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 get_pages_pagebreak_tag(self, mobi_file_path):
'''
Determine pages based on the presence of
<mbp:pagebreak>.
'''
pages = []
# Get the MOBI html.
mr = MobiReader(mobi_file_path, default_log)
if mr.book_header.encryption_type != 0:
# DRMed book
return self.get_pages_fast(mobi_file_path)
mr.extract_text()
html = as_bytes(mr.mobi_html.lower())
for m in re.finditer(b'<[^>]*pagebreak[^>]*>', html):
pages.append(m.end())
return pages
def get_pages_pagebreak_tag(self, mobi_file_path):
'''
Determine pages based on the presense of
<mbp:pagebreak>.
'''
pages = []
# Get the MOBI html.
mr = MobiReader(mobi_file_path, default_log)
if mr.book_header.encryption_type != 0:
# DRMed book
return self.get_pages_fast(mobi_file_path)
mr.extract_text()
html = mr.mobi_html.lower()
for m in re.finditer('<[^>]*pagebreak[^>]*>', html):
pages.append(m.end())
return pages
def parse_mobi(pathtoebook, book_fmt):
mobiReader = MobiReader(pathtoebook, default_log)
html = b''
offset = 1
# use code from calibre.ebooks.mobi.reader.mobi8:Mobi8Reader.__call__
if book_fmt == 'AZW3' and mobiReader.kf8_type == 'joint':
offset = mobiReader.kf8_boundary + 2
mobiReader.extract_text(offset=offset)
html = mobiReader.mobi_html
if book_fmt == 'AZW3':
m8r = Mobi8Reader(mobiReader, default_log)
m8r.kf8_sections = mobiReader.sections[offset-1:]
m8r.read_indices()
m8r.build_parts()
html = b''.join(m8r.parts)
# match text between HTML tags
for match_text in re.finditer(b'>[^<>]+<', html):
yield (match_text.start() + 1, match_text.group(0)[1:-1])
def do_explode(path, dest):
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre.ebooks.mobi.reader.mobi8 import Mobi8Reader
with open(path, 'rb') as stream:
mr = MobiReader(stream, default_log, None, None)
with CurrentDir(dest):
mr = Mobi8Reader(mr, default_log, for_tweak=True)
opf = os.path.abspath(mr())
obfuscated_fonts = mr.encrypted_fonts
return opf, obfuscated_fonts
def convert(self, stream, options, file_ext, log, accelerators):
self.is_kf8 = False
self.mobi_is_joint = False
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from lxml import html
parse_cache = {}
try:
mr = MobiReader(stream, log, options.input_encoding,
options.debug_pipeline)
if mr.kf8_type is None:
mr.extract_content('.', parse_cache)
except:
mr = MobiReader(stream,
log,
options.input_encoding,
options.debug_pipeline,
try_extra_data_fix=True)
if mr.kf8_type is None:
mr.extract_content('.', parse_cache)
if mr.kf8_type is not None:
log('Found KF8 MOBI of type %r' % mr.kf8_type)
if mr.kf8_type == 'joint':
self.mobi_is_joint = True
from calibre.ebooks.mobi.reader.mobi8 import Mobi8Reader
mr = Mobi8Reader(mr, log)
opf = os.path.abspath(mr())
self.encrypted_fonts = mr.encrypted_fonts
self.is_kf8 = True
return opf
raw = parse_cache.pop('calibre_raw_mobi_markup', False)
if raw:
if isinstance(raw, unicode_type):
raw = raw.encode('utf-8')
with lopen('debug-raw.html', 'wb') as f:
f.write(raw)
from calibre.ebooks.oeb.base import close_self_closing_tags
for f, root in parse_cache.items():
raw = html.tostring(root,
encoding='utf-8',
method='xml',
include_meta_content_type=False)
raw = close_self_closing_tags(raw)
with lopen(f, 'wb') as q:
q.write(raw)
accelerators['pagebreaks'] = '//h:div[@class="mbp_pagebreak"]'
return mr.created_opf_path
def do_explode(path, dest):
with open(path, 'rb') as stream:
mr = MobiReader(stream, default_log, None, None)
with CurrentDir(dest):
mr = Mobi8Reader(mr, default_log)
opf = os.path.abspath(mr())
try:
os.remove('debug-raw.html')
except:
pass
return opf
def do_explode(path, dest):
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre.ebooks.mobi.reader.mobi8 import Mobi8Reader
with open(path, 'rb') as stream:
mr = MobiReader(stream, default_log, None, None)
with CurrentDir(dest):
mr = Mobi8Reader(mr, default_log)
opf = os.path.abspath(mr())
obfuscated_fonts = mr.encrypted_fonts
try:
os.remove('debug-raw.html')
except:
pass
return opf, obfuscated_fonts
def parse_mobi(book_path):
# use code from calibre.ebooks.mobi.reader.mobi8:Mobi8Reader.__call__
# and calibre.ebook.conversion.plugins.mobi_input:MOBIInput.convert
# https://github.com/kevinhendricks/KindleUnpack/blob/master/lib/mobi_k8proc.py#L216
try:
mr = MobiReader(book_path, default_log)
except Exception:
mr = MobiReader(book_path, default_log, try_extra_data_fix=True)
if mr.kf8_type == 'joint':
raise Exception('JointMOBI')
mr.check_for_drm()
mr.extract_text()
html = mr.mobi_html
if mr.kf8_type == 'standalone':
m8r = Mobi8Reader(mr, default_log)
m8r.kf8_sections = mr.sections
m8r.read_indices()
m8r.build_parts()
html = b''.join(m8r.parts)
# match text between HTML tags
for match_text in re.finditer(b'>[^<>]+<', html):
yield (match_text.group(0)[1:-1].decode('utf-8'),
match_text.start() + 1)
def convert(self, stream, options, file_ext, log,
accelerators):
self.is_kf8 = False
self.mobi_is_joint = False
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from lxml import html
parse_cache = {}
try:
mr = MobiReader(stream, log, options.input_encoding,
options.debug_pipeline)
if mr.kf8_type is None:
mr.extract_content('.', parse_cache)
except:
mr = MobiReader(stream, log, options.input_encoding,
options.debug_pipeline, try_extra_data_fix=True)
if mr.kf8_type is None:
mr.extract_content('.', parse_cache)
if mr.kf8_type is not None:
log('Found KF8 MOBI of type %r'%mr.kf8_type)
if mr.kf8_type == 'joint':
self.mobi_is_joint = True
from calibre.ebooks.mobi.reader.mobi8 import Mobi8Reader
mr = Mobi8Reader(mr, log)
opf = os.path.abspath(mr())
self.encrypted_fonts = mr.encrypted_fonts
self.is_kf8 = True
return opf
raw = parse_cache.pop('calibre_raw_mobi_markup', False)
if raw:
if isinstance(raw, unicode_type):
raw = raw.encode('utf-8')
with lopen('debug-raw.html', 'wb') as f:
f.write(raw)
from calibre.ebooks.oeb.base import close_self_closing_tags
for f, root in parse_cache.items():
raw = html.tostring(root, encoding='utf-8', method='xml',
include_meta_content_type=False)
raw = close_self_closing_tags(raw)
with lopen(f, 'wb') as q:
q.write(raw)
accelerators['pagebreaks'] = '//h:div[@class="mbp_pagebreak"]'
return mr.created_opf_path
def do_explode(path, dest):
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre.ebooks.mobi.reader.mobi8 import Mobi8Reader
with open(path, 'rb') as stream:
mr = MobiReader(stream, default_log, None, None)
with CurrentDir(dest):
mr = Mobi8Reader(mr, default_log)
opf = os.path.abspath(mr())
obfuscated_fonts = mr.encrypted_fonts
# If there are no images then the azw3 input plugin dumps all
# binary records as .unknown images, remove them
if os.path.exists('images') and os.path.isdir('images'):
files = os.listdir('images')
unknown = [x for x in files if x.endswith('.unknown')]
if len(files) == len(unknown):
[os.remove('images/'+f) for f in files]
try:
os.remove('debug-raw.html')
except:
pass
return opf, obfuscated_fonts
def get_pages_accurate(self, mobi_file_path):
'''
A more accurate but much more resource intensive and slower
method to calculate the page length.
Parses the uncompressed text. In an average paper back book
There are 32 lines per page and a maximum of 70 characters
per line.
Each paragraph starts a new line and every 70 characters
(minus markup) in a paragraph starts a new line. The
position after every 30 lines will be marked as a new
page.
This can be make more accurate by accounting for
<div class="mbp_pagebreak" /> as a new page marker.
And <br> elements as an empty line.
'''
pages = []
# Get the MOBI html.
mr = MobiReader(mobi_file_path, default_log)
if mr.book_header.encryption_type != 0:
# DRMed book
return self.get_pages_fast(mobi_file_path)
mr.extract_text()
# States
in_tag = False
in_p = False
check_p = False
closing = False
p_char_count = 0
# Get positions of every line
# A line is either a paragraph starting
# or every 70 characters in a paragraph.
lines = []
pos = -1
# We want this to be as fast as possible so we
# are going to do one pass across the text. re
# and string functions will parse the text each
# time they are called.
#
# We can can use .lower() here because we are
# not modifying the text. In this case the case
# doesn't matter just the absolute character and
# the position within the stream.
data = bytearray(as_bytes(mr.mobi_html.lower()))
slash, p, lt, gt = map(ord, '/p<>')
for c in data:
pos += 1
# Check if we are starting or stopping a p tag.
if check_p:
if c == slash:
closing = True
continue
elif c == p:
if closing:
in_p = False
else:
in_p = True
lines.append(pos - 2)
check_p = False
closing = False
continue
if c == lt:
in_tag = True
check_p = True
continue
elif c == gt:
in_tag = False
check_p = False
continue
if in_p and not in_tag:
p_char_count += 1
if p_char_count == 70:
lines.append(pos)
p_char_count = 0
# Every 30 lines is a new page
for i in range(0, len(lines), 32):
pages.append(lines[i])
return pages
def get_pages_accurate(self, mobi_file_path):
'''
A more accurate but much more resource intensive and slower
method to calculate the page length.
Parses the uncompressed text. In an average paper back book
There are 32 lines per page and a maximum of 70 characters
per line.
Each paragraph starts a new line and every 70 characters
(minus markup) in a paragraph starts a new line. The
position after every 30 lines will be marked as a new
page.
This can be make more accurate by accounting for
<div class="mbp_pagebreak" /> as a new page marker.
And <br> elements as an empty line.
'''
pages = []
# Get the MOBI html.
mr = MobiReader(mobi_file_path, default_log)
if mr.book_header.encryption_type != 0:
# DRMed book
return self.get_pages_fast(mobi_file_path)
mr.extract_text()
# States
in_tag = False
in_p = False
check_p = False
closing = False
p_char_count = 0
# Get positions of every line
# A line is either a paragraph starting
# or every 70 characters in a paragraph.
lines = []
pos = -1
# We want this to be as fast as possible so we
# are going to do one pass across the text. re
# and string functions will parse the text each
# time they are called.
#
# We can can use .lower() here because we are
# not modifying the text. In this case the case
# doesn't matter just the absolute character and
# the position within the stream.
for c in mr.mobi_html.lower():
pos += 1
# Check if we are starting or stopping a p tag.
if check_p:
if c == '/':
closing = True
continue
elif c == 'p':
if closing:
in_p = False
else:
in_p = True
lines.append(pos - 2)
check_p = False
closing = False
continue
if c == '<':
in_tag = True
check_p = True
continue
elif c == '>':
in_tag = False
check_p = False
continue
if in_p and not in_tag:
p_char_count += 1
if p_char_count == 70:
lines.append(pos)
p_char_count = 0
# Every 30 lines is a new page
for i in xrange(0, len(lines), 32):
pages.append(lines[i])
return pages
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
