scripts/genslugs

   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     parser.add_option('-f', '--force', action='store_true', dest='force', default=False,
  24         help='overwrite current identifiers')
  25
  26     options, input_filenames = parser.parse_args()
  27
  28     if len(input_filenames) < 1:
  29         parser.print_help()
  30         exit(1)
  31
  32     # Do some real work
  33     for input_filename in input_filenames:
  34         if options.verbose:
  35             print input_filename
  36
  37         doc = etree.parse(input_filename)
  38         try:
  39             title = doc.find('//{http://purl.org/dc/elements/1.1/}title').text
  40         except AttributeError:
  41             print '%s:error:Book title not found. Skipping.' % input_filename
  42             continue
  43
  44         parent = ''
  45         try:
  46             parent_url = doc.find('//{http://purl.org/dc/elements/1.1/}relation.isPartOf').text
  47             parent = parent_url.rsplit('/', 1)[1] + ' '
  48         except AttributeError:
  49             pass
  50         except IndexError:
  51             print '%s:error:Invalid parent URL "%s". Skipping.' % (input_filename, parent_url)
  52
  53         book_url = doc.find('//{http://purl.org/dc/elements/1.1/}identifier.url')
  54         if book_url is None:
  55             book_description = doc.find('//{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description')
  56             book_url = etree.SubElement(book_description, '{http://purl.org/dc/elements/1.1/}identifier.url')
  57         if not options.force and book_url.text.startswith('http://'):
  58             print '%s:Notice:Book already has identifier URL "%s". Skipping.' % (input_filename, book_url.text)
  59             continue
  60
  61         book_url.text = BOOK_URL + slughifi(parent + title)[:60]
  62
  63         doc.write(input_filename, xml_declaration=True, pretty_print=True, encoding='utf-8')
  64