def do_one_isbn_add(self):
try:
db = self.gui.library_view.model().db
try:
x = self.isbn_books.pop(0)
except IndexError:
self.gui.library_view.model().books_added(self.isbn_add_dialog.value)
self.isbn_add_dialog.accept()
self.gui.iactions['Edit Metadata'].download_metadata(
ids=self.add_by_isbn_ids, ensure_fields=frozenset(['title',
'authors']))
return
mi = MetaInformation(None)
mi.isbn = x['isbn']
if self.isbn_add_tags:
mi.tags = list(self.isbn_add_tags)
fmts = [] if x['path'] is None else [x['path']]
self.add_by_isbn_ids.add(db.import_book(mi, fmts))
self.isbn_add_dialog.value += 1
QTimer.singleShot(10, self.do_one_isbn_add)
except:
self.isbn_add_dialog.accept()
raise
def get_metadata_from_reader(rdr):
raw = rdr.GetFile(rdr.home)
home = BeautifulSoup(xml_to_unicode(raw, strip_encoding_pats=True,
resolve_entities=True)[0])
title = rdr.title
try:
x = rdr.GetEncoding()
codecs.lookup(x)
enc = x
except:
enc = 'cp1252'
title = force_unicode(title, enc)
authors = _get_authors(home)
mi = MetaInformation(title, authors)
publisher = _get_publisher(home)
if publisher:
mi.publisher = publisher
isbn = _get_isbn(home)
if isbn:
mi.isbn = isbn
comments = _get_comments(home)
if comments:
mi.comments = comments
cdata = _get_cover(home, rdr)
if cdata is not None:
mi.cover_data = ('jpg', cdata)
return mi
def do_one_isbn_add(self):
try:
db = self.gui.library_view.model().db
try:
x = self.isbn_books.pop(0)
except IndexError:
self.gui.library_view.model().books_added(
self.isbn_add_dialog.value)
self.isbn_add_dialog.accept()
self.gui.iactions['Edit Metadata'].download_metadata(
ids=self.add_by_isbn_ids,
ensure_fields=frozenset(['title', 'authors']))
return
mi = MetaInformation(None)
mi.isbn = x['isbn']
if self.isbn_add_tags:
mi.tags = list(self.isbn_add_tags)
fmts = [] if x['path'] is None else [x['path']]
self.add_by_isbn_ids.add(db.import_book(mi, fmts))
self.isbn_add_dialog.value += 1
QTimer.singleShot(10, self.do_one_isbn_add)
except:
self.isbn_add_dialog.accept()
raise
def get_metadata(stream, cpath=None):
if not podofo:
raise Unavailable(podofo_err)
pt = PersistentTemporaryFile('_podofo.pdf')
pt.write(stream.read())
pt.close()
server = Server(pool_size=1)
job = ParallelJob('read_pdf_metadata', 'Read pdf metadata',
lambda x,y:x, args=[pt.name, cpath])
server.add_job(job)
while not job.is_finished:
time.sleep(0.1)
job.update()
job.update()
server.close()
if job.result is None:
raise ValueError('Failed to read metadata: ' + job.details)
title, authors, creator, tags, ok = job.result
if not ok:
print 'Failed to extract cover:'
print job.details
if title == '_':
title = getattr(stream, 'name', _('Unknown'))
title = os.path.splitext(title)[0]
mi = MetaInformation(title, authors)
if creator:
mi.book_producer = creator
if tags:
mi.tags = tags
if os.path.exists(pt.name): os.remove(pt.name)
if ok:
mi.cover = cpath
return mi
def _metadata_from_formats(formats, force_read_metadata=False, pattern=None):
mi = MetaInformation(None, None)
formats.sort(cmp=lambda x,y: cmp(METADATA_PRIORITIES[path_to_ext(x)],
METADATA_PRIORITIES[path_to_ext(y)]))
extensions = list(map(path_to_ext, formats))
if 'opf' in extensions:
opf = formats[extensions.index('opf')]
mi2 = opf_metadata(opf)
if mi2 is not None and mi2.title:
return mi2
for path, ext in zip(formats, extensions):
with lopen(path, 'rb') as stream:
try:
newmi = get_metadata(stream, stream_type=ext,
use_libprs_metadata=True,
force_read_metadata=force_read_metadata,
pattern=pattern)
mi.smart_update(newmi)
except:
continue
if getattr(mi, 'application_id', None) is not None:
return mi
if not mi.title:
mi.title = _('Unknown')
if not mi.authors:
mi.authors = [_('Unknown')]
return mi
def get_djvu_metadata(stream, cover=True):
with TemporaryDirectory('_djvu_metadata_read') as djvupath:
stream.seek(0)
with open(os.path.join(djvupath, 'src.djvu'), 'wb') as f:
shutil.copyfileobj(stream, f)
try:
res = fork_job('calibre_plugins.djvu_metadata.djvu', 'get_djvu_metadata_worker', (djvupath, bool(cover)))
except WorkerError as e:
prints(e.orig_tb)
raise RuntimeError('Failed to run djvused')
info = res['result']
with open(res['stdout_stderr'], 'rb') as f:
raw = f.read().strip()
if raw:
prints(raw)
if info is None:
raise ValueError('Could not read metadata from djvu')
covpath = os.path.join(djvupath, 'cover.jpg')
cdata = None
if cover and os.path.exists(covpath):
with open(covpath, 'rb') as f:
cdata = f.read()
title = info.get('Title', None)
au = info.get('Author', None)
if au is None:
au = [_('Unknown')]
else:
au = string_to_authors(au)
mi = MetaInformation(title, au)
if cdata:
mi.cover_data = ('jpg', cdata)
return mi
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
mi = MetaInformation(_('Unknown'), [_('Unknown')])
stream.seek(0)
try:
with ZipFile(stream) as zf:
opf_name = get_first_opf_name(zf)
opf_stream = StringIO(zf.read(opf_name))
opf = OPF(opf_stream)
mi = opf.to_book_metadata()
if extract_cover:
cover_href = opf.raster_cover
if not cover_href:
for meta in opf.metadata.xpath('//*[local-name()="meta" and @name="cover"]'):
val = meta.get('content')
if val.rpartition('.')[2].lower() in {'jpeg', 'jpg', 'png'}:
cover_href = val
break
if cover_href:
try:
mi.cover_data = (os.path.splitext(cover_href)[1], zf.read(cover_href))
except Exception:
pass
except Exception:
return mi
return mi
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
name = getattr(stream, 'name', '').rpartition('.')[0]
if name:
name = os.path.basename(name)
mi = MetaInformation(name or _('Unknown'), [_('Unknown')])
stream.seek(0)
mdata = ''
for x in range(0, 4):
line = stream.readline().decode('utf-8', 'replace')
if not line:
break
else:
mdata += line
mdata = mdata[:1024]
mo = re.search(
'(?u)^[ ]*(?P<title>.+)[ ]*(\n{3}|(\r\n){3}|\r{3})[ ]*(?P<author>.+)[ ]*(\n|\r\n|\r)$',
mdata)
if mo is not None:
mi.title = mo.group('title')
mi.authors = mo.group('author').split(',')
return mi
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
mi = MetaInformation(_('Unknown'), [_('Unknown')])
stream.seek(0)
try:
with ZipFile(stream) as zf:
opf_name = get_first_opf_name(zf)
opf_stream = StringIO(zf.read(opf_name))
opf = OPF(opf_stream)
mi = opf.to_book_metadata()
if extract_cover:
cover_href = opf.raster_cover
if not cover_href:
for meta in opf.metadata.xpath('//*[local-name()="meta" and @name="cover"]'):
val = meta.get('content')
if val.rpartition('.')[2].lower() in {'jpeg', 'jpg', 'png'}:
cover_href = val
break
if cover_href:
try:
mi.cover_data = (os.path.splitext(cover_href)[1], zf.read(cover_href))
except Exception:
pass
except Exception:
return mi
return mi
def add_empty(self, *args):
'''
Add an empty book item to the library. This does not import any formats
from a book file.
'''
author = series = None
index = self.gui.library_view.currentIndex()
if index.isValid():
raw = index.model().db.authors(index.row())
if raw:
authors = [a.strip().replace('|', ',') for a in raw.split(',')]
if authors:
author = authors[0]
series = index.model().db.series(index.row())
dlg = AddEmptyBookDialog(self.gui, self.gui.library_view.model().db,
author, series)
if dlg.exec_() == dlg.Accepted:
num = dlg.qty_to_add
series = dlg.selected_series
db = self.gui.library_view.model().db
ids = []
for x in xrange(num):
mi = MetaInformation(_('Unknown'), dlg.selected_authors)
if series:
mi.series = series
mi.series_index = db.get_next_series_num_for(series)
ids.append(db.import_book(mi, []))
self.gui.library_view.model().books_added(num)
if hasattr(self.gui, 'db_images'):
self.gui.db_images.reset()
self.gui.tags_view.recount()
if ids:
ids.reverse()
self.gui.library_view.select_rows(ids)
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
name = getattr(stream, 'name', '').rpartition('.')[0]
if name:
name = os.path.basename(name)
mi = MetaInformation(name or _('Unknown'), [_('Unknown')])
stream.seek(0)
mdata = u''
for x in range(0, 4):
line = stream.readline().decode('utf-8', 'replace')
if line == '':
break
else:
mdata += line
mdata = mdata[:100]
mo = re.search('(?u)^[ ]*(?P<title>.+)[ ]*(\n{3}|(\r\n){3}|\r{3})[ ]*(?P<author>.+)[ ]*(\n|\r\n|\r)$', mdata)
if mo is not None:
mi.title = mo.group('title')
mi.authors = mo.group('author').split(',')
return mi
def add_empty(self, *args):
'''
Add an empty book item to the library. This does not import any formats
from a book file.
'''
author = series = None
index = self.gui.library_view.currentIndex()
if index.isValid():
raw = index.model().db.authors(index.row())
if raw:
authors = [a.strip().replace('|', ',') for a in raw.split(',')]
if authors:
author = authors[0]
series = index.model().db.series(index.row())
dlg = AddEmptyBookDialog(self.gui,
self.gui.library_view.model().db, author,
series)
if dlg.exec_() == dlg.Accepted:
num = dlg.qty_to_add
series = dlg.selected_series
db = self.gui.library_view.model().db
ids = []
for x in xrange(num):
mi = MetaInformation(_('Unknown'), dlg.selected_authors)
if series:
mi.series = series
mi.series_index = db.get_next_series_num_for(series)
ids.append(db.import_book(mi, []))
self.gui.library_view.model().books_added(num)
if hasattr(self.gui, 'db_images'):
self.gui.db_images.reset()
self.gui.tags_view.recount()
if ids:
ids.reverse()
self.gui.library_view.select_rows(ids)
def add_empty(self, *args):
'''
Add an empty book item to the library. This does not import any formats
from a book file.
'''
author = series = title = None
index = self.gui.library_view.currentIndex()
if index.isValid():
raw = index.model().db.authors(index.row())
if raw:
authors = [a.strip().replace('|', ',') for a in raw.split(',')]
if authors:
author = authors[0]
series = index.model().db.series(index.row())
title = index.model().db.title(index.row())
dlg = AddEmptyBookDialog(self.gui, self.gui.library_view.model().db,
author, series, dup_title=title)
if dlg.exec_() == dlg.Accepted:
temp_files = []
num = dlg.qty_to_add
series = dlg.selected_series
title = dlg.selected_title or _('Unknown')
db = self.gui.library_view.model().db
ids, orig_fmts = [], []
if dlg.duplicate_current_book:
origmi = db.get_metadata(index.row(), get_cover=True, cover_as_data=True)
if dlg.copy_formats.isChecked():
book_id = db.id(index.row())
orig_fmts = tuple(db.new_api.format(book_id, fmt, as_path=True) for fmt in db.new_api.formats(book_id))
for x in xrange(num):
if dlg.duplicate_current_book:
mi = origmi
else:
mi = MetaInformation(title, dlg.selected_authors)
if series:
mi.series = series
mi.series_index = db.get_next_series_num_for(series)
fmts = []
empty_format = gprefs.get('create_empty_format_file', '')
if dlg.duplicate_current_book and dlg.copy_formats.isChecked():
fmts = orig_fmts
elif empty_format:
from calibre.ebooks.oeb.polish.create import create_book
pt = PersistentTemporaryFile(suffix='.' + empty_format)
pt.close()
temp_files.append(pt.name)
create_book(mi, pt.name, fmt=empty_format)
fmts = [pt.name]
ids.append(db.import_book(mi, fmts))
tuple(map(os.remove, orig_fmts))
self.gui.library_view.model().books_added(num)
self.gui.refresh_cover_browser()
self.gui.tags_view.recount()
if ids:
ids.reverse()
self.gui.library_view.select_rows(ids)
for path in temp_files:
os.remove(path)
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 add_empty(self, *args):
'''
Add an empty book item to the library. This does not import any formats
from a book file.
'''
author = series = title = None
index = self.gui.library_view.currentIndex()
if index.isValid():
raw = index.model().db.authors(index.row())
if raw:
authors = [a.strip().replace('|', ',') for a in raw.split(',')]
if authors:
author = authors[0]
series = index.model().db.series(index.row())
title = index.model().db.title(index.row())
dlg = AddEmptyBookDialog(self.gui, self.gui.library_view.model().db,
author, series, dup_title=title)
if dlg.exec_() == dlg.Accepted:
temp_files = []
num = dlg.qty_to_add
series = dlg.selected_series
title = dlg.selected_title or _('Unknown')
db = self.gui.library_view.model().db
ids, orig_fmts = [], []
if dlg.duplicate_current_book:
origmi = db.get_metadata(index.row(), get_cover=True, cover_as_data=True)
if dlg.copy_formats.isChecked():
book_id = db.id(index.row())
orig_fmts = tuple(db.new_api.format(book_id, fmt, as_path=True) for fmt in db.new_api.formats(book_id))
for x in xrange(num):
if dlg.duplicate_current_book:
mi = origmi
else:
mi = MetaInformation(title, dlg.selected_authors)
if series:
mi.series = series
mi.series_index = db.get_next_series_num_for(series)
fmts = []
empty_format = gprefs.get('create_empty_format_file', '')
if dlg.duplicate_current_book and dlg.copy_formats.isChecked():
fmts = orig_fmts
elif empty_format:
from calibre.ebooks.oeb.polish.create import create_book
pt = PersistentTemporaryFile(suffix='.' + empty_format)
pt.close()
temp_files.append(pt.name)
create_book(mi, pt.name, fmt=empty_format)
fmts = [pt.name]
ids.append(db.import_book(mi, fmts))
tuple(map(os.remove, orig_fmts))
self.gui.library_view.model().books_added(num)
self.gui.refresh_cover_browser()
self.gui.tags_view.recount()
if ids:
ids.reverse()
self.gui.library_view.select_rows(ids)
for path in temp_files:
os.remove(path)
def add_annotation_to_library(self, db, db_id, annotation):
from calibre.ebooks.BeautifulSoup import Tag
from calibre.ebooks.metadata import MetaInformation
bm = annotation
ignore_tags = set(['Catalog', 'Clippings'])
if bm.type == 'kindle_bookmark':
mi = db.get_metadata(db_id, index_is_id=True)
user_notes_soup = self.generate_annotation_html(bm.value)
if mi.comments:
a_offset = mi.comments.find('<div class="user_annotations">')
ad_offset = mi.comments.find(
'<hr class="annotations_divider" />')
if a_offset >= 0:
mi.comments = mi.comments[:a_offset]
if ad_offset >= 0:
mi.comments = mi.comments[:ad_offset]
if set(mi.tags).intersection(ignore_tags):
return
if mi.comments:
hrTag = Tag(user_notes_soup, 'hr')
hrTag['class'] = 'annotations_divider'
user_notes_soup.insert(0, hrTag)
mi.comments += unicode(user_notes_soup.prettify())
else:
mi.comments = unicode(user_notes_soup.prettify())
# Update library comments
db.set_comment(db_id, mi.comments)
# Add bookmark file to db_id
db.add_format_with_hooks(db_id,
bm.value.bookmark_extension,
bm.value.path,
index_is_id=True)
elif bm.type == 'kindle_clippings':
# Find 'My Clippings' author=Kindle in database, or add
last_update = 'Last modified %s' % strftime(
u'%x %X', bm.value['timestamp'].timetuple())
mc_id = list(
db.data.search_getting_ids('title:"My Clippings"',
'',
sort_results=False))
if mc_id:
db.add_format_with_hooks(mc_id[0],
'TXT',
bm.value['path'],
index_is_id=True)
mi = db.get_metadata(mc_id[0], index_is_id=True)
mi.comments = last_update
db.set_metadata(mc_id[0], mi)
else:
mi = MetaInformation('My Clippings', authors=['Kindle'])
mi.tags = ['Clippings']
mi.comments = last_update
db.add_books([bm.value['path']], ['txt'], [mi])
def _start_splitmerge(self,book_list, tdir=None, db=None):
# logger.debug(book_list)
em = self.get_epubmerge_plugin()
es = self.get_epubsplit_plugin()
good_list = [ b for b in book_list if b['good'] ]
tmp = PersistentTemporaryFile(prefix='merge-',
suffix='.epub',
dir=tdir)
if len(good_list) == 1:
deftitle = "New "+good_list[0]['title']
defauthors = good_list[0]['authors']
else:
deftitle = "New Chapters Anthology"
defauthors = ["Various Authors"]
mi = MetaInformation(deftitle,defauthors)
tagslists = [ x['tags'] for x in good_list ]
mi.tags = [item for sublist in tagslists for item in sublist]
mi.comments = "<p>New Chapters from:</p>"
mi.comments += '<br/>'.join( [ "%s by %s"%(x['title'],", ".join(x['authors'])) for x in good_list ] )
em.do_merge(tmp,
[b['splittmp'] for b in good_list],
authoropts=mi.authors,
titleopt=mi.title,
descopt=mi.comments,
tags=mi.tags,
keepmetadatafiles=False,
)
book_id = db.create_book_entry(mi,
add_duplicates=True)
db.add_format_with_hooks(book_id,
'EPUB',
tmp, index_is_id=True)
self.gui.library_view.model().books_added(1)
self.gui.library_view.model().refresh_ids([book_id])
# self.gui.iactions['Edit Metadata'].edit_metadata(False)
self.gui.tags_view.recount()
## run word counts
cp_plugin = self.gui.iactions['Count Pages']
cp_plugin.count_statistics([book_id],['WordCount'])
## run auto convert
self.gui.iactions['Convert Books'].auto_convert_auto_add([book_id])
## add to FFF update lists
self.gui.library_view.select_rows([book_id])
fff_plugin = self.gui.iactions['FanFicFare']
fff_plugin.update_lists()
remove_dir(tdir)
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
mi = MetaInformation(_('Unknown'), [_('Unknown')])
stream.seek(0)
pheader = PdbHeaderReader(stream)
section_data = None
for i in range(1, pheader.num_sections):
raw_data = pheader.section_data(i)
section_header = SectionHeader(raw_data)
if section_header.type == DATATYPE_METADATA:
section_data = raw_data[8:]
break
if not section_data:
return mi
default_encoding = 'latin-1'
record_count, = struct.unpack('>H', section_data[0:2])
adv = 0
title = None
author = None
pubdate = 0
for i in range(record_count):
try:
type, length = struct.unpack_from('>HH', section_data, 2 + adv)
except struct.error:
break
# CharSet
if type == 1:
val, = struct.unpack('>H', section_data[6+adv:8+adv])
default_encoding = MIBNUM_TO_NAME.get(val, 'latin-1')
# Author
elif type == 4:
author = section_data[6+adv+(2*length)]
# Title
elif type == 5:
title = section_data[6+adv+(2*length)]
# Publication Date
elif type == 6:
pubdate, = struct.unpack('>I', section_data[6+adv:6+adv+4])
adv += 2*length
if title:
mi.title = title.replace('\0', '').decode(default_encoding, 'replace')
if author:
author = author.replace('\0', '').decode(default_encoding, 'replace')
mi.author = author.split(',')
mi.pubdate = datetime.fromtimestamp(pubdate)
return mi
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
mi = MetaInformation(_('Unknown'), [_('Unknown')])
stream.seek(0)
pheader = PdbHeaderReader(stream)
section_data = None
for i in range(1, pheader.num_sections):
raw_data = pheader.section_data(i)
section_header = SectionHeader(raw_data)
if section_header.type == DATATYPE_METADATA:
section_data = raw_data[8:]
break
if not section_data:
return mi
default_encoding = 'latin-1'
record_count, = struct.unpack('>H', section_data[0:2])
adv = 0
title = None
author = None
pubdate = 0
for i in xrange(record_count):
try:
type, length = struct.unpack_from('>HH', section_data, 2 + adv)
except struct.error:
break
# CharSet
if type == 1:
val, = struct.unpack('>H', section_data[6+adv:8+adv])
default_encoding = MIBNUM_TO_NAME.get(val, 'latin-1')
# Author
elif type == 4:
author = section_data[6+adv+(2*length)]
# Title
elif type == 5:
title = section_data[6+adv+(2*length)]
# Publication Date
elif type == 6:
pubdate, = struct.unpack('>I', section_data[6+adv:6+adv+4])
adv += 2*length
if title:
mi.title = title.replace('\0', '').decode(default_encoding, 'replace')
if author:
author = author.replace('\0', '').decode(default_encoding, 'replace')
mi.author = author.split(',')
mi.pubdate = datetime.fromtimestamp(pubdate)
return mi
def __init__(self, raw, codec, title):
self.doctype = raw[:4]
self.length, self.num_items = struct.unpack('>LL', raw[4:12])
raw = raw[12:]
pos = 0
self.mi = MetaInformation(_('Unknown'), [_('Unknown')])
self.has_fake_cover = True
self.start_offset = None
left = self.num_items
self.kf8_header = None
self.uuid = self.cdetype = None
while left > 0:
left -= 1
idx, size = struct.unpack('>LL', raw[pos:pos + 8])
content = raw[pos + 8:pos + size]
pos += size
if idx >= 100 and idx < 200:
self.process_metadata(idx, content, codec)
elif idx == 203:
self.has_fake_cover = bool(struct.unpack('>L', content)[0])
elif idx == 201:
co, = struct.unpack('>L', content)
if co < NULL_INDEX:
self.cover_offset = co
elif idx == 202:
self.thumbnail_offset, = struct.unpack('>L', content)
elif idx == 501:
try:
self.cdetype = content.decode('ascii')
except UnicodeDecodeError:
self.cdetype = None
# cdetype
if content == b'EBSP':
if not self.mi.tags:
self.mi.tags = []
self.mi.tags.append(_('Sample Book'))
elif idx == 502:
# last update time
pass
elif idx == 503: # Long title
# Amazon seems to regard this as the definitive book title
# rather than the title from the PDB header. In fact when
# sending MOBI files through Amazon's email service if the
# title contains non ASCII chars or non filename safe chars
# they are messed up in the PDB header
try:
title = content.decode(codec)
except:
pass
#else:
# print 'unknown record', idx, repr(content)
if title:
self.mi.title = replace_entities(title)
def get_clippings_cid(self, title):
'''
Find or create cid for title
'''
cid = None
try:
cid = list(self.parent.opts.gui.current_db.data.parse('title:"%s" and tag:Clippings' % title))[0]
except:
mi = MetaInformation(title, authors = ['Various'])
mi.tags = ['Clippings']
cid = self.parent.opts.gui.current_db.create_book_entry(mi, cover=None,
add_duplicates=False, force_id=None)
return cid
def get_clippings_cid(self, title):
'''
Find or create cid for title
'''
cid = None
try:
cid = list(self.parent.opts.gui.current_db.data.parse('title:"%s" and tag:Clippings' % title))[0]
except:
mi = MetaInformation(title, authors = ['Various'])
mi.tags = ['Clippings']
cid = self.parent.opts.gui.current_db.create_book_entry(mi, cover=None,
add_duplicates=False, force_id=None)
return cid
def get_metadata(stream, cover=True):
with TemporaryDirectory('_pdf_metadata_read') as pdfpath:
stream.seek(0)
with open(os.path.join(pdfpath, 'src.pdf'), 'wb') as f:
shutil.copyfileobj(stream, f)
try:
res = fork_job('calibre.ebooks.metadata.pdf', 'read_info',
(pdfpath, bool(cover)))
except WorkerError as e:
prints(e.orig_tb)
raise RuntimeError('Failed to run pdfinfo')
info = res['result']
with open(res['stdout_stderr'], 'rb') as f:
raw = f.read().strip()
if raw:
prints(raw)
if not info:
raise ValueError('Could not read info dict from PDF')
covpath = os.path.join(pdfpath, 'cover.jpg')
cdata = None
if cover and os.path.exists(covpath):
with open(covpath, 'rb') as f:
cdata = f.read()
title = info.get('Title', None)
au = info.get('Author', None)
if au is None:
au = [_('Unknown')]
else:
au = string_to_authors(au)
mi = MetaInformation(title, au)
#if isbn is not None:
# mi.isbn = isbn
creator = info.get('Creator', None)
if creator:
mi.book_producer = creator
keywords = info.get('Keywords', None)
mi.tags = []
if keywords:
mi.tags = [x.strip() for x in keywords.split(',')]
subject = info.get('Subject', None)
if subject:
mi.tags.insert(0, subject)
if cdata:
mi.cover_data = ('jpeg', cdata)
return mi
def get_metadata(stream, extract_cover=True):
"""
Return metadata as a L{MetaInfo} object
"""
mi = MetaInformation(None, [_('Unknown')])
stream.seek(0)
pheader = PdbHeaderReader(stream)
# Only Dropbook produced 132 byte record0 files are supported
if len(pheader.section_data(0)) == 132:
hr = HeaderRecord(pheader.section_data(0))
if hr.compression in (2, 10) and hr.has_metadata == 1:
try:
mdata = pheader.section_data(hr.metadata_offset)
mdata = mdata.decode('cp1252', 'replace').split('\x00')
mi.title = re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[0])
mi.authors = [re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[1])]
mi.publisher = re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[3])
mi.isbn = re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[4])
except Exception:
pass
if extract_cover:
mi.cover_data = get_cover(pheader, hr)
if not mi.title:
mi.title = pheader.title if pheader.title else _('Unknown')
return mi
def add_empty(self, *args):
'''
Add an empty book item to the library. This does not import any formats
from a book file.
'''
author = series = None
index = self.gui.library_view.currentIndex()
if index.isValid():
raw = index.model().db.authors(index.row())
if raw:
authors = [a.strip().replace('|', ',') for a in raw.split(',')]
if authors:
author = authors[0]
series = index.model().db.series(index.row())
dlg = AddEmptyBookDialog(self.gui,
self.gui.library_view.model().db, author,
series)
if dlg.exec_() == dlg.Accepted:
temp_files = []
num = dlg.qty_to_add
series = dlg.selected_series
title = dlg.selected_title or _('Unknown')
db = self.gui.library_view.model().db
ids = []
for x in xrange(num):
mi = MetaInformation(title, dlg.selected_authors)
if series:
mi.series = series
mi.series_index = db.get_next_series_num_for(series)
fmts = []
empty_format = gprefs.get('create_empty_format_file', '')
if empty_format:
from calibre.ebooks.oeb.polish.create import create_book
pt = PersistentTemporaryFile(suffix='.' + empty_format)
pt.close()
temp_files.append(pt.name)
create_book(mi, pt.name, fmt=empty_format)
fmts = [pt.name]
ids.append(db.import_book(mi, fmts))
self.gui.library_view.model().books_added(num)
if hasattr(self.gui, 'db_images'):
self.gui.db_images.beginResetModel(
), self.gui.db_images.endResetModel()
self.gui.tags_view.recount()
if ids:
ids.reverse()
self.gui.library_view.select_rows(ids)
for path in temp_files:
os.remove(path)
def add_annotation_to_library(self, db, db_id, annotation):
from calibre.ebooks.BeautifulSoup import Tag
from calibre.ebooks.metadata import MetaInformation
bm = annotation
ignore_tags = set(['Catalog', 'Clippings'])
if bm.type == 'kindle_bookmark':
mi = db.get_metadata(db_id, index_is_id=True)
user_notes_soup = self.generate_annotation_html(bm.value)
if mi.comments:
a_offset = mi.comments.find('<div class="user_annotations">')
ad_offset = mi.comments.find('<hr class="annotations_divider" />')
if a_offset >= 0:
mi.comments = mi.comments[:a_offset]
if ad_offset >= 0:
mi.comments = mi.comments[:ad_offset]
if set(mi.tags).intersection(ignore_tags):
return
if mi.comments:
hrTag = Tag(user_notes_soup,'hr')
hrTag['class'] = 'annotations_divider'
user_notes_soup.insert(0, hrTag)
mi.comments += unicode(user_notes_soup.prettify())
else:
mi.comments = unicode(user_notes_soup.prettify())
# Update library comments
db.set_comment(db_id, mi.comments)
# Add bookmark file to db_id
db.add_format_with_hooks(db_id, bm.value.bookmark_extension,
bm.value.path, index_is_id=True)
elif bm.type == 'kindle_clippings':
# Find 'My Clippings' author=Kindle in database, or add
last_update = 'Last modified %s' % strftime(u'%x %X',bm.value['timestamp'].timetuple())
mc_id = list(db.data.search_getting_ids('title:"My Clippings"', '', sort_results=False))
if mc_id:
db.add_format_with_hooks(mc_id[0], 'TXT', bm.value['path'],
index_is_id=True)
mi = db.get_metadata(mc_id[0], index_is_id=True)
mi.comments = last_update
db.set_metadata(mc_id[0], mi)
else:
mi = MetaInformation('My Clippings', authors=['Kindle'])
mi.tags = ['Clippings']
mi.comments = last_update
db.add_books([bm.value['path']], ['txt'], [mi])
def get_metadata(f):
read = lambda at, amount: _read(f, at, amount)
f.seek(0)
buf = f.read(12)
if buf[4:] == 'ftypLRX2':
offset = 0
while True:
offset += word_be(buf[:4])
try:
buf = read(offset, 8)
except:
raise ValueError('Not a valid LRX file')
if buf[4:] == 'bbeb':
break
offset += 8
buf = read(offset, 16)
if buf[:8].decode('utf-16-le') != 'LRF\x00':
raise ValueError('Not a valid LRX file')
lrf_version = word_le(buf[8:12])
offset += 0x4c
compressed_size = short_le(read(offset, 2))
offset += 2
if lrf_version >= 800:
offset += 6
compressed_size -= 4
uncompressed_size = word_le(read(offset, 4))
info = decompress(f.read(compressed_size))
if len(info) != uncompressed_size:
raise ValueError('LRX file has malformed metadata section')
root = etree.fromstring(info)
bi = root.find('BookInfo')
title = bi.find('Title')
title_sort = title.get('reading', None)
title = title.text
author = bi.find('Author')
author_sort = author.get('reading', None)
mi = MetaInformation(title, string_to_authors(author.text))
mi.title_sort, mi.author_sort = title_sort, author_sort
author = author.text
publisher = bi.find('Publisher')
mi.publisher = getattr(publisher, 'text', None)
mi.tags = [x.text for x in bi.findall('Category')]
mi.language = root.find('DocInfo').find('Language').text
return mi
elif buf[4:8] == 'LRX':
raise ValueError('Librie LRX format not supported')
else:
raise ValueError('Not a LRX file')
def _get_metadata(self, id, args, kwargs):
from calibre.ebooks.metadata.meta import get_metadata
try:
mi = get_metadata(*args, **kwargs)
except:
mi = MetaInformation('', [_('Unknown')])
self.emit(SIGNAL('metadata(PyQt_PyObject, PyQt_PyObject)'), id, mi)
def _from_formats(self, id, args, kwargs):
from calibre.ebooks.metadata.meta import metadata_from_formats
try:
mi = metadata_from_formats(*args, **kwargs)
except:
mi = MetaInformation('', [_('Unknown')])
self.metadataf.emit(id, mi)
def _get_metadata(self, id, args, kwargs):
from calibre.ebooks.metadata.meta import get_metadata
try:
mi = get_metadata(*args, **kwargs)
except:
mi = MetaInformation('', [_('Unknown')])
self.metadata.emit(id, mi)
def get_comic_metadata(stream, stream_type, series_index='volume'):
# See http://code.google.com/p/comicbookinfo/wiki/Example
from calibre.ebooks.metadata import MetaInformation
comment = None
mi = MetaInformation(None, None)
if stream_type == 'cbz':
from calibre.utils.zipfile import ZipFile
zf = ZipFile(stream)
comment = zf.comment
elif stream_type == 'cbr':
from calibre.utils.unrar import comment as get_comment
comment = get_comment(stream)
if comment:
import json
m = json.loads(comment)
if hasattr(m, 'iterkeys'):
for cat in m.iterkeys():
if cat.startswith('ComicBookInfo'):
get_comic_book_info(m[cat], mi, series_index=series_index)
break
return mi
def add_annotation_to_library(self, db, db_id, annotation):
from calibre.ebooks.BeautifulSoup import Tag
from calibre.ebooks.metadata import MetaInformation
bm = annotation
ignore_tags = set(["Catalog", "Clippings"])
if bm.type == "kindle_bookmark":
mi = db.get_metadata(db_id, index_is_id=True)
user_notes_soup = self.generate_annotation_html(bm.value)
if mi.comments:
a_offset = mi.comments.find('<div class="user_annotations">')
ad_offset = mi.comments.find('<hr class="annotations_divider" />')
if a_offset >= 0:
mi.comments = mi.comments[:a_offset]
if ad_offset >= 0:
mi.comments = mi.comments[:ad_offset]
if set(mi.tags).intersection(ignore_tags):
return
if mi.comments:
hrTag = Tag(user_notes_soup, "hr")
hrTag["class"] = "annotations_divider"
user_notes_soup.insert(0, hrTag)
mi.comments += unicode(user_notes_soup.prettify())
else:
mi.comments = unicode(user_notes_soup.prettify())
# Update library comments
db.set_comment(db_id, mi.comments)
# Add bookmark file to db_id
db.add_format_with_hooks(db_id, bm.value.bookmark_extension, bm.value.path, index_is_id=True)
elif bm.type == "kindle_clippings":
# Find 'My Clippings' author=Kindle in database, or add
last_update = "Last modified %s" % strftime(u"%x %X", bm.value["timestamp"].timetuple())
mc_id = list(db.data.search_getting_ids('title:"My Clippings"', ""))
if mc_id:
db.add_format_with_hooks(mc_id[0], "TXT", bm.value["path"], index_is_id=True)
mi = db.get_metadata(mc_id[0], index_is_id=True)
mi.comments = last_update
db.set_metadata(mc_id[0], mi)
else:
mi = MetaInformation("My Clippings", authors=["Kindle"])
mi.tags = ["Clippings"]
mi.comments = last_update
db.add_books([bm.value["path"]], ["txt"], [mi])
def add_empty(self, *args):
'''
Add an empty book item to the library. This does not import any formats
from a book file.
'''
author = series = None
index = self.gui.library_view.currentIndex()
if index.isValid():
raw = index.model().db.authors(index.row())
if raw:
authors = [a.strip().replace('|', ',') for a in raw.split(',')]
if authors:
author = authors[0]
series = index.model().db.series(index.row())
dlg = AddEmptyBookDialog(self.gui, self.gui.library_view.model().db,
author, series)
if dlg.exec_() == dlg.Accepted:
temp_files = []
num = dlg.qty_to_add
series = dlg.selected_series
title = dlg.selected_title or _('Unknown')
db = self.gui.library_view.model().db
ids = []
for x in xrange(num):
mi = MetaInformation(title, dlg.selected_authors)
if series:
mi.series = series
mi.series_index = db.get_next_series_num_for(series)
fmts = []
empty_format = gprefs.get('create_empty_format_file', '')
if empty_format:
from calibre.ebooks.oeb.polish.create import create_book
pt = PersistentTemporaryFile(suffix='.' + empty_format)
pt.close()
temp_files.append(pt.name)
create_book(mi, pt.name, fmt=empty_format)
fmts = [pt.name]
ids.append(db.import_book(mi, fmts))
self.gui.library_view.model().books_added(num)
if hasattr(self.gui, 'db_images'):
self.gui.db_images.beginResetModel(), self.gui.db_images.endResetModel()
self.gui.tags_view.recount()
if ids:
ids.reverse()
self.gui.library_view.select_rows(ids)
for path in temp_files:
os.remove(path)
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 get_metadata(stream):
''' Return fb2 metadata as a L{MetaInformation} object '''
root = _get_fbroot(stream)
book_title = _parse_book_title(root)
authors = _parse_authors(root)
# fallback for book_title
if book_title:
book_title = unicode(book_title)
else:
book_title = force_unicode(
os.path.splitext(
os.path.basename(getattr(stream, 'name', _('Unknown'))))[0])
mi = MetaInformation(book_title, authors)
try:
_parse_cover(root, mi)
except:
pass
try:
_parse_comments(root, mi)
except:
pass
try:
_parse_tags(root, mi)
except:
pass
try:
_parse_series(root, mi)
except:
pass
try:
_parse_isbn(root, mi)
except:
pass
try:
_parse_publisher(root, mi)
except:
pass
try:
_parse_pubdate(root, mi)
except:
pass
#try:
# _parse_timestamp(root, mi)
#except:
# pass
try:
_parse_language(root, mi)
except:
pass
#_parse_uuid(root, mi)
#if DEBUG:
# prints(mi)
return mi
def get_metadata(stream, extract_cover=True):
"""
Return metadata as a L{MetaInfo} object
"""
mi = MetaInformation(None, [_('Unknown')])
stream.seek(0)
pheader = PdbHeaderReader(stream)
# Only Dropbook produced 132 byte record0 files are supported
if len(pheader.section_data(0)) == 132:
hr = HeaderRecord(pheader.section_data(0))
if hr.compression in (2, 10) and hr.has_metadata == 1:
try:
mdata = pheader.section_data(hr.metadata_offset)
mdata = mdata.split('\x00')
mi.title = re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[0])
mi.authors = [re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[1])]
mi.publisher = re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[3])
mi.isbn = re.sub(r'[^a-zA-Z0-9 \._=\+\-!\?,\'\"]', '', mdata[4])
except:
pass
if extract_cover:
mi.cover_data = get_cover(pheader, hr)
if not mi.title:
mi.title = pheader.title if pheader.title else _('Unknown')
return mi
def get_metadata(stream, extract_cover=True):
""" Return metadata as a L{MetaInfo} object """
mi = MetaInformation(_('Unknown'), [_('Unknown')])
snbFile = SNBFile()
try:
if not hasattr(stream, 'write'):
snbFile.Parse(io.BytesIO(stream), True)
else:
stream.seek(0)
snbFile.Parse(stream, True)
meta = snbFile.GetFileStream('snbf/book.snbf')
if meta is not None:
meta = etree.fromstring(meta)
mi.title = meta.find('.//head/name').text
mi.authors = [meta.find('.//head/author').text]
mi.language = meta.find('.//head/language').text.lower().replace('_', '-')
mi.publisher = meta.find('.//head/publisher').text
if extract_cover:
cover = meta.find('.//head/cover')
if cover is not None and cover.text is not None:
root, ext = os.path.splitext(cover.text)
if ext == '.jpeg':
ext = '.jpg'
mi.cover_data = (ext[-3:], snbFile.GetFileStream('snbc/images/' + cover.text))
except Exception:
import traceback
traceback.print_exc()
return mi
def set_metadata(stream,
mi,
apply_null=False,
update_timestamp=False,
force_identifiers=False):
stream.seek(0)
reader = get_zip_reader(stream, root=os.getcwdu())
raster_cover = reader.opf.raster_cover
mi = MetaInformation(mi)
new_cdata = None
replacements = {}
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
new_cover = cpath = None
if new_cdata and raster_cover:
try:
cpath = posixpath.join(posixpath.dirname(reader.opf_path),
raster_cover)
cover_replacable = not reader.encryption_meta.is_encrypted(cpath) and \
os.path.splitext(cpath)[1].lower() in ('.png', '.jpg', '.jpeg')
if cover_replacable:
new_cover = _write_new_cover(new_cdata, cpath)
replacements[cpath] = open(new_cover.name, 'rb')
except:
import traceback
traceback.print_exc()
update_metadata(reader.opf,
mi,
apply_null=apply_null,
update_timestamp=update_timestamp,
force_identifiers=force_identifiers)
newopf = StringIO(reader.opf.render())
if isinstance(reader.archive, LocalZipFile):
reader.archive.safe_replace(reader.container[OPF.MIMETYPE],
newopf,
extra_replacements=replacements)
else:
safe_replace(stream,
reader.container[OPF.MIMETYPE],
newopf,
extra_replacements=replacements)
try:
if cpath is not None:
replacements[cpath].close()
os.remove(replacements[cpath].name)
except:
pass
def get_metadata(stream):
"""
Return metadata as a L{MetaInfo} object
"""
stream.seek(0)
if stream.read(5) != r'{\rtf':
return MetaInformation(_('Unknown'))
block = get_document_info(stream)[0]
if not block:
return MetaInformation(_('Unknown'))
stream.seek(0)
cpg = detect_codepage(stream)
stream.seek(0)
title_match = title_pat.search(block)
if title_match is not None:
title = decode(title_match.group(1).strip(), cpg)
else:
title = _('Unknown')
author_match = author_pat.search(block)
if author_match is not None:
author = decode(author_match.group(1).strip(), cpg)
else:
author = None
mi = MetaInformation(title)
if author:
mi.authors = string_to_authors(author)
comment_match = comment_pat.search(block)
if comment_match is not None:
comment = decode(comment_match.group(1).strip(), cpg)
mi.comments = comment
tags_match = tags_pat.search(block)
if tags_match is not None:
tags = decode(tags_match.group(1).strip(), cpg)
mi.tags = list(filter(None, (x.strip() for x in tags.split(','))))
publisher_match = publisher_pat.search(block)
if publisher_match is not None:
publisher = decode(publisher_match.group(1).strip(), cpg)
mi.publisher = publisher
return mi
def get_metadata(stream):
""" Return metadata as a L{MetaInfo} object """
title = 'Unknown'
mi = MetaInformation(title, ['Unknown'])
stream.seek(0)
try:
if not stream.read(14) == MAGIC:
print >> sys.stderr, u'Couldn\'t read RB header from file'
return mi
stream.read(10)
read_i32 = lambda: struct.unpack('<I', stream.read(4))[0]
stream.seek(read_i32())
toc_count = read_i32()
for i in range(toc_count):
stream.read(32)
length, offset, flag = read_i32(), read_i32(), read_i32()
if flag == 2:
break
else:
print >> sys.stderr, u'Couldn\'t find INFO from RB file'
return mi
stream.seek(offset)
info = stream.read(length).splitlines()
for line in info:
if '=' not in line:
continue
key, value = line.split('=')
if key.strip() == 'TITLE':
mi.title = value.strip()
elif key.strip() == 'AUTHOR':
mi.author = value
mi.authors = string_to_authors(value)
except Exception as err:
msg = u'Couldn\'t read metadata from rb: %s with error %s' % (
mi.title, unicode(err))
print >> sys.stderr, msg.encode('utf8')
raise
return mi
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
mi = MetaInformation(_('Unknown'), [_('Unknown')])
stream.seek(0)
try:
with ZipFile(stream) as zf:
opf_name = get_first_opf_name(zf)
opf_stream = StringIO(zf.read(opf_name))
opf = OPF(opf_stream)
mi = opf.to_book_metadata()
if extract_cover:
cover_href = opf.raster_cover
if cover_href:
mi.cover_data = (os.path.splitext(cover_href)[1], zf.read(cover_href))
except:
return mi
return mi
def get_metadata(stream):
""" Return metadata as a L{MetaInfo} object """
title = 'Unknown'
mi = MetaInformation(title, ['Unknown'])
stream.seek(0)
try:
if not stream.read(14) == MAGIC:
print(u'Couldn\'t read RB header from file', file=sys.stderr)
return mi
stream.read(10)
read_i32 = lambda: struct.unpack('<I', stream.read(4))[0]
stream.seek(read_i32())
toc_count = read_i32()
for i in range(toc_count):
stream.read(32)
length, offset, flag = read_i32(), read_i32(), read_i32()
if flag == 2:
break
else:
print(u'Couldn\'t find INFO from RB file', file=sys.stderr)
return mi
stream.seek(offset)
info = stream.read(length).splitlines()
for line in info:
if '=' not in line:
continue
key, value = line.split('=')
if key.strip() == 'TITLE':
mi.title = value.strip()
elif key.strip() == 'AUTHOR':
mi.author = value
mi.authors = string_to_authors(value)
except Exception as err:
msg = u'Couldn\'t read metadata from rb: %s with error %s'%(mi.title, unicode(err))
print(msg.encode('utf8'), file=sys.stderr)
raise
return mi
def get_metadata_quick(raw):
p = podofo.PDFDoc()
p.load(raw)
title = p.title
if not title:
title = '_'
author = p.author
authors = string_to_authors(author) if author else [_('Unknown')]
creator = p.creator
try:
tags = [x.strip() for x in p.keywords.split(u',')]
tags = [x for x in tags if x]
except:
tags = []
mi = MetaInformation(title, authors)
if creator:
mi.book_producer = creator
if tags:
mi.tags = tags
return mi
def get_metadata_quick(raw):
p = podofo.PDFDoc()
p.load(raw)
title = p.title
if not title:
title = '_'
author = p.author
authors = string_to_authors(author) if author else [_('Unknown')]
creator = p.creator
try:
tags = [x.strip() for x in p.keywords.split(u',')]
tags = [x for x in tags if x]
except:
tags = []
mi = MetaInformation(title, authors)
if creator:
mi.book_producer = creator
if tags:
mi.tags = tags
return mi
def get_metadata(stream, extract_cover=True):
'''
Return metadata as a L{MetaInfo} object
'''
mi = MetaInformation(_('Unknown'), [_('Unknown')])
stream.seek(0)
try:
with ZipFile(stream) as zf:
opf_name = get_first_opf_name(zf)
opf_stream = StringIO(zf.read(opf_name))
opf = OPF(opf_stream)
mi = opf.to_book_metadata()
if extract_cover:
cover_href = opf.raster_cover
if cover_href:
mi.cover_data = (os.path.splitext(cover_href)[1],
zf.read(cover_href))
except:
return mi
return mi
def parse_comic_comment(comment, series_index='volume'):
# See http://code.google.com/p/comicbookinfo/wiki/Example
from calibre.ebooks.metadata import MetaInformation
import json
mi = MetaInformation(None, None)
m = json.loads(comment)
if isinstance(m, dict):
for cat in m:
if cat.startswith('ComicBookInfo'):
get_comic_book_info(m[cat], mi, series_index=series_index)
break
return mi
def _metadata_from_formats(formats, force_read_metadata=False, pattern=None):
mi = MetaInformation(None, None)
formats.sort(key=lambda x: METADATA_PRIORITIES[path_to_ext(x)])
extensions = list(map(path_to_ext, formats))
if 'opf' in extensions:
opf = formats[extensions.index('opf')]
mi2 = opf_metadata(opf)
if mi2 is not None and mi2.title:
return mi2
for path, ext in zip(formats, extensions):
with lopen(path, 'rb') as stream:
try:
newmi = get_metadata(stream,
stream_type=ext,
use_libprs_metadata=True,
force_read_metadata=force_read_metadata,
pattern=pattern)
mi.smart_update(newmi)
except:
continue
if getattr(mi, 'application_id', None) is not None:
return mi
if not mi.title:
mi.title = _('Unknown')
if not mi.authors:
mi.authors = [_('Unknown')]
return mi
def get_metadata_from_reader(rdr):
raw = rdr.GetFile(rdr.home)
home = BeautifulSoup(
xml_to_unicode(raw, strip_encoding_pats=True,
resolve_entities=True)[0])
title = rdr.title
try:
x = rdr.GetEncoding()
codecs.lookup(x)
enc = x
except:
enc = 'cp1252'
title = force_unicode(title, enc)
authors = _get_authors(home)
mi = MetaInformation(title, authors)
publisher = _get_publisher(home)
if publisher:
mi.publisher = publisher
isbn = _get_isbn(home)
if isbn:
mi.isbn = isbn
comments = _get_comments(home)
if comments:
mi.comments = comments
cdata = _get_cover(home, rdr)
if cdata is not None:
mi.cover_data = ('jpg', cdata)
return mi
def get_metadata(stream):
""" Return metadata as a L{MetaInfo} object """
title = 'Unknown'
mi = MetaInformation(title, ['Unknown'])
stream.seek(0)
try:
if stream.read(10) not in MAGIC:
print >>sys.stderr, u'Couldn\'t read IMP header from file'
return mi
def cString(skip=0):
result = ''
while 1:
data = stream.read(1)
if data == '\x00':
if not skip: return result
skip -= 1
result, data = '', ''
result += data
stream.read(38) # skip past some uninteresting headers
_, category, title, author = cString(), cString(), cString(1), cString(2)
if title:
mi.title = title
if author:
mi.authors = string_to_authors(author)
mi.author = author
if category:
mi.category = category
except Exception as err:
msg = u'Couldn\'t read metadata from imp: %s with error %s'%(mi.title, unicode(err))
print >>sys.stderr, msg.encode('utf8')
return mi
def get_metadata(stream, cover=True):
with TemporaryDirectory('_pdf_metadata_read') as pdfpath:
stream.seek(0)
with open(os.path.join(pdfpath, 'src.pdf'), 'wb') as f:
shutil.copyfileobj(stream, f)
try:
res = fork_job('calibre.ebooks.metadata.pdf', 'read_info',
(pdfpath, bool(cover)))
except WorkerError as e:
prints(e.orig_tb)
raise RuntimeError('Failed to run pdfinfo')
info = res['result']
with open(res['stdout_stderr'], 'rb') as f:
raw = f.read().strip()
if raw:
prints(raw)
if not info:
raise ValueError('Could not read info dict from PDF')
covpath = os.path.join(pdfpath, 'cover.jpg')
cdata = None
if cover and os.path.exists(covpath):
with open(covpath, 'rb') as f:
cdata = f.read()
title = info.get('Title', None)
au = info.get('Author', None)
if au is None:
au = [_('Unknown')]
else:
au = string_to_authors(au)
mi = MetaInformation(title, au)
# if isbn is not None:
# mi.isbn = isbn
creator = info.get('Creator', None)
if creator:
mi.book_producer = creator
keywords = info.get('Keywords', None)
mi.tags = []
if keywords:
mi.tags = [x.strip() for x in keywords.split(',')]
isbn = [check_isbn(x) for x in mi.tags if check_isbn(x)]
if isbn:
mi.isbn = isbn = isbn[0]
mi.tags = [x for x in mi.tags if check_isbn(x) != isbn]
subject = info.get('Subject', None)
if subject:
mi.tags.insert(0, subject)
if cdata:
mi.cover_data = ('jpeg', cdata)
return mi
def get_metadata(stream, extract_cover=True):
""" Return metadata as a L{MetaInfo} object """
mi = MetaInformation(_('Unknown'), [_('Unknown')])
snbFile = SNBFile()
try:
if not hasattr(stream, 'write'):
snbFile.Parse(StringIO(stream), True)
else:
stream.seek(0)
snbFile.Parse(stream, True)
meta = snbFile.GetFileStream('snbf/book.snbf')
if meta is not None:
meta = etree.fromstring(meta)
mi.title = meta.find('.//head/name').text
mi.authors = [meta.find('.//head/author').text]
mi.language = meta.find('.//head/language').text.lower().replace('_', '-')
mi.publisher = meta.find('.//head/publisher').text
if extract_cover:
cover = meta.find('.//head/cover')
if cover is not None and cover.text is not None:
root, ext = os.path.splitext(cover.text)
if ext == '.jpeg':
ext = '.jpg'
mi.cover_data = (ext[-3:], snbFile.GetFileStream('snbc/images/' + cover.text))
except Exception:
import traceback
traceback.print_exc()
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.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):
''' Return fb2 metadata as a L{MetaInformation} object '''
root = _get_fbroot(get_fb2_data(stream)[0])
ctx = Context(root)
book_title = _parse_book_title(root, ctx)
authors = _parse_authors(root, ctx) or [_('Unknown')]
# fallback for book_title
if book_title:
book_title = unicode_type(book_title)
else:
book_title = force_unicode(
os.path.splitext(
os.path.basename(getattr(stream, 'name', _('Unknown'))))[0])
mi = MetaInformation(book_title, authors)
try:
_parse_cover(root, mi, ctx)
except:
pass
try:
_parse_comments(root, mi, ctx)
except:
pass
try:
_parse_tags(root, mi, ctx)
except:
pass
try:
_parse_series(root, mi, ctx)
except:
pass
try:
_parse_isbn(root, mi, ctx)
except:
pass
try:
_parse_publisher(root, mi, ctx)
except:
pass
try:
_parse_pubdate(root, mi, ctx)
except:
pass
try:
_parse_language(root, mi, ctx)
except:
pass
return mi
def do_add_empty(
dbctx, title, authors, isbn, tags, series, series_index, cover, identifiers,
languages
):
mi = MetaInformation(None)
if title is not None:
mi.title = title
if authors:
mi.authors = authors
if identifiers:
mi.set_identifiers(identifiers)
if isbn:
mi.isbn = isbn
if tags:
mi.tags = tags
if series:
mi.series, mi.series_index = series, series_index
if cover:
mi.cover = cover
if languages:
mi.languages = languages
ids, duplicates = dbctx.run('add', 'empty', read_cover(mi))
prints(_('Added book ids: %s') % ','.join(map(str, ids)))
def get_social_metadata(title, authors, publisher, isbn, username=None,
password=None):
from calibre.ebooks.metadata import MetaInformation
mi = MetaInformation(title, authors)
if isbn:
br = get_browser()
try:
login(br, username, password)
raw = br.open_novisit('http://www.librarything.com/isbn/'
+isbn).read()
except:
return mi
if '/wiki/index.php/HelpThing:Verify' in raw:
raise Exception('LibraryThing is blocking calibre.')
if not raw:
return mi
raw = raw.decode('utf-8', 'replace')
raw = strip_encoding_declarations(raw)
root = html.fromstring(raw)
h1 = root.xpath('//div[@class="headsummary"]/h1')
if h1 and not mi.title:
mi.title = html.tostring(h1[0], method='text', encoding=unicode)
h2 = root.xpath('//div[@class="headsummary"]/h2/a')
if h2 and not mi.authors:
mi.authors = [html.tostring(x, method='text', encoding=unicode) for
x in h2]
h3 = root.xpath('//div[@class="headsummary"]/h3/a')
if h3:
match = None
for h in h3:
series = html.tostring(h, method='text', encoding=unicode)
match = re.search(r'(.+) \((.+)\)', series)
if match is not None:
break
if match is not None:
mi.series = match.group(1).strip()
match = re.search(r'[0-9.]+', match.group(2))
si = 1.0
if match is not None:
si = float(match.group())
mi.series_index = si
#tags = root.xpath('//div[@class="tags"]/span[@class="tag"]/a')
#if tags:
# mi.tags = [html.tostring(x, method='text', encoding=unicode) for x
# in tags]
span = root.xpath(
'//table[@class="wsltable"]/tr[@class="wslcontent"]/td[4]//span')
if span:
raw = html.tostring(span[0], method='text', encoding=unicode)
match = re.search(r'([0-9.]+)', raw)
if match is not None:
rating = float(match.group())
if rating > 0 and rating <= 5:
mi.rating = rating
return mi
def read_user_metadata(self):
'''
Read all metadata specified by the user. Command line options override
metadata from a specified OPF file.
'''
from calibre.ebooks.metadata import MetaInformation
from calibre.ebooks.metadata.opf2 import OPF
mi = MetaInformation(None, [])
if self.opts.read_metadata_from_opf is not None:
self.opts.read_metadata_from_opf = os.path.abspath(
self.opts.read_metadata_from_opf)
opf = OPF(open(self.opts.read_metadata_from_opf, 'rb'),
os.path.dirname(self.opts.read_metadata_from_opf))
mi = opf.to_book_metadata()
self.opts_to_mi(mi)
if mi.cover:
if mi.cover.startswith('http:') or mi.cover.startswith('https:'):
mi.cover = self.download_cover(mi.cover)
ext = mi.cover.rpartition('.')[-1].lower().strip()
if ext not in ('png', 'jpg', 'jpeg', 'gif'):
ext = 'jpg'
mi.cover_data = (ext, open(mi.cover, 'rb').read())
mi.cover = None
self.user_metadata = mi
def get_metadata(stream, cover=True):
with TemporaryDirectory("_pdf_metadata_read") as pdfpath:
stream.seek(0)
with open(os.path.join(pdfpath, "src.pdf"), "wb") as f:
shutil.copyfileobj(stream, f)
try:
res = fork_job("calibre.ebooks.metadata.pdf", "read_info", (pdfpath, bool(cover)))
except WorkerError as e:
prints(e.orig_tb)
raise RuntimeError("Failed to run pdfinfo")
info = res["result"]
with open(res["stdout_stderr"], "rb") as f:
raw = f.read().strip()
if raw:
prints(raw)
if not info:
raise ValueError("Could not read info dict from PDF")
covpath = os.path.join(pdfpath, "cover.jpg")
cdata = None
if cover and os.path.exists(covpath):
with open(covpath, "rb") as f:
cdata = f.read()
title = info.get("Title", None)
au = info.get("Author", None)
if au is None:
au = [_("Unknown")]
else:
au = string_to_authors(au)
mi = MetaInformation(title, au)
# if isbn is not None:
# mi.isbn = isbn
creator = info.get("Creator", None)
if creator:
mi.book_producer = creator
keywords = info.get("Keywords", None)
mi.tags = []
if keywords:
mi.tags = [x.strip() for x in keywords.split(",")]
isbn = [check_isbn(x) for x in mi.tags if check_isbn(x)]
if isbn:
mi.isbn = isbn = isbn[0]
mi.tags = [x for x in mi.tags if check_isbn(x) != isbn]
subject = info.get("Subject", None)
if subject:
mi.tags.insert(0, subject)
if cdata:
mi.cover_data = ("jpeg", cdata)
return mi
