def read_book(self):
self.book_ref = EPUB(self.filename)
contents_found = self.book_ref.read_epub()
if not contents_found:
print('Cannot process: ' + self.filename)
return
self.book = self.book_ref.book
class ParseMOBI:
def __init__(self, filename, temp_dir, file_md5):
self.book_ref = None
self.book = None
self.filename = filename
self.epub_filepath = None
self.split_large_xml = False
self.temp_dir = temp_dir
self.extract_dir = os.path.join(temp_dir, file_md5)
def read_book(self):
with HidePrinting():
KindleUnpack.unpackBook(self.filename, self.extract_dir)
epub_filename = os.path.splitext(os.path.basename(
self.filename))[0] + '.epub'
self.epub_filepath = os.path.join(self.extract_dir, 'mobi8',
epub_filename)
if not os.path.exists(self.epub_filepath):
zip_dir = os.path.join(self.extract_dir, 'mobi7')
zip_file = os.path.join(self.extract_dir, epub_filename)
self.epub_filepath = shutil.make_archive(zip_file, 'zip', zip_dir)
self.split_large_xml = True
self.book_ref = EPUB(self.epub_filepath)
contents_found = self.book_ref.read_epub()
if not contents_found:
return False
self.book = self.book_ref.book
return True
def get_title(self):
return self.book['title']
def get_author(self):
return self.book['author']
def get_year(self):
return self.book['year']
def get_cover_image(self):
return self.book['cover']
def get_isbn(self):
return self.book['isbn']
def get_tags(self):
return self.book['tags']
def get_contents(self):
extract_path = os.path.join(self.extract_dir)
zipfile.ZipFile(self.epub_filepath).extractall(extract_path)
self.book_ref.parse_chapters(temp_dir=self.temp_dir,
split_large_xml=self.split_large_xml)
file_settings = {'images_only': False}
return self.book['book_list'], file_settings
def read_book(self):
with HidePrinting():
KindleUnpack.unpackBook(self.filename, self.extract_path)
epub_filename = os.path.splitext(
os.path.basename(self.filename))[0] + '.epub'
self.epub_filepath = os.path.join(
self.extract_path, 'mobi8', epub_filename)
if not os.path.exists(self.epub_filepath):
zip_dir = os.path.join(self.extract_path, 'mobi7')
zip_file = os.path.join(
self.extract_path, epub_filename)
self.epub_filepath = shutil.make_archive(zip_file, 'zip', zip_dir)
self.book = EPUB(self.epub_filepath, self.temp_dir)
class ParseEPUB:
def __init__(self, filename, temp_dir, file_md5):
# TODO
# Maybe also include book description
self.book_ref = None
self.book = None
self.filename = filename
self.extract_path = os.path.join(temp_dir, file_md5)
def read_book(self):
self.book_ref = EPUB(self.filename)
contents_found = self.book_ref.read_epub()
if not contents_found:
print('Cannot process: ' + self.filename)
return
self.book = self.book_ref.book
def get_title(self):
return self.book['title']
def get_author(self):
return self.book['author']
def get_year(self):
return self.book['year']
def get_cover_image(self):
return self.book['cover']
def get_isbn(self):
return self.book['isbn']
def get_tags(self):
return self.book['tags']
def get_contents(self):
zipfile.ZipFile(self.filename).extractall(self.extract_path)
self.book_ref.parse_toc()
self.book_ref.parse_chapters(temp_dir=self.extract_path)
file_settings = {'images_only': False}
return self.book['book_list'], file_settings
def read_book(self):
with HidePrinting():
KindleUnpack.unpackBook(self.filename, self.extract_dir)
epub_filename = os.path.splitext(os.path.basename(
self.filename))[0] + '.epub'
self.epub_filepath = os.path.join(self.extract_dir, 'mobi8',
epub_filename)
if not os.path.exists(self.epub_filepath):
zip_dir = os.path.join(self.extract_dir, 'mobi7')
zip_file = os.path.join(self.extract_dir, epub_filename)
self.epub_filepath = shutil.make_archive(zip_file, 'zip', zip_dir)
self.split_large_xml = True
self.book_ref = EPUB(self.epub_filepath)
contents_found = self.book_ref.read_epub()
if not contents_found:
return False
self.book = self.book_ref.book
return True
class ParseEPUB:
def __init__(self, filename, temp_dir, file_md5):
self.book = None
self.filename = filename
self.temp_dir = temp_dir
self.extract_path = os.path.join(temp_dir, file_md5)
def read_book(self):
self.book = EPUB(self.filename, self.temp_dir)
def generate_metadata(self):
self.book.generate_metadata()
return self.book.metadata
def generate_content(self):
zipfile.ZipFile(self.filename).extractall(self.extract_path)
self.book.generate_toc()
self.book.generate_content()
toc = []
content = []
for count, i in enumerate(self.book.content):
toc.append((i[0], i[1], count + 1))
content.append(i[2])
# Return toc, content, images_only
return toc, content, False
class ParseMOBI:
# This module parses Amazon ebooks using KindleUnpack to first create an
# epub and then read the usual way
def __init__(self, filename, temp_dir, file_md5):
self.book = None
self.filename = filename
self.epub_filepath = None
self.temp_dir = temp_dir
self.extract_path = os.path.join(temp_dir, file_md5)
def read_book(self):
with HidePrinting():
KindleUnpack.unpackBook(self.filename, self.extract_path)
epub_filename = os.path.splitext(
os.path.basename(self.filename))[0] + '.epub'
self.epub_filepath = os.path.join(
self.extract_path, 'mobi8', epub_filename)
if not os.path.exists(self.epub_filepath):
zip_dir = os.path.join(self.extract_path, 'mobi7')
zip_file = os.path.join(
self.extract_path, epub_filename)
self.epub_filepath = shutil.make_archive(zip_file, 'zip', zip_dir)
self.book = EPUB(self.epub_filepath, self.temp_dir)
def generate_metadata(self):
self.book.generate_metadata()
return self.book.metadata
def generate_content(self):
zipfile.ZipFile(self.epub_filepath).extractall(self.extract_path)
self.book.generate_toc()
self.book.generate_content()
toc = []
content = []
for count, i in enumerate(self.book.content):
toc.append((1, i[1], count + 1))
content.append(i[2])
# Return toc, content, images_only
return toc, content, False
def read_book(self):
self.book = EPUB(self.filename, self.temp_dir)