Codebase list sugar-read-activity / 1643fa4 epubview / epubinfo.py
1643fa4

Tree @1643fa4 (Download .tar.gz)

epubinfo.py @1643fa4 — raw · history · blame 

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
import xml.etree.ElementTree as etree


class EpubInfo():

    # TODO: Cover the entire DC range

    def __init__(self, opffile):
        self._tree = etree.parse(opffile)
        self._root = self._tree.getroot()
        self._e_metadata = self._root.find(
            '{http://www.idpf.org/2007/opf}metadata')

        self.title = self._get_title()
        self.creator = self._get_creator()
        self.date = self._get_date()
        self.subject = self._get_subject()
        self.source = self._get_source()
        self.rights = self._get_rights()
        self.identifier = self._get_identifier()
        self.language = self._get_language()
        self.summary = self._get_description()
        self.cover_image = self._get_cover_image()

    def _get_data(self, tagname):
        element = self._e_metadata.find(tagname)
        return element.text

    def _get_title(self):
        try:
            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}title')
        except AttributeError:
            return None

        return ret

    def _get_description(self):
        try:
            ret = self._get_data(
                './/{http://purl.org/dc/elements/1.1/}description')
        except AttributeError:
            return None

        return ret

    def _get_creator(self):
        try:
            ret = self._get_data(
                './/{http://purl.org/dc/elements/1.1/}creator')
        except AttributeError:
            return None
        return ret

    def _get_date(self):
        # TODO: iter
        try:
            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}date')
        except AttributeError:
            return None

        return ret

    def _get_source(self):
        try:
            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}source')
        except AttributeError:
            return None

        return ret

    def _get_rights(self):
        try:
            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}rights')
        except AttributeError:
            return None

        return ret

    def _get_identifier(self):
        # TODO: iter
        element = self._e_metadata.find(
            './/{http://purl.org/dc/elements/1.1/}identifier')

        if element is not None:
            return {'id': element.get('id'), 'value': element.text}
        else:
            return None

    def _get_language(self):
        try:
            ret = self._get_data(
                './/{http://purl.org/dc/elements/1.1/}language')
        except AttributeError:
            return None

        return ret

    def _get_subject(self):
        try:
            subjectlist = []
            for element in self._e_metadata.iterfind(
                    './/{http://purl.org/dc/elements/1.1/}subject'):
                subjectlist.append(element.text)
        except AttributeError:
            return None

        return subjectlist

    def _get_cover_image(self):
        element = self._e_metadata.find('{http://www.idpf.org/2007/opf}meta')
        if element is not None and element.get('name') == 'cover':
            return element.get('content')
        else:
            return None