NunoSempere/calibre-web
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Minor code refactorisation of epub.py

Browse Source 
- Reduce the amount of nested indentation
- Use proper functions instead of fragile manual parsing
This commit is contained in:
jvoisin 2022-12-25 16:37:58 +01:00
parent d0411fd9c7
commit 631496775e
1 changed files with 41 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

87
cps/epub.py
View File

@ -28,18 +28,18 @@ from .constants import BookMeta
def _extract_cover(zip_file, cover_file, cover_path, tmp_file_name): def _extract_cover(zip_file, cover_file, cover_path, tmp_file_name):
if cover_file is None: if cover_file is None:
return None return None
else:
cf = extension = None
zip_cover_path = os.path.join(cover_path, cover_file).replace('\\', '/')
prefix = os.path.splitext(tmp_file_name)[0] cf = extension = None
tmp_cover_name = prefix + '.' + os.path.basename(zip_cover_path) zip_cover_path = os.path.join(cover_path, cover_file).replace('\\', '/')
ext = os.path.splitext(tmp_cover_name)
if len(ext) > 1: prefix = os.path.splitext(tmp_file_name)[0]
extension = ext[1].lower() tmp_cover_name = prefix + '.' + os.path.basename(zip_cover_path)
if extension in cover.COVER_EXTENSIONS: ext = os.path.splitext(tmp_cover_name)
cf = zip_file.read(zip_cover_path) if len(ext) > 1:
return cover.cover_processing(tmp_file_name, cf, extension) extension = ext[1].lower()
if extension in cover.COVER_EXTENSIONS:
cf = zip_file.read(zip_cover_path)
return cover.cover_processing(tmp_file_name, cf, extension)
def get_epub_info(tmp_file_path, original_file_name, original_file_extension): def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
@ -87,11 +87,7 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
epub_metadata['date'] = '' epub_metadata['date'] = ''
if epub_metadata['description'] == u'Unknown': if epub_metadata['description'] == u'Unknown':
description = tree.xpath("//*[local-name() = 'description']/text()") epub_metadata['description'] = tree.xpath("//*[local-name() = 'description']/text()")
if len(description) > 0:
epub_metadata['description'] = description
else:
epub_metadata['description'] = ""
lang = epub_metadata['language'].split('-', 1)[0].lower() lang = epub_metadata['language'].split('-', 1)[0].lower()
epub_metadata['language'] = isoLanguages.get_lang3(lang) epub_metadata['language'] = isoLanguages.get_lang3(lang)
@ -131,41 +127,40 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
def parse_epub_cover(ns, tree, epub_zip, cover_path, tmp_file_path): def parse_epub_cover(ns, tree, epub_zip, cover_path, tmp_file_path):
cover_section = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns) cover_section = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns)
cover_file = None
# if len(cover_section) > 0:
for cs in cover_section: for cs in cover_section:
cover_file = _extract_cover(epub_zip, cs, cover_path, tmp_file_path) cover_file = _extract_cover(epub_zip, cs, cover_path, tmp_file_path)
if cover_file: if cover_file:
break return cover_file
if not cover_file:
meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns) meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns)
if len(meta_cover) > 0: if len(meta_cover) > 0:
cover_section = tree.xpath(
"/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns)
if not cover_section:
cover_section = tree.xpath( cover_section = tree.xpath(
"/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns) "/pkg:package/pkg:manifest/pkg:item[@properties='" + meta_cover[0] + "']/@href", namespaces=ns)
if not cover_section: else:
cover_section = tree.xpath( cover_section = tree.xpath("/pkg:package/pkg:guide/pkg:reference/@href", namespaces=ns)
"/pkg:package/pkg:manifest/pkg:item[@properties='" + meta_cover[0] + "']/@href", namespaces=ns)
cover_file = None
for cs in cover_section:
if cs.endswith('.xhtml') or s.endswith('.html'):
markup = epub_zip.read(os.path.join(cover_path, cs))
markup_tree = etree.fromstring(markup)
# no matter xhtml or html with no namespace
img_src = markup_tree.xpath("//*[local-name() = 'img']/@src")
# Alternative image source
if not len(img_src):
img_src = markup_tree.xpath("//attribute::*[contains(local-name(), 'href')]")
if len(img_src):
# img_src maybe start with "../"" so fullpath join then relpath to cwd
filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(cover_path, cover_section[0])),
img_src[0]))
cover_file = _extract_cover(epub_zip, filename, "", tmp_file_path)
else: else:
cover_section = tree.xpath("/pkg:package/pkg:guide/pkg:reference/@href", namespaces=ns) cover_file = _extract_cover(epub_zip, cs, cover_path, tmp_file_path)
for cs in cover_section: if cover_file:
filetype = cs.rsplit('.', 1)[-1] return cover_file
if filetype == "xhtml" or filetype == "html": # if cover is (x)html format
markup = epub_zip.read(os.path.join(cover_path, cs))
markup_tree = etree.fromstring(markup)
# no matter xhtml or html with no namespace
img_src = markup_tree.xpath("//*[local-name() = 'img']/@src")
# Alternative image source
if not len(img_src):
img_src = markup_tree.xpath("//attribute::*[contains(local-name(), 'href')]")
if len(img_src):
# img_src maybe start with "../"" so fullpath join then relpath to cwd
filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(cover_path, cover_section[0])),
img_src[0]))
cover_file = _extract_cover(epub_zip, filename, "", tmp_file_path)
else:
cover_file = _extract_cover(epub_zip, cs, cover_path, tmp_file_path)
if cover_file: break
return cover_file
def parse_epub_series(ns, tree, epub_metadata): def parse_epub_series(ns, tree, epub_metadata):