Creating exctract_cover_memory for EPUB (224906db) · Commits · Mirror / Simple OPDS

book_tools/format/init.py

+7 −11

Original line number	Diff line number	Diff line
		@@ -8,6 +8,7 @@ from book_tools.format.mimetype import Mimetype
		from book_tools.format.util import list_zip_file_infos
		from book_tools.format.epub import EPub
		from book_tools.format.fb2 import FB2, FB2Zip
		from book_tools.format.other import Dummy
		#from fbreader.format.pdf import PDF
		#from fbreader.format.msword import MSWord
		from book_tools.format.mobi import Mobipocket
		@@ -22,6 +23,8 @@ class __detector:
		@staticmethod
		def file(filename):
		(n, e) = os.path.splitext(filename)
		if e.lower() == '.xml':
		return Mimetype.XML
		if e.lower() == '.fb2':
		return Mimetype.FB2
		elif e.lower()=='.epub' or e.lower()=='.zip':
		@@ -62,7 +65,8 @@ def detect_mime(file):
		pass
		elif mime == Mimetype.OCTET_STREAM:
		mobiflag = file.read(68)
		if mobiflag.decode()[60:] == 'BOOKMOBI':
		mobiflag = mobiflag[60:]
		if mobiflag.decode() == 'BOOKMOBI':
		return Mimetype.MOBI
		except:
		pass
		@@ -82,16 +86,8 @@ def create_bookfile(file, original_filename):
		return FB2Zip(file, original_filename)
		elif mimetype == Mimetype.MOBI:
		return Mobipocket(file, original_filename)
		# elif mimetype == Mimetype.PDF:
		# return PDF(path, original_filename)
		# elif mimetype == Mimetype.MSWORD:
		# return MSWord(path, original_filename)
		# elif mimetype == Mimetype.RTF:
		# return RTF(path, original_filename)
		# elif mimetype == Mimetype.DJVU:
		# return DjVu(path, original_filename)
		# elif mimetype in [Mimetype.TEXT]:
		# return Dummy(path, original_filename, mimetype)
		elif mimetype in [Mimetype.TEXT, Mimetype.PDF, Mimetype.MSWORD, Mimetype.RTF, Mimetype.DJVU]:
		return Dummy(file, original_filename, mimetype)
		else:
		raise Exception('File type \'%s\' is not supported, sorry' % mimetype)

book_tools/format/bookfile.py

+3 −0

Original line number	Diff line number	Diff line
		@@ -34,6 +34,9 @@ class BookFile(object):
		def extract_cover_internal(self, working_dir):
		return (None, False)

		def extract_cover_memory(self):
		return None

		@staticmethod
		def __is_text(text):
		return isinstance(text, str)

book_tools/format/epub.py

+19 −10

Original line number	Diff line number	Diff line
		@@ -145,7 +145,7 @@ class EPub(BookFile):
		return xpath('/opf:package/opf:manifest/opf:item[@href="%s"]' % ref)

		def image_infos(node):
		path = os.path.normpath(prefix + node.get('href'))
		path = os.path.normpath(prefix + node.get('href')).replace('\\','/')
		try:
		fileinfo = self.__zip_file.getinfo(path)
		except:
		@@ -172,43 +172,45 @@ class EPub(BookFile):
		raise Exception('unknown mimetype %s' % mime)

		try:
		return image_infos(xpath('/opf:package/opf:manifest/opf:item[@properties="cover-image"]'))
		except:
		node = xpath('/opf:package/opf:manifest/opf:item[@properties="cover-image"]')
		return image_infos(node)
		except Exception as err:
		pass

		try:
		node = xpath('/opf:package/opf:metadata/opf:meta[@name="cover"]')
		return image_infos(xpath('/opf:package/opf:manifest/opf:item[@id="%s"]' % node.get('content')))
		except:
		except Exception as err:
		pass

		try:
		node = xpath('/opf:package/opf:metadata/meta[@name="cover"]')
		return image_infos(xpath('/opf:package/opf:manifest/opf:item[@id="%s"]' % node.get('content')))
		except:
		except Exception as err:
		pass

		try:
		node = xpath('/package/metadata/meta[@name="cover"]')
		return image_infos(xpath('/package/manifest/item[@id="%s"]' % node.get('content')))
		except:
		except Exception as err:
		pass

		try:
		node = xpath('/opf:package/opf:guide/opf:reference[@type="other.ms-coverimage-standard"][@title="Cover"]')
		return image_infos(item_for_href(node.get('href')))
		except:
		except Exception as err:
		pass

		try:
		node = xpath('/opf:package/opf:guide/opf:reference[@type="other.ms-coverimage-standard"]')
		return image_infos(item_for_href(node.get('href')))
		except:
		except Exception as err:
		pass

		try:
		return image_infos(xpath('/opf:package/opf:manifest/opf:item[@id="cover"]'))
		except:
		node = xpath('/opf:package/opf:manifest/opf:item[@id="cover"]')
		return image_infos(node)
		except Exception as err:
		pass

		return []
		@@ -402,3 +404,10 @@ class EPub(BookFile):
		shutil.move(os.path.join(working_dir, name), os.path.join(working_dir, split[-1]))
		shutil.rmtree(os.path.join(working_dir, split[0]))
		return (split[-1] if len(split) > 0 else None, False)

		def extract_cover_memory(self):
		if len(self.cover_fileinfos) == 0:
		return None
		name = self.cover_fileinfos[-1]['filename']
		content = self.__zip_file.open(name).read()
		return content

book_tools/format/fb2.py

+13 −0

Original line number	Diff line number	Diff line
		@@ -52,6 +52,18 @@ class FB2Base(BookFile):
		except:
		return (None, False)

		def extract_cover_memory(self):
		try:
		tree = self.__create_tree__()
		res = tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:coverpage/fb:image', namespaces=self.__namespaces)
		cover_id = res[0].get('{' + Namespace.XLINK + '}href')[1:]
		res = tree.xpath('//fb:binary[@id="%s"]' % cover_id, namespaces=self.__namespaces)
		content = base64.b64decode(res[0].text)
		return content
		except Exception as err:
		print(err)
		return None

		def __detect_title(self, tree):
		res = tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:book-title', namespaces=self.__namespaces)
		if len(res) == 0:
		@@ -131,6 +143,7 @@ class FB2(FB2Base):

		def __create_tree__(self):
		try:
		self.file.seek(0, 0)
		return etree.parse(self.file)
		except:
		raise FB2StructureException('the file is not a valid XML')

book_tools/format/other.py

0 → 100644

+8 −0

Original line number	Diff line number	Diff line
		from book_tools.format.bookfile import BookFile

		class Dummy(BookFile):
		def __init__(self, file, original_filename, mimetype):
		BookFile.__init__(self, file, original_filename, mimetype)

		def __exit__(self, kind, value, traceback):
		pass
		No newline at end of file