1 # -*- coding: utf-8 -*-
2 from xml.parsers.expat import ExpatError
4 # Import ElementTree from anywhere
6 import xml.etree.ElementTree as ET # Python >= 2.5
9 import elementtree.ElementTree as ET # effbot's pure Python module
11 import lxml.etree as ET # ElementTree API using libxml2
17 __all__ = ('parse', 'ParseError')
21 class ParseError(Exception):
22 def __init__(self, message):
23 super(self, Exception).__init__(message)
27 class XMLNamespace(object):
28 '''Represents XML namespace.'''
30 def __init__(self, uri):
33 def __call__(self, tag):
34 return '{%s}%s' % (self.uri, tag)
36 def __contains__(self, tag):
37 return tag.startswith(str(self))
40 return 'NS(%r)' % self.uri
43 return '%s' % self.uri
47 class BookInfo(object):
48 RDF = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#')
49 DC = XMLNamespace('http://purl.org/dc/elements/1.1/')
52 DC('creator') : ('author', converters.str_to_person),
53 DC('title') : ('title', converters.str_to_unicode),
54 DC('subject.period') : ('epoch', converters.str_to_unicode),
55 DC('subject.type') : ('kind', converters.str_to_unicode),
56 DC('subject.genre') : ('genre', converters.str_to_unicode),
57 DC('date') : ('created_at', converters.str_to_date),
58 DC('date.pd') : ('released_to_public_domain_at', converters.str_to_date),
59 DC('contributor.translator') : ('translator', converters.str_to_person),
60 DC('contributor.technical_editor') : ('technical_editor', converters.str_to_person),
61 DC('publisher') : ('publisher', converters.str_to_unicode),
62 DC('source') : ('source_name', converters.str_to_unicode),
63 DC('source.URL') : ('source_url', converters.str_to_unicode),
68 def from_string(cls, xml):
69 """docstring for from_string"""
70 from StringIO import StringIO
71 return cls.from_file(StringIO(xml))
75 def from_file(cls, xml_file):
79 tree = ET.parse(xml_file)
83 description = tree.find('//' + book_info.RDF('Description'))
84 if description is None:
85 raise ParseError('no Description tag found in document')
87 for element in description.findall('*'):
88 book_info.parse_element(element)
93 def parse_element(self, element):
95 attribute, converter = self.mapping[element.tag]
96 setattr(self, attribute, converter(element.text))
102 """XML representation of this object."""
103 ET._namespace_map[str(self.RDF)] = 'rdf'
104 ET._namespace_map[str(self.DC)] = 'dc'
106 root = ET.Element(self.RDF('RDF'))
107 description = ET.SubElement(root, self.RDF('Description'))
109 for tag, (attribute, converter) in self.mapping.iteritems():
110 if hasattr(self, attribute):
112 e.text = unicode(getattr(self, attribute))
113 description.append(e)
115 return unicode(ET.tostring(root, 'utf-8'), 'utf-8')
118 def parse(file_name):
119 return BookInfo.from_file(file_name)