#!/usr/bin/env python3 # Copyright (C) 2014 J.F.Dockes # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the # Free Software Foundation, Inc., # 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. ###################################### from __future__ import print_function import sys import rclexecm import rclxslt from zipfile import ZipFile from rclbasehandler import RclBaseHandler stylesheet_meta = ''' <xsl:value-of select="."/> abstract keywords author keywords ''' stylesheet_content = '''


''' class OOExtractor(RclBaseHandler): def __init__(self, em): super(OOExtractor, self).__init__(em) def html_text(self, fn): f = open(fn, 'rb') data = f.read() f.close() docdata = b'\n\n\n' try: res = rclxslt.apply_sheet_data(stylesheet_meta, data) docdata += res except: # To be checked. I'm under the impression that I get this when # nothing matches? #self.em.rclog("no/bad metadata in %s" % fn) pass docdata += b'' res = rclxslt.apply_sheet_data(stylesheet_content, data) docdata += res docdata += b'' return docdata if __name__ == '__main__': proto = rclexecm.RclExecM() extract = OOExtractor(proto) rclexecm.main(proto, extract)