  16     usage = """Usage: %prog [options] SOURCE [SOURCE...]
  17     Generate slugs for SOURCE."""
  18
  19     parser = optparse.OptionParser(usage=usage)
  20
  21     parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
  22         help='print status messages to stdout')
  23
  24     options, input_filenames = parser.parse_args()
  25
  26     if len(input_filenames) < 1:
  27         parser.print_help()
  28         exit(1)
  29
  30     # Do some real work
  31     for input_filename in input_filenames:
  32         if options.verbose:
  33             print input_filename
  34
  35         doc = etree.parse(input_filename)
  36         try:
  37             title = doc.find('//{http://purl.org/dc/elements/1.1/}title').text
  38         except AttributeError:
  39             print '%s:error:book title not found, skipping' % input_filename
  40             continue
  41
  42         parent = ''
  43         try:
  44             parent_url = doc.find('//{http://purl.org/dc/elements/1.1/}relation.isPartOf').text
  45             parent = parent_url.rsplit('/', 1)[1] + ' '
  46         except AttributeError:
  47             pass
  48
  49         book_url = doc.find('//{http://purl.org/dc/elements/1.1/}identifier.url')
  50         if book_url is None:
  51             book_description = doc.find('//{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description')
  52             book_url = etree.SubElement(book_description, '{http://purl.org/dc/elements/1.1/}identifier.url')
  53         elif book_url.text.startswith('http://'):
  54             print '%s:notice:book already has identifier starting with http://, skipping' % input_filename
  55             continue
  56         book_url.text = BOOK_URL + slughifi(parent + title)
  57
  58         doc.write(input_filename, xml_declaration=True, pretty_print=True, encoding='utf-8')
  59