def extract_zip(
path: Path,
img_types: Iterable[str],
outpath: str = os.path.join(tempfile.gettempdir(), 'html-mangareader'),
) -> List[Path]:
"""Extract image files found in an archive file.
Parameters:
* `path`: path to archive.
* `img_types`: list of recognized image file extensions.
* `outpath`: directory to extract images to. Defaults to OS temp directory.
Returns: list of absolute paths to extracted image files.
Throws:
* `ImagesNotFound` if no images were found in the archive.
* `BadZipFile` if CBZ/ZIP archive could not be read.
* `BadRarFile` if CBR/RAR archive could not be read.
* `Bad7zFile` if CB7/7Z archive could not be read.
"""
file_ext = path.suffix.lower()[1:]
try:
if file_ext in ZIP_TYPES:
with zipfile.ZipFile(path, mode='r') as zip_file:
return extract_archive(img_types, zip_file)
elif file_ext in RAR_TYPES:
with rarfile.RarFile(path, mode='r') as rar_file:
return extract_archive(img_types, rar_file)
elif file_ext in _7Z_TYPES:
with SevenZipAdapter(path, mode='r') as _7z_file:
return extract_archive(img_types, _7z_file)
else:
raise ImagesNotFound(f'Unknown archive format: {path}')
except ImagesNotFound:
raise ImagesNotFound(f'No image files were found in archive: {path}')
def extract_archive(
img_types: Iterable[str],
archive: Union[zipfile.ZipFile, rarfile.RarFile],
outpath: str = os.path.join(tempfile.gettempdir(), 'html-mangareader'),
) -> List[Path]:
"""Extract image files in archive to the outpath."""
imagefiles = list(filter(lambda f: f.split('.')[-1].lower() in img_types, archive.namelist()))
if not imagefiles:
raise ImagesNotFound()
archive.extractall(outpath, imagefiles)
return [Path(outpath) / image for image in sorted(imagefiles, key=filename_comparator)]
def scan_directory(path: Union[str, Path], img_types: Iterable[str]) -> List[Path]:
"""Get a list of image file paths from a directory.
Parameters:
* `path`: directory to scan for images.
* `img_types`: list of recognized image file extensions.
Returns: list of absolute paths to image files.
Throws: `ImagesNotFound` if no images were found in the directory.
"""
files = filter(lambda f: f.is_file(), Path(path).iterdir())
imagefiles = list(filter(lambda f: f.suffix.lower()[1:] in img_types, files))
if not imagefiles:
raise ImagesNotFound(f'No image files were found in directory "{Path(path).resolve()}"')
return [
p if p.is_absolute() else p.resolve() for p in sorted(imagefiles, key=filename_comparator)
]
def render_from_template(
paths: Iterable[Union[Path, str]],
version: str,
title: str,
doc_template: str,
page_template: str,
outfile: str = os.path.join(tempfile.gettempdir(), 'html-mangareader', 'render.html'),
) -> str:
"""Render a list of image paths to the finished HTML document.
Parameters:
* `paths`: full file:// paths to images to render on the page.
* `version`: version number to render on page.
* `title`: title of the page.
* `doc_template`: HTML template for the overall document.
* `page_template`: HTML template for each comic page element.
* `outfile`: path to write the rendered document to. Defaults to OS temp directory.
Returns: path to rendered HTML document.
Throws: `ImagesNotFound` if the image list is empty.
"""
if not paths:
raise ImagesNotFound('No images were sent to the renderer.')
imagepaths = [Path(p).as_uri() for p in paths]
os.makedirs(os.path.dirname(outfile), exist_ok=True)
with open(outfile, 'w', encoding='utf-8', newline='\r\n') as renderfd:
html_template = Template(doc_template)
img_template = Template(page_template)
img_list = [
img_template.substitute(
img=imagepaths[i],
id=str(i),
previd=str(i - 1) if i > 0 else 'none',
nextid=str(i + 1) if i < len(imagepaths) - 1 else 'none',
)
for i in range(0, len(imagepaths))
]
doc_string = html_template.substitute(pages=''.join(img_list), version=version, title=title)
renderfd.write(doc_string)
# print("view saved to " + outfile)
return outfile