def update_metadata(ebook, new_opf):
from calibre.ebooks.metadata.opf2 import OPF
from calibre.ebooks.metadata.epub import update_metadata
opfpath = ebook.name_to_abspath(ebook.opf_name)
with ebook.open(ebook.opf_name, "r+b") as stream, open(new_opf, "rb") as ns:
opf = OPF(stream, basedir=os.path.dirname(opfpath), populate_spine=False, unquote_urls=False)
mi = OPF(ns, unquote_urls=False, populate_spine=False).to_book_metadata()
mi.cover, mi.cover_data = None, (None, None)
update_metadata(opf, mi, apply_null=True, update_timestamp=True)
stream.seek(0)
stream.truncate()
stream.write(opf.render())
def update_metadata(ebook, new_opf):
from calibre.ebooks.metadata.opf2 import OPF
from calibre.ebooks.metadata.epub import update_metadata
opfpath = ebook.name_to_abspath(ebook.opf_name)
with ebook.open(ebook.opf_name, 'r+b') as stream, open(new_opf, 'rb') as ns:
opf = OPF(stream, basedir=os.path.dirname(opfpath), populate_spine=False,
unquote_urls=False)
mi = OPF(ns, unquote_urls=False,
populate_spine=False).to_book_metadata()
mi.cover, mi.cover_data = None, (None, None)
update_metadata(opf, mi, apply_null=True, update_timestamp=True)
stream.seek(0)
stream.truncate()
stream.write(opf.render())
def set_metadata_opf2(root, cover_prefix, mi, opf_version,
cover_data=None, apply_null=False, update_timestamp=False, force_identifiers=False, add_missing_cover=True):
mi = MetaInformation(mi)
for x in ('guide', 'toc', 'manifest', 'spine'):
setattr(mi, x, None)
opf = OPF(None, preparsed_opf=root, read_toc=False)
if mi.languages:
mi.languages = normalize_languages(list(opf.raw_languages) or [], mi.languages)
opf.smart_update(mi, apply_null=apply_null)
if getattr(mi, 'uuid', None):
opf.application_id = mi.uuid
if apply_null or force_identifiers:
opf.set_identifiers(mi.get_identifiers())
else:
orig = opf.get_identifiers()
orig.update(mi.get_identifiers())
opf.set_identifiers({k:v for k, v in orig.iteritems() if k and v})
if update_timestamp and mi.timestamp is not None:
opf.timestamp = mi.timestamp
raster_cover = opf.raster_cover
if raster_cover is None and cover_data is not None and add_missing_cover:
guide_raster_cover = opf.guide_raster_cover
i = None
if guide_raster_cover is not None:
i = guide_raster_cover
raster_cover = i.get('href')
else:
if cover_prefix and not cover_prefix.endswith('/'):
cover_prefix += '/'
name = cover_prefix + 'cover.jpg'
i = create_manifest_item(opf.root, name, 'cover')
if i is not None:
raster_cover = name
if i is not None:
if opf_version.major < 3:
[x.getparent().remove(x) for x in opf.root.xpath('//*[local-name()="meta" and @name="cover"]')]
m = opf.create_metadata_element('meta', is_dc=False)
m.set('name', 'cover'), m.set('content', i.get('id'))
else:
for x in opf.root.xpath('//*[local-name()="item" and contains(@properties, "cover-image")]'):
x.set('properties', x.get('properties').replace('cover-image', '').strip())
i.set('properties', 'cover-image')
with pretty_print:
return opf.render(), raster_cover
def set_metadata_opf2(root, cover_prefix, mi, opf_version,
cover_data=None, apply_null=False, update_timestamp=False, force_identifiers=False, add_missing_cover=True):
mi = MetaInformation(mi)
for x in ('guide', 'toc', 'manifest', 'spine'):
setattr(mi, x, None)
opf = OPF(None, preparsed_opf=root, read_toc=False)
if mi.languages:
mi.languages = normalize_languages(list(opf.raw_languages) or [], mi.languages)
opf.smart_update(mi, apply_null=apply_null)
if getattr(mi, 'uuid', None):
opf.application_id = mi.uuid
if apply_null or force_identifiers:
opf.set_identifiers(mi.get_identifiers())
else:
orig = opf.get_identifiers()
orig.update(mi.get_identifiers())
opf.set_identifiers({k:v for k, v in orig.items() if k and v})
if update_timestamp and mi.timestamp is not None:
opf.timestamp = mi.timestamp
raster_cover = opf.raster_cover
if raster_cover is None and cover_data is not None and add_missing_cover:
guide_raster_cover = opf.guide_raster_cover
i = None
if guide_raster_cover is not None:
i = guide_raster_cover
raster_cover = i.get('href')
else:
if cover_prefix and not cover_prefix.endswith('/'):
cover_prefix += '/'
name = cover_prefix + 'cover.jpg'
i = create_manifest_item(opf.root, name, 'cover')
if i is not None:
raster_cover = name
if i is not None:
if opf_version.major < 3:
[x.getparent().remove(x) for x in opf.root.xpath('//*[local-name()="meta" and @name="cover"]')]
m = opf.create_metadata_element('meta', is_dc=False)
m.set('name', 'cover'), m.set('content', i.get('id'))
else:
for x in opf.root.xpath('//*[local-name()="item" and contains(@properties, "cover-image")]'):
x.set('properties', x.get('properties').replace('cover-image', '').strip())
i.set('properties', 'cover-image')
with pretty_print:
return opf.render(), raster_cover
def set_metadata(stream, mi):
replacements = {}
# Get the OPF in the archive.
with ZipFile(stream) as zf:
opf_path = get_first_opf_name(zf)
opf_stream = io.BytesIO(zf.read(opf_path))
opf = OPF(opf_stream)
# Cover.
new_cdata = None
try:
new_cdata = mi.cover_data[1]
if not new_cdata:
raise Exception('no cover')
except:
try:
with open(mi.cover, 'rb') as f:
new_cdata = f.read()
except:
pass
if new_cdata:
cpath = opf.raster_cover
if not cpath:
cpath = 'cover.jpg'
new_cover = _write_new_cover(new_cdata, cpath)
replacements[cpath] = open(new_cover.name, 'rb')
mi.cover = cpath
# Update the metadata.
opf.smart_update(mi, replace_metadata=True)
newopf = io.BytesIO(opf.render())
safe_replace(stream,
opf_path,
newopf,
extra_replacements=replacements,
add_missing=True)
# Cleanup temporary files.
try:
if cpath is not None:
replacements[cpath].close()
os.remove(replacements[cpath].name)
except:
pass
def set_metadata(stream, mi):
replacements = {}
# Get the OPF in the archive.
with ZipFile(stream) as zf:
opf_path = get_first_opf_name(zf)
opf_stream = StringIO(zf.read(opf_path))
opf = OPF(opf_stream)
# Cover.
new_cdata = None
try:
new_cdata = mi.cover_data[1]
if not new_cdata:
raise Exception('no cover')
except:
try:
new_cdata = open(mi.cover, 'rb').read()
except:
pass
if new_cdata:
cpath = opf.raster_cover
if not cpath:
cpath = 'cover.jpg'
new_cover = _write_new_cover(new_cdata, cpath)
replacements[cpath] = open(new_cover.name, 'rb')
mi.cover = cpath
# Update the metadata.
opf.smart_update(mi, replace_metadata=True)
newopf = StringIO(opf.render())
safe_replace(stream, opf_path, newopf, extra_replacements=replacements, add_missing=True)
# Cleanup temporary files.
try:
if cpath is not None:
replacements[cpath].close()
os.remove(replacements[cpath].name)
except:
pass
def convert(self, stream, options, file_ext, log, accelerators):
"""Convert a KePub file into a structure calibre can process."""
log("KEPUBInput::convert - start")
from calibre.utils.zipfile import ZipFile
from calibre import walk
from calibre.ebooks import DRMError
from calibre.ebooks.metadata.opf2 import OPF
try:
zf = ZipFile(stream)
cwd = os.getcwdu() if sys.version_info.major == 2 else os.getcwd()
zf.extractall(cwd)
except Exception:
log.exception("KEPUB appears to be invalid ZIP file, trying a "
"more forgiving ZIP parser")
from calibre.utils.localunzip import extractall
stream.seek(0)
extractall(stream)
opf = self.find_opf()
if opf is None:
for f in walk("."):
if (f.lower().endswith(".opf") and "__MACOSX" not in f
and not os.path.basename(f).startswith(".")):
opf = os.path.abspath(f)
break
path = getattr(stream, "name", "stream")
if opf is None:
raise ValueError(
_( # noqa: F821
"{0} is not a valid KEPUB file (could not find opf)").
format(path))
encfile = os.path.abspath("rights.xml")
if os.path.exists(encfile):
raise DRMError(os.path.basename(path))
cwd = os.getcwdu() if sys.version_info.major == 2 else os.getcwd()
opf = os.path.relpath(opf, cwd)
parts = os.path.split(opf)
opf = OPF(opf, os.path.dirname(os.path.abspath(opf)))
self.encrypted_fonts = []
if len(parts) > 1 and parts[0]:
delta = "/".join(parts[:-1]) + "/"
for elem in opf.itermanifest():
elem.set("href", delta + elem.get("href"))
for elem in opf.iterguide():
elem.set("href", delta + elem.get("href"))
f = (self.rationalize_cover3
if opf.package_version >= 3.0 else self.rationalize_cover2)
self.removed_cover = f(opf, log)
self.optimize_opf_parsing = opf
for x in opf.itermanifest():
if x.get("media-type", "") == "application/x-dtbook+xml":
raise ValueError(
_("EPUB files with DTBook markup are not supported"
) # noqa: F821
)
not_for_spine = set()
for y in opf.itermanifest():
id_ = y.get("id", None)
if id_ and y.get("media-type", None) in {
"application/vnd.adobe-page-template+xml",
"application/vnd.adobe.page-template+xml",
"application/adobe-page-template+xml",
"application/adobe.page-template+xml",
"application/text",
}:
not_for_spine.add(id_)
seen = set()
for x in list(opf.iterspine()):
ref = x.get("idref", None)
if not ref or ref in not_for_spine or ref in seen:
x.getparent().remove(x)
continue
seen.add(ref)
if len(list(opf.iterspine())) == 0:
raise ValueError(
_("No valid entries in the spine of this EPUB") # noqa: F821
)
with open("content.opf", "wb") as nopf:
nopf.write(opf.render())
return os.path.abspath("content.opf")
def convert(self, stream, options, file_ext, log, accelerators):
log("KEPUBInput::convert - start")
from calibre.utils.zipfile import ZipFile
from calibre import walk
from calibre.ebooks import DRMError
from calibre.ebooks.metadata.opf2 import OPF
try:
zf = ZipFile(stream)
zf.extractall(os.getcwdu())
except:
log.exception('KEPUB appears to be invalid ZIP file, trying a '
'more forgiving ZIP parser')
from calibre.utils.localunzip import extractall
stream.seek(0)
extractall(stream)
opf = self.find_opf()
if opf is None:
for f in walk(u'.'):
if f.lower().endswith('.opf') and '__MACOSX' not in f and \
not os.path.basename(f).startswith('.'):
opf = os.path.abspath(f)
break
path = getattr(stream, 'name', 'stream')
if opf is None:
raise ValueError(
_('%s is not a valid KEPUB file (could not find opf)') % path)
encfile = os.path.abspath('rights.xml')
if os.path.exists(encfile):
raise DRMError(os.path.basename(path))
opf = os.path.relpath(opf, os.getcwdu())
parts = os.path.split(opf)
opf = OPF(opf, os.path.dirname(os.path.abspath(opf)))
self.encrypted_fonts = []
if len(parts) > 1 and parts[0]:
delta = '/'.join(parts[:-1]) + '/'
for elem in opf.itermanifest():
elem.set('href', delta + elem.get('href'))
for elem in opf.iterguide():
elem.set('href', delta + elem.get('href'))
f = self.rationalize_cover3 if opf.package_version >= 3.0 else \
self.rationalize_cover2
self.removed_cover = f(opf, log)
self.optimize_opf_parsing = opf
for x in opf.itermanifest():
if x.get('media-type', '') == 'application/x-dtbook+xml':
raise ValueError(
_('EPUB files with DTBook markup are not supported'))
not_for_spine = set()
for y in opf.itermanifest():
id_ = y.get('id', None)
if id_ and y.get('media-type', None) in {
'application/vnd.adobe-page-template+xml',
'application/vnd.adobe.page-template+xml',
'application/adobe-page-template+xml',
'application/adobe.page-template+xml', 'application/text'
}:
not_for_spine.add(id_)
seen = set()
for x in list(opf.iterspine()):
ref = x.get('idref', None)
if not ref or ref in not_for_spine or ref in seen:
x.getparent().remove(x)
continue
seen.add(ref)
if len(list(opf.iterspine())) == 0:
raise ValueError(_('No valid entries in the spine of this EPUB'))
with open('content.opf', 'wb') as nopf:
nopf.write(opf.render())
return os.path.abspath(u'content.opf')
def convert(self, stream, options, file_ext, log, accelerators):
log("KEPUBInput::convert - start")
from calibre.utils.zipfile import ZipFile
from calibre import walk
from calibre.ebooks import DRMError
from calibre.ebooks.metadata.opf2 import OPF
try:
zf = ZipFile(stream)
zf.extractall(os.getcwdu())
except:
log.exception('KEPUB appears to be invalid ZIP file, trying a '
'more forgiving ZIP parser')
from calibre.utils.localunzip import extractall
stream.seek(0)
extractall(stream)
opf = self.find_opf()
if opf is None:
for f in walk(u'.'):
if f.lower().endswith('.opf') and '__MACOSX' not in f and \
not os.path.basename(f).startswith('.'):
opf = os.path.abspath(f)
break
path = getattr(stream, 'name', 'stream')
if opf is None:
raise ValueError(
_('%s is not a valid KEPUB file (could not find opf)') % path)
encfile = os.path.abspath('rights.xml')
if os.path.exists(encfile):
raise DRMError(os.path.basename(path))
opf = os.path.relpath(opf, os.getcwdu())
parts = os.path.split(opf)
opf = OPF(opf, os.path.dirname(os.path.abspath(opf)))
self.encrypted_fonts = []
if len(parts) > 1 and parts[0]:
delta = '/'.join(parts[:-1]) + '/'
for elem in opf.itermanifest():
elem.set('href', delta + elem.get('href'))
for elem in opf.iterguide():
elem.set('href', delta + elem.get('href'))
f = self.rationalize_cover3 if opf.package_version >= 3.0 else \
self.rationalize_cover2
self.removed_cover = f(opf, log)
self.optimize_opf_parsing = opf
for x in opf.itermanifest():
if x.get('media-type', '') == 'application/x-dtbook+xml':
raise ValueError(_(
'EPUB files with DTBook markup are not supported'))
not_for_spine = set()
for y in opf.itermanifest():
id_ = y.get('id', None)
if id_ and y.get('media-type', None) in {
'application/vnd.adobe-page-template+xml',
'application/vnd.adobe.page-template+xml',
'application/adobe-page-template+xml',
'application/adobe.page-template+xml', 'application/text'
}:
not_for_spine.add(id_)
seen = set()
for x in list(opf.iterspine()):
ref = x.get('idref', None)
if not ref or ref in not_for_spine or ref in seen:
x.getparent().remove(x)
continue
seen.add(ref)
if len(list(opf.iterspine())) == 0:
raise ValueError(_('No valid entries in the spine of this EPUB'))
with open('content.opf', 'wb') as nopf:
nopf.write(opf.render())
return os.path.abspath(u'content.opf')
def convert(self, stream, options, file_ext, log, accelerators):
"""Convert a KePub file into a structure calibre can process."""
log("KEPUBInput::convert - start")
from calibre.utils.zipfile import ZipFile
from calibre import walk
from calibre.ebooks import DRMError
from calibre.ebooks.metadata.opf2 import OPF
try:
zf = ZipFile(stream)
zf.extractall(os.getcwdu())
except Exception:
log.exception(
"KEPUB appears to be invalid ZIP file, trying a "
"more forgiving ZIP parser"
)
from calibre.utils.localunzip import extractall
stream.seek(0)
extractall(stream)
opf = self.find_opf()
if opf is None:
for f in walk(u"."):
if (
f.lower().endswith(".opf")
and "__MACOSX" not in f
and not os.path.basename(f).startswith(".")
):
opf = os.path.abspath(f)
break
path = getattr(stream, "name", "stream")
if opf is None:
raise ValueError(
_( # noqa: F821
"{0} is not a valid KEPUB file (could not find opf)"
).format(path)
)
encfile = os.path.abspath("rights.xml")
if os.path.exists(encfile):
raise DRMError(os.path.basename(path))
opf = os.path.relpath(opf, os.getcwdu())
parts = os.path.split(opf)
opf = OPF(opf, os.path.dirname(os.path.abspath(opf)))
self.encrypted_fonts = []
if len(parts) > 1 and parts[0]:
delta = "/".join(parts[:-1]) + "/"
for elem in opf.itermanifest():
elem.set("href", delta + elem.get("href"))
for elem in opf.iterguide():
elem.set("href", delta + elem.get("href"))
f = (
self.rationalize_cover3
if opf.package_version >= 3.0
else self.rationalize_cover2
)
self.removed_cover = f(opf, log)
self.optimize_opf_parsing = opf
for x in opf.itermanifest():
if x.get("media-type", "") == "application/x-dtbook+xml":
raise ValueError(
_("EPUB files with DTBook markup are not supported") # noqa: F821
)
not_for_spine = set()
for y in opf.itermanifest():
id_ = y.get("id", None)
if id_ and y.get("media-type", None) in {
"application/vnd.adobe-page-template+xml",
"application/vnd.adobe.page-template+xml",
"application/adobe-page-template+xml",
"application/adobe.page-template+xml",
"application/text",
}:
not_for_spine.add(id_)
seen = set()
for x in list(opf.iterspine()):
ref = x.get("idref", None)
if not ref or ref in not_for_spine or ref in seen:
x.getparent().remove(x)
continue
seen.add(ref)
if len(list(opf.iterspine())) == 0:
raise ValueError(
_("No valid entries in the spine of this EPUB") # noqa: F821
)
with open("content.opf", "wb") as nopf:
nopf.write(opf.render())
return os.path.abspath(u"content.opf")
