def _get_metadata(self, book, pdf_stats):
'''
Return a populated Book object with available metadata
'''
from calibre.ebooks.metadata import author_to_author_sort, authors_to_string, title_sort
from calibre.ebooks.metadata.pdf import get_metadata
self._log_location(repr(book))
pdf_path = os.path.join(self.temp_dir, pdf_stats['path'])
with open(pdf_path, 'rb') as f:
stream = cStringIO.StringIO(f.read())
mi = get_metadata(stream, cover=False)
this_book = Book(mi.title, authors=mi.authors)
this_book.author_sort = author_to_author_sort(mi.authors[0])
this_book.datetime = datetime.fromtimestamp(
int(pdf_stats['stats']['st_birthtime'])).timetuple()
this_book.dateadded = int(pdf_stats['stats']['st_birthtime'])
this_book.path = book
this_book.size = int(pdf_stats['stats']['st_size'])
this_book.thumbnail = self._get_goodreader_thumb(book)
if this_book.thumbnail:
this_book.thumb_data = base64.b64encode(this_book.thumbnail)
else:
this_book.thumb_data = None
this_book.title_sort = title_sort(mi.title)
this_book.uuid = None
return this_book
def _create_new_book(self, fpath, metadata, thumb):
'''
'''
from calibre.ebooks.metadata import authors_to_string
self._log_location(metadata.title)
format = fpath.rpartition('.')[2].lower()
this_book = Book(metadata.title, '; '.join(metadata.authors))
this_book.author_sort = metadata.author_sort
this_book.dateadded = time.mktime(time.gmtime())
this_book.datetime = datetime.fromtimestamp(
this_book.dateadded).timetuple()
this_book.path = self.path_template.format(metadata.title,
metadata.authors[0], format)
this_book.size = os.path.getsize(fpath)
this_book.thumbnail = self._cover_to_thumb(metadata)
this_book.thumb_data = base64.b64encode(this_book.thumbnail)
this_book.title_sort = metadata.title_sort
this_book.uuid = metadata.uuid
if False:
self._log("%s by %s" %
(this_book.title, '; '.join(this_book.authors)))
self._log("path: %s" % this_book.path)
self._log("author_sort: %s" % this_book.author_sort)
self._log("title_sort: %s" % this_book.title_sort)
return this_book
def _get_metadata(self, book, pdf_stats):
"""
Return a populated Book object with available metadata
"""
from calibre.ebooks.metadata import author_to_author_sort, authors_to_string, title_sort
from calibre.ebooks.metadata.pdf import get_metadata
self._log_location(repr(book))
pdf_path = os.path.join(self.temp_dir, pdf_stats["path"])
with open(pdf_path, "rb") as f:
stream = cStringIO.StringIO(f.read())
mi = get_metadata(stream, cover=False)
this_book = Book(mi.title, " & ".join(mi.authors))
this_book.author_sort = author_to_author_sort(mi.authors[0])
this_book.datetime = datetime.fromtimestamp(int(pdf_stats["stats"]["st_birthtime"])).timetuple()
this_book.dateadded = int(pdf_stats["stats"]["st_birthtime"])
this_book.path = book
this_book.size = int(pdf_stats["stats"]["st_size"])
this_book.thumbnail = self._get_goodreader_thumb(book)
if this_book.thumbnail:
this_book.thumb_data = base64.b64encode(this_book.thumbnail)
else:
this_book.thumb_data = None
this_book.title_sort = title_sort(mi.title)
this_book.uuid = None
return this_book
def _get_metadata(self, book, book_stats):
'''
Return a populated Book object with available metadata
'''
from calibre.ebooks.metadata import author_to_author_sort, authors_to_string, title_sort
self._log_location(repr(book))
format = book.rsplit('.')[1].lower()
if format == 'mobi':
from calibre.ebooks.metadata.mobi import get_metadata as get_mobi_metadata
path = os.path.join(self.temp_dir, book_stats['path'])
with open(path, 'rb') as f:
stream = cStringIO.StringIO(f.read())
mi = get_mobi_metadata(stream)
elif format == 'pdf':
from calibre.ebooks.metadata.pdf import get_metadata as get_pdf_metadata
path = os.path.join(self.temp_dir, book_stats['path'])
with open(path, 'rb') as f:
stream = cStringIO.StringIO(f.read())
mi = get_pdf_metadata(stream)
else:
self._log("unsupported format: '{}'".format(format))
return Book()
if False:
''' Perform a bit of voodoo to match Kindle multiple author style '''
ks_authors = []
for a in mi.authors:
if "," in a:
# Already ln, fn
ks_authors.append(a)
else:
ks_authors.append(author_to_author_sort(a))
this_book = Book(mi.title, '; '.join(mi.authors))
this_book.author_sort = '; '.join(mi.authors)
this_book.datetime = datetime.fromtimestamp(
int(book_stats['stats']['st_birthtime'])).timetuple()
this_book.dateadded = int(book_stats['stats']['st_birthtime'])
this_book.path = book
this_book.size = int(book_stats['stats']['st_size'])
this_book.thumbnail = self._get_kindle_thumb(mi.cover_data[1])
if this_book.thumbnail:
this_book.thumb_data = base64.b64encode(this_book.thumbnail)
else:
this_book.thumb_data = None
this_book.title_sort = title_sort(mi.title)
this_book.uuid = None
return this_book
def _get_metadata(self, book, book_stats):
'''
Return a populated Book object with available metadata
'''
from calibre.ebooks.metadata import author_to_author_sort, authors_to_string, title_sort
self._log_location(repr(book))
format = book.rsplit('.')[1].lower()
if format == 'mobi':
from calibre.ebooks.metadata.mobi import get_metadata as get_mobi_metadata
path = os.path.join(self.temp_dir, book_stats['path'])
with open(path, 'rb') as f:
stream = cStringIO.StringIO(f.read())
mi = get_mobi_metadata(stream)
elif format == 'pdf':
from calibre.ebooks.metadata.pdf import get_metadata as get_pdf_metadata
path = os.path.join(self.temp_dir, book_stats['path'])
with open(path, 'rb') as f:
stream = cStringIO.StringIO(f.read())
mi = get_pdf_metadata(stream)
else:
self._log("unsupported format: '{}'".format(format))
return Book()
if False:
''' Perform a bit of voodoo to match Kindle multiple author style '''
ks_authors = []
for a in mi.authors:
if "," in a:
# Already ln, fn
ks_authors.append(a)
else:
ks_authors.append(author_to_author_sort(a))
this_book = Book(mi.title, '; '.join(mi.authors))
this_book.author_sort = '; '.join(mi.authors)
this_book.datetime = datetime.fromtimestamp(int(book_stats['stats']['st_birthtime'])).timetuple()
this_book.dateadded = int(book_stats['stats']['st_birthtime'])
this_book.path = book
this_book.size = int(book_stats['stats']['st_size'])
this_book.thumbnail = self._get_kindle_thumb(mi.cover_data[1])
if this_book.thumbnail:
this_book.thumb_data = base64.b64encode(this_book.thumbnail)
else:
this_book.thumb_data = None
this_book.title_sort = title_sort(mi.title)
this_book.uuid = None
return this_book
def _get_cached_metadata(self, cur, book):
'''
Return a populated Book object from a cached book's metadata
'''
self._log_location(book)
cur.execute('''
SELECT
authors,
author_sort,
dateadded,
filename,
size,
thumb_data,
title,
title_sort,
uuid
FROM metadata
WHERE filename={0}
'''.format(self._quote_sqlite_identifier(book)))
cached_book = cur.fetchone()
if cached_book:
#self._log(cached_book.keys())
#self._log(repr(cached_book[b'authors']))
#self._log(authors_to_string(cached_book[b'authors'].split(' & ')))
this_book = Book(cached_book[b'title'],
authors=cached_book[b'authors'].split(' & '))
this_book.author_sort = cached_book[b'author_sort']
this_book.datetime = datetime.fromtimestamp(
cached_book[b'dateadded']).timetuple()
this_book.path = cached_book[b'filename']
this_book.size = cached_book[b'size']
if cached_book[b'thumb_data']:
this_book.thumbnail = base64.b64decode(
cached_book[b'thumb_data'])
else:
this_book.thumbnail = None
this_book.title_sort = cached_book[b'title_sort']
this_book.uuid = cached_book[b'uuid']
return this_book
else:
self._log("***Error: unable to find '%s' in db" % book)
return None
def _get_cached_metadata(self, cur, book):
"""
Return a populated Book object from a cached book's metadata
format(json.dumps(book)))
"""
self._log_location(book)
cur.execute(
"""
SELECT
authors,
author_sort,
dateadded,
filename,
size,
thumb_data,
title,
title_sort,
uuid
FROM metadata
WHERE filename=?
""",
(book,),
)
cached_book = cur.fetchone()
if cached_book:
# self._log(cached_book.keys())
this_book = Book(cached_book[b"title"], cached_book[b"authors"])
this_book.author_sort = cached_book[b"author_sort"]
this_book.datetime = datetime.fromtimestamp(cached_book[b"dateadded"]).timetuple()
this_book.path = cached_book[b"filename"]
this_book.size = cached_book[b"size"]
if cached_book[b"thumb_data"]:
this_book.thumbnail = base64.b64decode(cached_book[b"thumb_data"])
else:
this_book.thumbnail = None
this_book.title_sort = cached_book[b"title_sort"]
this_book.uuid = cached_book[b"uuid"]
return this_book
else:
self._log("***Error: unable to find '%s' in db" % book)
return None
def _get_cached_metadata(self, cur, book):
'''
Return a populated Book object from a cached book's metadata
'''
self._log_location(book)
cur.execute('''
SELECT
authors,
author_sort,
dateadded,
filename,
size,
thumb_data,
title,
title_sort,
uuid
FROM metadata
WHERE filename={0}
'''.format(self._quote_sqlite_identifier(book))
)
cached_book = cur.fetchone()
if cached_book:
#self._log(cached_book.keys())
#self._log(repr(cached_book[b'authors']))
#self._log(authors_to_string(cached_book[b'authors'].split(' & ')))
this_book = Book(cached_book[b'title'], authors=cached_book[b'authors'].split(' & '))
this_book.author_sort = cached_book[b'author_sort']
this_book.datetime = datetime.fromtimestamp(cached_book[b'dateadded']).timetuple()
this_book.path = cached_book[b'filename']
this_book.size = cached_book[b'size']
if cached_book[b'thumb_data']:
this_book.thumbnail = base64.b64decode(cached_book[b'thumb_data'])
else:
this_book.thumbnail = None
this_book.title_sort = cached_book[b'title_sort']
this_book.uuid = cached_book[b'uuid']
return this_book
else:
self._log("***Error: unable to find '%s' in db" % book)
return None
def _create_new_book(self, fpath, metadata, thumb):
"""
"""
from calibre.ebooks.metadata import authors_to_string
self._log_location(metadata.title)
this_book = Book(metadata.title, " & ".join(metadata.authors))
this_book.author_sort = metadata.author_sort
this_book.dateadded = time.mktime(time.gmtime())
this_book.datetime = datetime.fromtimestamp(this_book.dateadded).timetuple()
this_book.path = self.path_template.format(metadata.title)
this_book.size = os.path.getsize(fpath)
this_book.thumbnail = self._cover_to_thumb(metadata)
this_book.thumb_data = base64.b64encode(this_book.thumbnail)
this_book.title_sort = metadata.title_sort
this_book.uuid = metadata.uuid
if False:
self._log("%s by %s" % (this_book.title, " & ".join(this_book.authors)))
self._log("path: %s" % this_book.path)
self._log("author_sort: %s" % this_book.author_sort)
self._log("title_sort: %s" % this_book.title_sort)
return this_book
def books(self, oncard=None, end_session=True):
'''
Return a list of ebooks on the device.
@param oncard: If 'carda' or 'cardb' return a list of ebooks on the
specific storage card, otherwise return list of ebooks
in main memory of device. If a card is specified and no
books are on the card return empty list.
@return: A BookList.
'''
if oncard:
return BookList()
self._log_location()
booklist = BookList()
cached_books = {}
# Fetch current assets from Media folder
assets_profile = self._localize_database_path(self.assets_subpath)
#Fetch current metadata from iBooks's DB
db_profile = self._localize_database_path(self.books_subpath)
con = sqlite3.connect(db_profile['path'])
# Mount the Media folder
self.ios.mount_ios_media_folder()
# Get Books.plist so we can find the covers
books_plist = {}
if True:
raw_plist = XmlPropertyListParser().parse(self.ios.read('/Books/Sync/Books.plist'))['Books']
for book in raw_plist:
if not 'Path' in book:
print(" No 'Path' element found for '%s' by '%s'" % (book['Name'], book['Artist']))
#print(book)
#print
continue
if 'Cover Path' in book:
books_plist['/'.join(['/Books', book['Path']])] = unicode('/'.join(['/Books', book['Path'], book['Cover Path']]))
else:
books_plist['/'.join(['/Books', book['Path']])] = unicode('/'.join(['/Books', 'Sync', 'Artwork', book['Persistent ID']]))
# Process any outliers
raw_plist = XmlPropertyListParser().parse(self.ios.read('/Books/Books.plist'))['Books']
for book in raw_plist:
if not 'Path' in book:
print(" No 'Path' element found for '%s' by '%s'" % (book['Name'], book['Artist']))
#print(book)
#print
continue
# Don't overwrite existing cover_paths
if not '/'.join(['/Books', book['Path']]) in books_plist:
if 'Cover Path' in book and not ['/'.join(['/Books', book['Path']])] in book_plist:
books_plist['/'.join(['/Books', book['Path']])] = unicode('/'.join(['/Books', book['Path'], book['Cover Path']]))
else:
books_plist['/'.join(['/Books', book['Path']])] = unicode('/'.join(['/Books', 'Sync', 'Artwork', book['Persistent ID']]))
raw_plist = XmlPropertyListParser().parse(self.ios.read('/Books/Purchases/Purchases.plist'))['Books']
for book in raw_plist:
if not 'Path' in book:
print(" No 'Path' element found for '%s' by '%s'" % (book['Name'], book['Artist']))
print(book)
print
continue
# Don't overwrite existing cover_paths
if not '/'.join(['/Books', book['Path']]) in books_plist:
if 'Cover Path' in book:
books_plist['/'.join(['/Books/Purchases', book['Path']])] = unicode('/'.join(['/Books/Purchases', book['Path'], book['Cover Path']]))
else:
books_plist['/'.join(['/Books/Purchases', book['Path']])] = unicode('/'.join(['/Books', 'Sync', 'Artwork', book['Persistent ID']]))
else:
raw_plist = XmlPropertyListParser().parse(self.ios.read('/Books/Books.plist'))['Books']
for book in raw_plist:
if not 'Path' in book:
print(" No 'Path' element found for '%s' by '%s'" % (book['Name'], book['Artist']))
print(book)
print
continue
if 'Cover Path' in book:
books_plist['/'.join(['/Books', book['Path']])] = unicode('/'.join(['/Books', book['Path'], book['Cover Path']]))
else:
books_plist['/'.join(['/Books', book['Path']])] = unicode('/'.join(['/Books', 'Sync', 'Artwork', book['Persistent ID']]))
raw_plist = XmlPropertyListParser().parse(self.ios.read('/Books/Purchases/Purchases.plist'))['Books']
for book in raw_plist:
if not 'Path' in book:
print(" No 'Path' element found for '%s' by '%s'" % (book['Name'], book['Artist']))
print(book)
print
continue
if 'Cover Path' in book:
books_plist['/'.join(['/Books/Purchases', book['Path']])] = unicode('/'.join(['/Books/Purchases', book['Path'], book['Cover Path']]))
else:
books_plist['/'.join(['/Books/Purchases', book['Path']])] = unicode('/'.join(['/Books', 'Sync', 'Artwork', book['Persistent ID']]))
print(books_plist)
with con:
con.row_factory = sqlite3.Row
# Build a collection map
collections_map = {}
# Get the books
cur = con.cursor()
#cur.execute("ATTACH DATABASE '{0}' as 'ASSETS'".format(assets_profile['path'])
cur.execute('''SELECT ZASSETURL,
ZBOOKAUTHOR,
ZSORTAUTHOR,
ZBOOKTITLE,
ZSORTTITLE,
ZDATABASEKEY,
ZDATEADDED
FROM ZBKBOOKINFO
WHERE ZASSETURL LIKE 'file://localhost%' AND
ZASSETURL LIKE '%.epub/'
''')
rows = cur.fetchall()
book_count = len(rows)
for i, row in enumerate(rows):
book_id = row[b'ZDATABASEKEY']
# Get the collection assignments
collections = []
# Get the primary metadata
this_book = Book(row[b'ZBOOKTITLE'], row[b'ZBOOKAUTHOR'])
original_path = row[b'ZASSETURL']
path = original_path[original_path.find('Media/') + len('Media'):-1]
this_book.path = path.replace('%20', ' ')
timestamp = int(row[b'ZDATEADDED']) + NSTimeIntervalSince1970
this_book.datetime = datetime.fromtimestamp(timestamp).timetuple()
this_book.device_collections = collections
this_book.uuid = None
this_book.thumbnail = self._generate_thumbnail(this_book, books_plist[this_book.path])
# Retrieve folder size from cache or compute and cache
try:
zfr = ZipFile(self.folder_archive_path)
file_size = zfr.read(this_book.path)
this_book.size = int(file_size)
self._log_diagnostic("returning folder size from cache")
except:
self._log_diagnostic("opening folder cache for appending")
zfw = ZipFile(self.folder_archive_path, mode='a')
stats = self.ios.stat(this_book.path)
this_book.size = self.ios.get_folder_size(this_book.path)
zfw.writestr(this_book.path, str(this_book.size))
zfw.close()
finally:
zfr.close()
booklist.add_book(this_book, False)
if self.report_progress is not None:
self.report_progress(float((i + 1)*100 / book_count)/100,
'%(num)d of %(tot)d' % dict(num=i + 1, tot=book_count))
cached_books[this_book.path] = {
'title': this_book.title,
'author': this_book.author,
'authors': this_book.author.split(' & '),
'uuid': this_book.uuid
}
cur.close()
# Close the connection
self.ios.dismount_ios_media_folder()
if self.report_progress is not None:
self.report_progress(1.0, _('finished'))
self.cached_books = cached_books
return booklist