def get_metadata(stream):
from calibre.ebooks.metadata import MetaInformation
from calibre.ptempfile import TemporaryDirectory
from calibre.ebooks.mobi.reader.headers import MetadataHeader
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre.utils.img import save_cover_data_to
from calibre import CurrentDir
stream.seek(0)
try:
raw = stream.read(3)
except Exception:
raw = b''
stream.seek(0)
if raw == b'TPZ':
from calibre.ebooks.metadata.topaz import get_metadata
return get_metadata(stream)
from calibre.utils.logging import Log
log = Log()
try:
mi = MetaInformation(os.path.basename(stream.name), [_('Unknown')])
except:
mi = MetaInformation(_('Unknown'), [_('Unknown')])
mh = MetadataHeader(stream, log)
if mh.title and mh.title != _('Unknown'):
mi.title = mh.title
if mh.exth is not None:
if mh.exth.mi is not None:
mi = mh.exth.mi
else:
size = 1024**3
if hasattr(stream, 'seek') and hasattr(stream, 'tell'):
pos = stream.tell()
stream.seek(0, 2)
size = stream.tell()
stream.seek(pos)
if size < 4 * 1024 * 1024:
with TemporaryDirectory('_mobi_meta_reader') as tdir:
with CurrentDir(tdir):
mr = MobiReader(stream, log)
parse_cache = {}
mr.extract_content(tdir, parse_cache)
if mr.embedded_mi is not None:
mi = mr.embedded_mi
if hasattr(mh.exth, 'cover_offset'):
cover_index = mh.first_image_index + mh.exth.cover_offset
data = mh.section_data(int(cover_index))
else:
try:
data = mh.section_data(mh.first_image_index)
except Exception:
data = b''
if data and what(None,
data) in {'jpg', 'jpeg', 'gif', 'png', 'bmp', 'webp'}:
try:
mi.cover_data = ('jpg', save_cover_data_to(data))
except Exception:
log.exception('Failed to read MOBI cover')
return mi
def get_metadata(stream):
from calibre.ebooks.metadata import MetaInformation
from calibre.ptempfile import TemporaryDirectory
from calibre.ebooks.mobi.reader.headers import MetadataHeader
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre.utils.magick.draw import save_cover_data_to
from calibre import CurrentDir
stream.seek(0)
try:
raw = stream.read(3)
except:
raw = ''
stream.seek(0)
if raw == b'TPZ':
from calibre.ebooks.metadata.topaz import get_metadata
return get_metadata(stream)
from calibre.utils.logging import Log
log = Log()
try:
mi = MetaInformation(os.path.basename(stream.name), [_('Unknown')])
except:
mi = MetaInformation(_('Unknown'), [_('Unknown')])
mh = MetadataHeader(stream, log)
if mh.title and mh.title != _('Unknown'):
mi.title = mh.title
if mh.exth is not None:
if mh.exth.mi is not None:
mi = mh.exth.mi
else:
size = 1024**3
if hasattr(stream, 'seek') and hasattr(stream, 'tell'):
pos = stream.tell()
stream.seek(0, 2)
size = stream.tell()
stream.seek(pos)
if size < 4*1024*1024:
with TemporaryDirectory('_mobi_meta_reader') as tdir:
with CurrentDir(tdir):
mr = MobiReader(stream, log)
parse_cache = {}
mr.extract_content(tdir, parse_cache)
if mr.embedded_mi is not None:
mi = mr.embedded_mi
if hasattr(mh.exth, 'cover_offset'):
cover_index = mh.first_image_index + mh.exth.cover_offset
data = mh.section_data(int(cover_index))
else:
try:
data = mh.section_data(mh.first_image_index)
except:
data = ''
if data and what(None, data) in {'jpg', 'jpeg', 'gif', 'png', 'bmp', 'webp'}:
try:
mi.cover_data = ('jpg', save_cover_data_to(data, 'cover.jpg', return_data=True))
except Exception:
log.exception('Failed to read MOBI cover')
return mi
def explode(path, dest, question=lambda x:True):
with open(path, 'rb') as stream:
raw = stream.read(3)
stream.seek(0)
if raw == b'TPZ':
raise BadFormat(_('This is not a MOBI file. It is a Topaz file.'))
try:
header = MetadataHeader(stream, default_log)
except MobiError:
raise BadFormat(_('This is not a MOBI file.'))
if header.encryption_type != 0:
raise DRMError(_('This file is locked with DRM. It cannot be tweaked.'))
kf8_type = header.kf8_type
if kf8_type is None:
raise BadFormat(_('This MOBI file does not contain a KF8 format '
'book. KF8 is the new format from Amazon. calibre can '
'only tweak MOBI files that contain KF8 books. Older '
'MOBI files without KF8 are not tweakable.'))
if kf8_type == 'joint':
if not question(_('This MOBI file contains both KF8 and '
'older Mobi6 data. Tweaking it will remove the Mobi6 data, which '
'means the file will not be usable on older Kindles. Are you '
'sure?')):
return None
return fork_job('calibre.ebooks.mobi.tweak', 'do_explode', args=(path,
dest), no_output=True)['result']
def thumbpath_from_filepath(self, filepath):
from calibre.ebooks.metadata.kfx import (CONTAINER_MAGIC,
read_book_key_kfx)
from calibre.ebooks.mobi.reader.headers import MetadataHeader
from calibre.utils.logging import default_log
thumb_dir = self.amazon_system_thumbnails_dir()
if not os.path.exists(thumb_dir):
return
with lopen(filepath, 'rb') as f:
is_kfx = f.read(4) == CONTAINER_MAGIC
f.seek(0)
uuid = cdetype = None
if is_kfx:
uuid, cdetype = read_book_key_kfx(f)
else:
mh = MetadataHeader(f, default_log)
if mh.exth is not None:
uuid = mh.exth.uuid
cdetype = mh.exth.cdetype
if not uuid or not cdetype:
return
return os.path.join(
thumb_dir,
'thumbnail_{uuid}_{cdetype}_portrait.jpg'.format(uuid=uuid,
cdetype=cdetype))
def write_apnx(self, mobi_file_path, apnx_path, accurate=True, page_count=0):
'''
If you want a fixed number of pages (such as from a custom column) then
pass in a value to page_count, otherwise a count will be estimated
using either the fast or accurate algorithm.
'''
import uuid
apnx_meta = { 'guid': str(uuid.uuid4()).replace('-', '')[:8], 'asin':
'', 'cdetype': 'EBOK', 'format': 'MOBI_7', 'acr': '' }
with open(mobi_file_path, 'rb') as mf:
ident = PdbHeaderReader(mf).identity()
if ident != 'BOOKMOBI':
# Check that this is really a MOBI file.
raise Exception(_('Not a valid MOBI file. Reports identity of %s') % ident)
apnx_meta['acr'] = str(PdbHeaderReader(mf).name())
# We'll need the PDB name, the MOBI version, and some metadata to make FW 3.4 happy with KF8 files...
with open(mobi_file_path, 'rb') as mf:
mh = MetadataHeader(mf, default_log)
if mh.mobi_version == 8:
apnx_meta['format'] = 'MOBI_8'
else:
apnx_meta['format'] = 'MOBI_7'
if mh.exth is None or not mh.exth.cdetype:
apnx_meta['cdetype'] = 'EBOK'
else:
apnx_meta['cdetype'] = str(mh.exth.cdetype)
if mh.exth is None or not mh.exth.uuid:
apnx_meta['asin'] = ''
else:
apnx_meta['asin'] = str(mh.exth.uuid)
# Get the pages depending on the chosen parser
pages = []
if page_count:
pages = self.get_pages_exact(mobi_file_path, page_count)
else:
if accurate:
try:
pages = self.get_pages_accurate(mobi_file_path)
except:
# Fall back to the fast parser if we can't
# use the accurate one. Typically this is
# due to the file having DRM.
pages = self.get_pages_fast(mobi_file_path)
else:
pages = self.get_pages_fast(mobi_file_path)
if not pages:
raise Exception(_('Could not generate page mapping.'))
# Generate the APNX file from the page mapping.
apnx = self.generate_apnx(pages, apnx_meta)
# Write the APNX.
with open(apnx_path, 'wb') as apnxf:
apnxf.write(apnx)
fsync(apnxf)
def __init__(self, pathtoazw3, log, clone_data=None, tdir=None):
if clone_data is not None:
super(AZW3Container, self).__init__(None,
None,
log,
clone_data=clone_data)
for x in ('pathtoazw3', 'obfuscated_fonts'):
setattr(self, x, clone_data[x])
return
self.pathtoazw3 = pathtoazw3
if tdir is None:
tdir = PersistentTemporaryDirectory('_azw3_container')
tdir = os.path.abspath(os.path.realpath(tdir))
self.root = tdir
with open(pathtoazw3, 'rb') as stream:
raw = stream.read(3)
if raw == b'TPZ':
raise InvalidMobi(
_('This is not a MOBI file. It is a Topaz file.'))
try:
header = MetadataHeader(stream, default_log)
except MobiError:
raise InvalidMobi(_('This is not a MOBI file.'))
if header.encryption_type != 0:
raise DRMError()
kf8_type = header.kf8_type
if kf8_type is None:
raise InvalidMobi(
_('This MOBI file does not contain a KF8 format '
'book. KF8 is the new format from Amazon. calibre can '
'only edit MOBI files that contain KF8 books. Older '
'MOBI files without KF8 are not editable.'))
if kf8_type == 'joint':
raise InvalidMobi(
_('This MOBI file contains both KF8 and '
'older Mobi6 data. calibre can only edit MOBI files '
'that contain only KF8 data.'))
try:
opf_path, obfuscated_fonts = fork_job(
'calibre.ebooks.oeb.polish.container',
'do_explode',
args=(pathtoazw3, tdir),
no_output=True)['result']
except WorkerError as e:
log(e.orig_tb)
raise InvalidMobi('Failed to explode MOBI')
super(AZW3Container, self).__init__(tdir, opf_path, log)
self.obfuscated_fonts = {
x.replace(os.sep, '/')
for x in obfuscated_fonts
}
def thumbpath_from_filepath(self, filepath):
from calibre.ebooks.mobi.reader.headers import MetadataHeader
from calibre.utils.logging import default_log
thumb_dir = os.path.join(self._main_prefix, 'system', 'thumbnails')
if not os.path.exists(thumb_dir):
return
with lopen(filepath, 'rb') as f:
mh = MetadataHeader(f, default_log)
if mh.exth is None or not mh.exth.uuid or not mh.exth.cdetype:
return
return os.path.join(
thumb_dir, 'thumbnail_{uuid}_{cdetype}_portrait.jpg'.format(
uuid=mh.exth.uuid, cdetype=mh.exth.cdetype))
def upload_kindle_thumbnail(self, metadata, filepath):
coverdata = getattr(metadata, 'thumbnail', None)
if not coverdata or not coverdata[2]:
return
thumb_dir = os.path.join(self._main_prefix, 'system', 'thumbnails')
if not os.path.exists(thumb_dir): return
from calibre.ebooks.mobi.reader.headers import MetadataHeader
with lopen(filepath, 'rb') as f:
mh = MetadataHeader(f, default_log)
if mh.exth is None or not mh.exth.uuid or not mh.exth.cdetype:
return
thumbfile = os.path.join(
thumb_dir, 'thumbnail_{uuid}_{cdetype}_portrait.jpg'.format(
uuid=mh.exth.uuid, cdetype=mh.exth.cdetype))
with open(thumbfile, 'wb') as f:
f.write(coverdata[2])
def get_metadata(stream):
from calibre.ebooks.metadata import MetaInformation
from calibre.ptempfile import TemporaryDirectory
from calibre.ebooks.mobi.reader.headers import MetadataHeader
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre import CurrentDir
try:
from PIL import Image as PILImage
PILImage
except ImportError:
import Image as PILImage
stream.seek(0)
try:
raw = stream.read(3)
except:
raw = ''
stream.seek(0)
if raw == b'TPZ':
from calibre.ebooks.metadata.topaz import get_metadata
return get_metadata(stream)
from calibre.utils.logging import Log
log = Log()
try:
mi = MetaInformation(os.path.basename(stream.name), [_('Unknown')])
except:
mi = MetaInformation(_('Unknown'), [_('Unknown')])
mh = MetadataHeader(stream, log)
if mh.title and mh.title != _('Unknown'):
mi.title = mh.title
if mh.exth is not None:
if mh.exth.mi is not None:
mi = mh.exth.mi
else:
size = 1024**3
if hasattr(stream, 'seek') and hasattr(stream, 'tell'):
pos = stream.tell()
stream.seek(0, 2)
size = stream.tell()
stream.seek(pos)
if size < 4*1024*1024:
with TemporaryDirectory('_mobi_meta_reader') as tdir:
with CurrentDir(tdir):
mr = MobiReader(stream, log)
parse_cache = {}
mr.extract_content(tdir, parse_cache)
if mr.embedded_mi is not None:
mi = mr.embedded_mi
if hasattr(mh.exth, 'cover_offset'):
cover_index = mh.first_image_index + mh.exth.cover_offset
data = mh.section_data(int(cover_index))
else:
try:
data = mh.section_data(mh.first_image_index)
except:
data = ''
buf = cStringIO.StringIO(data)
try:
im = PILImage.open(buf)
except:
log.exception('Failed to read MOBI cover')
else:
obuf = cStringIO.StringIO()
im.convert('RGB').save(obuf, format='JPEG')
mi.cover_data = ('jpg', obuf.getvalue())
return mi
def get_metadata(stream):
from calibre.ebooks.metadata import MetaInformation
from calibre.ptempfile import TemporaryDirectory
from calibre.ebooks.mobi.reader.headers import MetadataHeader
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre import CurrentDir
try:
from PIL import Image as PILImage
PILImage
except ImportError:
import Image as PILImage
stream.seek(0)
try:
raw = stream.read(3)
except:
raw = ''
stream.seek(0)
if raw == b'TPZ':
from calibre.ebooks.metadata.topaz import get_metadata
return get_metadata(stream)
from calibre.utils.logging import Log
log = Log()
try:
mi = MetaInformation(os.path.basename(stream.name), [_('Unknown')])
except:
mi = MetaInformation(_('Unknown'), [_('Unknown')])
mh = MetadataHeader(stream, log)
if mh.title and mh.title != _('Unknown'):
mi.title = mh.title
if mh.exth is not None:
if mh.exth.mi is not None:
mi = mh.exth.mi
else:
size = 1024**3
if hasattr(stream, 'seek') and hasattr(stream, 'tell'):
pos = stream.tell()
stream.seek(0, 2)
size = stream.tell()
stream.seek(pos)
if size < 4 * 1024 * 1024:
with TemporaryDirectory('_mobi_meta_reader') as tdir:
with CurrentDir(tdir):
mr = MobiReader(stream, log)
parse_cache = {}
mr.extract_content(tdir, parse_cache)
if mr.embedded_mi is not None:
mi = mr.embedded_mi
if hasattr(mh.exth, 'cover_offset'):
cover_index = mh.first_image_index + mh.exth.cover_offset
data = mh.section_data(int(cover_index))
else:
try:
data = mh.section_data(mh.first_image_index)
except:
data = ''
buf = cStringIO.StringIO(data)
try:
im = PILImage.open(buf)
except:
log.exception('Failed to read MOBI cover')
else:
obuf = cStringIO.StringIO()
im.convert('RGB').save(obuf, format='JPEG')
mi.cover_data = ('jpg', obuf.getvalue())
return mi
