Fixes another bug with retrieving all Dinosaur Comics

Not all comics come in serialized issues.

.gitignore

@@ -2,4 +2,6 @@
 *.log
 **/__pycache__
 *~
+src/*.egg-info
+dist/
 index.json

README.md

@@ -6,3 +6,8 @@ The following comics are nativly supported:
 * XKCD
 * Existential Comics
 * Bluesky
+
+# Installing
+This project requires the following dependencies:
+
+* `libraqm`

__main__.py

@@ -1,20 +0,0 @@
-#   This CLI tool allows for the download and packaging of various internet comics into .cbz files.
-#   Copyright (C) 2025  Markil 3
-#   http://www.singlepilot.net
-#
-#   This program is free software: you can redistribute it and/or modify
-#   it under the terms of the GNU General Public License as published by
-#   the Free Software Foundation, either version 3 of the License, or
-#   (at your option) any later version.
-#
-#   This program is distributed in the hope that it will be useful,
-#   but WITHOUT ANY WARRANTY; without even the implied warranty of
-#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-#   GNU General Public License for more details.
-#
-#   You should have received a copy of the GNU General Public License
-#   along with this program.  If not, see <https://www.gnu.org/licenses/>.
-from comic_download.__main__ import __main__
-
-if __name__ == "__main__":
-    __main__()

pyproject.toml

@@ -1,5 +1,26 @@
 [build-system]
 requires = [
-    "setuptools"
+    "setuptools >= 80.9.0"
 ]
 build-backend = "setuptools.build_meta"
+
+[project]
+name = "comic_download"
+version = "0.2.2"
+authors = [
+    {name = "Markil 3", email = "markil3@singlepilot.net"}
+]
+description = "An application to download comics from various sources to the local hard drive."
+readme = "README.md"
+keywords = ["comic", "download", "cbz", "ebook"]
+dependencies = [
+    "requests",
+    "beautifulsoup4",
+    "lxml",
+    "pillow",
+    "atproto",
+    "pycryptodome",
+]
+
+[project.scripts]
+comic_download = "comic_download.__main__:__main__"

requirements.txt

@@ -1,5 +0,0 @@
-requests
-beautifulsoup4
-lxml
-pillow
-atproto

setup.cfg

@@ -0,0 +1,28 @@
+[metadata]
+name = comic_download
+version = 0.2.2
+
+[options]
+package_dir=
+    =src
+zip_safe = False
+packages = find:
+include_package_data = True
+install_requires =
+    requests
+    beautifulsoup4
+    lxml
+    pillow
+    atproto
+    pycryptodome
+
+[options.packages.find]
+where=src
+
+[options.package_data]
+comic_download = *.ttf
+* = README.md, LICENSE
+
+[options.entry_points]
+console_scripts =
+    executable-name = comic_download.__main__:__main__

setup.py

@@ -1,29 +0,0 @@
-import os
-from setuptools import find_packages, setup
-
-def read(fname):
-    return open(os.path.join(os.path.dirname(__file__), fname)).read()
-
-setup(
-    name='comic_download',
-    packages=find_packages(include=['comic_download']),
-    version='0.0.1',
-    description='An application to download comics from various sources to the local hard drive.',
-    long_description=read('README.md'),
-    long_description_content_type='text/markdown',
-    author='Copyrate',
-    license='gpl-3.0',
-    url='https://git.singlepilot.net/copyrate/ComicDownload',
-    install_requires=[
-        'requests',
-        'beautifulsoup4',
-        'lxml',
-        'pillow',
-        'atproto'
-    ],
-    entry_points={
-        'console_scripts': [
-            'comic-download = comic_download.__main__:__main__'
-        ]
-    }
-)

src/comic_download/__init__.py

@@ -14,4 +14,4 @@
 #
 #   You should have received a copy of the GNU General Public License
 #   along with this program.  If not, see <https://www.gnu.org/licenses/>.
-from comic_download.comic_strip import SequenceException, ImageRepo, Comic, ComicStrip, file_safe_string, get_identifier_string, register_comic_class, find_comic_class, read_index, save_index, index_strip, is_strip_present
+from comic_download.comic_strip import SequenceException, AssetRepo, ComicCollection, ComicBook, ComicStrip, file_safe_string, get_identifier_string, register_comic_class, find_comic_class, read_index, save_index, index_strip, is_strip_present

src/comic_download/__main__.py

@@ -27,7 +27,7 @@ from pathlib import Path
 import importlib
 import pkgutil
 import comic_download
-from comic_download import Comic, find_comic_class
+from comic_download import ComicCollection, ComicBook, ComicStrip, find_comic_class
 
 def setup_args():
     parser = argparse.ArgumentParser(
@@ -71,19 +71,25 @@ def load_plugins():
             logging.info("Loading plugin %s" % name)
             importlib.import_module(name)
 
-def load_strip(base_path, comic, identifier, plain, thread_limit):
+def load_book(base_path: Path, comic_type: ComicBook, plain: bool, thread_limit: threading.Semaphore, *args):
     """
-    Threading function for downloading XKCD strips.
-    
-    Arguments:
+    Threading function to add a book to the loading queue.
 
+    :param base_path: The directory to download all downloads to.
+    :param comic: The comic book class to load, or the comic book itself.
+    :param plain: If true, then we skip image transformations.
+    :param thread_limit: The semaphore that controls how many threads we execute at once.
+    :param args: Any arguments here will be passed to the contructor of the comic_type class.
     """
     with thread_limit:
-        strip = comic.create_strip(identifier)
-        strip.await_load()
-        if not strip.get_package_path(base_path).exists():
-            strip.await_download()
-            strip.package_data(base_path)
+        if type(comic_type) == type:
+            book = comic_type(*args)
+        else:
+            book = comic_type
+        book.await_load()
+        if not book.get_package_path(base_path).exists():
+            book.await_download()
+            book.package_data(base_path, plain)
 
 def __main__():
     setup_logging()
@@ -105,30 +111,39 @@ def __main__():
 
     for url in args.url:
         comic_type = find_comic_class(url.netloc + url.path)
-        comic = comic_type.create_from_url(url)
-        comics.append(comic)
-        comic_download.read_index(base_path)
-        comic.await_load()
-        if args.latest:
-            r = [comic.get_latest_strip()]
+        if issubclass(comic_type, ComicStrip):
+            collection = comic_type.collection_cls.create_from_url(url)
+            comic_download.read_index(base_path)
+            collection.await_load()
+
+            # Figure out which strips to grab
+            if args.latest:
+                r = [collection.get_latest_strip()]
+            else:
+                r = collection.get_all_strips()
+                if r and type(r[0]) == int:
+                    start = args.start or collection.get_first_strip()
+                    end = args.end or collection.get_latest_strip()
+                    r = r[r.index(start):r.index(end) + 1]
+
+            # Add the chosen strips to the list of books to add
+            try:
+                for index in reversed(r):
+                    comics.append(comic_type(collection, index))
+            finally:
+                logging.info("Saving index")
+                comic_download.save_index(base_path)
         else:
-            r = comic.get_all_strips()
-            if r and type(r[0]) == int:
-                start = args.start or comic.get_first_strip()
-                end = args.end or comic.get_latest_strip()
-                r = r[r.index(start):r.index(end) + 1]
-
-        try:
-            for index in reversed(r):
-                if not comic_download.is_strip_present(comic, base_path, ".cbz", str(index)):
-                    t = threading.Thread(name=str(comic.get_identifier_string()) + "-" + str(index), target=load_strip, args=(base_path, comic, index, args.plain, thread_limit))
-                    threads.append(t)
-                    t.daemon = True
-                    t.start()
-        finally:
-            logging.info("Saving index")
-            comic_download.save_index(base_path)
+            comics.append(comic_type.create_from_url(url))
 
+        comic_download.read_index(base_path)
+        for comic in comics:
+            # Only make threads for books not accounted for in the index
+            if not comic_download.is_strip_present(comic, base_path, ".cbz"):
+                t = threading.Thread(name=str(comic), target=load_book, args=(base_path, comic, args.plain, thread_limit))
+                threads.append(t)
+                t.daemon = True
+                t.start()
     try:
         while any([t.is_alive() for t in threads]):
             time.sleep(1)

src/comic_download/bluesky.py

@@ -33,7 +33,7 @@ from PIL import Image, ImageDraw, ImageFont
 from bs4 import BeautifulSoup
 from atproto import Client
 
-from comic_download.comic_strip import Comic, ComicStrip, register_comic_class
+from comic_download.comic_strip import ComicCollection as Comic, ComicStrip, register_comic_class
 
 class BlueskyComic(Comic):
     """
@@ -185,11 +185,11 @@ class BlueskyComicStrip(ComicStrip):
                         self.captions.append(image.alt)
                     else:
                         self.captions.append("")
-        self.date = datetime.datetime.fromisoformat(post_data.value.created_at)
+        self.date = datetime.datetime.fromisoformat(post_data.value.created_at[0:-1])
 
     def _transform_images(self):
         self.transformed_images = self.images
     
 
-BlueskyComic.strip_cls = BlueskyComicStrip
-register_comic_class("bsky.app", BlueskyComic)
+BlueskyComicStrip.collection_cls = BlueskyComic
+register_comic_class("bsky.app", BlueskyComicStrip)

src/comic_download/comic_strip.py

@@ -21,6 +21,7 @@ import argparse
 from abc import ABC, abstractmethod
 from datetime import datetime, date
 from threading import Lock, Condition
+import io
 import bisect
 import time
 import re
@@ -113,7 +114,7 @@ A lock for enforcing thread safety when loading the comic index file.
 
 def read_index(base_path: Path):
     """
-    Saves the strip index to the same base path we download comic strips to.
+    Saves the strip index to the same base path we download comic books to.
     It is saved to "index.json."
 
     :param base_path: The folder to save the index to.
@@ -136,7 +137,7 @@ def read_index(base_path: Path):
 
 def save_index(base_path: Path):
     """
-    Saves the strip index to the same base path we download comic strips to.
+    Saves the strip index to the same base path we download comic books to.
     It is saved to "index.json."
 
     :param base_path: The folder to save the index to.
@@ -149,43 +150,37 @@ def save_index(base_path: Path):
             json.dump(strip_index, index_fp)
 
 def index_strip(strip):
-
     """
-    Registers a comic to the index. This does not save the comic index.
+    Registers a book to the index. This does not save the index.
 
-    :param strip: The comic strip to index
+    :param strip: The comic book to index
     """
     global strip_index
     global _index_loaded
     global _index_lock
     with _index_lock:
-        if not strip.comic.get_identifier_string() in strip_index:
-            strip_index[strip.comic.get_identifier_string()] = {}
-        strip_index[strip.comic.get_identifier_string()][strip.get_identifier_string()] = strip.get_filename()
+        strip_index[str(strip)] = strip.get_filename()
 
-def is_strip_present(comic, base_path: Path, suffix: str, identifier) -> bool:
+def is_strip_present(comic, base_path: Path, suffix: str) -> bool:
     """
-    Checks to see if a given strip has been saved to the file.
+    Checks to see if a given book has been saved to the file.
 
-    :param comic: The comic object that the strip belongs to.
+    :param comic: The comic book object to check.
     :param base_path: The folder we expect the strip to show up in.
     :param suffix: The type suffix we want to check (i.e. ".cbz")
-    :param identifier: The identifier to check.
     :returns: True if the strip file has been saved.
     """
     global strip_index
     global _index_loaded
     global _index_lock
-    if not comic.get_identifier_string() in strip_index:
+    if not str(comic) in strip_index:
         return False
-    if not get_identifier_string(identifier) in strip_index[comic.get_identifier_string()]:
-        return False
-    path = Path(base_path, strip_index[comic.get_identifier_string()][get_identifier_string(identifier)] + suffix)
+    path = Path(base_path, strip_index[str(comic)] + suffix)
     return path.exists()
             
 
 
-class ImageRepo(ABC):
+class AssetRepo(ABC):
     """
     A generic representation of an online repository of data. This class allows for the
     setup of downloading the main information in one pass, and secondary information (images)
@@ -224,7 +219,7 @@ class ImageRepo(ABC):
 
     def get_identifier_string(self):
         """
-        Obtains a file-safe string representation of the identifer. If the identifier is a list or tuple, the
+        Obtains a file-safe string representation of the identifier. If the identifier is a list or tuple, the
         elements will be joined by a dash character.
 
         :returns: The identifier in string form.
@@ -265,7 +260,7 @@ class ImageRepo(ABC):
         with self._load_lock:
             if not self._data_loaded:
                 self._load_data()
-                logging.info("Completed loading of %s", self.get_identifier_string())
+                logging.info("Completed loading of %s", repr(self))
             self._data_loaded = True
             self._load_lock.notify_all()
 
@@ -314,9 +309,9 @@ class ImageRepo(ABC):
         with self._download_lock:
             # Checks to see if we need to download and that one is not already in progress
             if self.image_urls and not self.images:
-                logging.info("Downloading %s", self.get_identifier_string())
+                logging.info("Downloading %s", repr(self))
                 self._download_data()
-                logging.info("Completed downloading of %s", self.get_identifier_string())
+                logging.info("Completed downloading of %s", repr(self))
             self._data_downloaded = True
             self._download_lock.notify_all()
 
@@ -330,6 +325,17 @@ class ImageRepo(ABC):
 
         self.download_data()
 
+    def transform_download_url(self, result):
+        """
+        If we need to run extra operations on a request (i.e. a redirect), we
+        can override this method to handle that before we attempt to extract
+        image data. If not overridden, this simply returns the original result.
+
+        :param result: The original request result.
+        :returns: The new request result to use.
+        """
+        return result
+
     def _download_data(self):
         """
         Downloads all images and saves them to temporary files in the #images field.
@@ -345,10 +351,12 @@ class ImageRepo(ABC):
             elif type(self.image_urls) == list:
                 iterator = range(len(self.image_urls))
             for name in iterator:
-                logging.info("    Downloading repository %s resource %s", self.get_identifier_string(), name)
-                image_path = NamedTemporaryFile(mode='wb', suffix=str(name), prefix=self.get_identifier_string(), delete = False)
+                logging.info("    Downloading repository %s resource %s", repr(self), name)
+                image_path = NamedTemporaryFile(mode='wb', suffix=str(name).replace('/', '-'), prefix=str(self), delete = False)
                 result = requests.get(self.image_urls[name], headers=self.download_headers)
                 result.raise_for_status()
+                # Handles necessary transformations for a URL (i.e., redirections)
+                result = self.transform_download_url(result)
                 image_path.write(result.content)
                 image_path.close()
                 if type(self.images) == list:
@@ -356,8 +364,14 @@ class ImageRepo(ABC):
                 else:
                     self.images[name] = image_path
 
+    def __str__(self):
+        return str(self.__class__.__name__) + "__" + self.get_identifier_string()
 
-class Comic(ImageRepo, ABC):
+    def __repr__(self):
+        return "<" + str(self.__class__.__name__) + " " + self.get_identifier_string() + ">"
+        
+
+class ComicCollection(AssetRepo, ABC):
     """
     A generic representation of a comic collection. Comic-wide resources are stored here.
     """
@@ -381,7 +395,7 @@ class Comic(ImageRepo, ABC):
     @classmethod
     def create_from_url(cls, url):
         """
-        Creates a Comic instance from a given URL
+        Creates a ComicCollection instance from a given URL
         """
         pass
 
@@ -419,39 +433,34 @@ class Comic(ImageRepo, ABC):
         """
         pass
 
-    def create_strip(self, identifier):
-        """
-        Creates a new ComicStrip object.
+    def __str__(self):
+        return self.__class__.__name__ + "__" + self.get_identifier_string()
 
-        The class variable #strip_cls must be set for this to work.
-        """
-        return self.strip_cls(self, identifier)
+    def __repr__(self):
+        if self.title:
+            return "<" + str(self.__class__.__name__) + " " + self.title + " (" + self.get_identifier_string() + ")>"
+        else:
+            return "<" + str(self.__class__.__name__) + " " + self.get_identifier_string() + ">"
 
-
-class ComicStrip(ImageRepo, ABC):
+class Book(AssetRepo, ABC):
     """
-    A generic representation of a single comic strip or issue.
+    An abstract class for downloading ebook resources.
     """
 
-    def __init__(self, comic, identifier):
+    def __init__(self, identifier, asset_type = list):
         """
-        Creates a comic strip
+        Creates a book.
 
-        :param comic: The `Comic` object that this strip is part of.
-        :param indentifier: The globally unique identifier used to find the strip on the website. Can be a tuple.
+        :param indentifier: The globally unique identifier used to find the book on the website. Coan be a tuple.
         """
-        super().__init__(identifier, list)
+        super().__init__(identifier, asset_type)
 
-        self.comic = comic
-        """The comic that this strip is part of."""
         self.title = None
-        """The title of the comic. Empty until the comic data is loaded."""
-        self.image_urls = []
-        """A list of URLs we can download the comic panels from, in order. Empty until the comic data is loaded."""
-        self._image_paths = []
+        """The title of the book. Empty until the book is loaded."""
+        self.series = None
+        """The series that this book is a part of, if applicable. Empty until the book is loaded."""
+        self._image_paths = asset_type()
         """A list of temporary files for the raw downloaded panels. Used internally."""
-        self.captions = []
-        """A list of captions for each panel."""
         self.date = None
         """The date that the comic was published."""
         self._transform_lock = Condition(Lock())
@@ -461,6 +470,411 @@ class ComicStrip(ImageRepo, ABC):
         self._transformed = False
         """A flag keeping track of whether the strip transformation took place."""
 
+    @classmethod
+    def create_from_url(cls, url):
+        """
+        Creates a book instance from a given URL
+        """
+        pass
+
+    def get_filename(self):
+        """
+        Obtains the name of the final export (not including the stem). Calling this method requires the data be loaded first.
+
+        :returns: A human-friendly filename, like "05 - Riddles in the Dark" or "2025-06-01 - Chapter 5."
+        """
+        if self.title:
+            return file_safe_string(self.title)[0:250]
+        else:
+            prefix_num_form = "#{:02}"
+            if type(self.identifier) == int:
+                prefix = prefix_num_form.format(self.identifier)
+            elif (type(self.identifier) == list or type(self.identifier) == tuple) and type(self.identifier[-1]) == int:
+                prefix = prefix_num_form.format(self.identifier[-1])
+            elif type(self.date) == date:
+                prefix = self.date.strftime("#%Y%m%d")
+            elif type(self.date) == datetime:
+                prefix = self.date.date().strftime("#%Y%m%d")
+            else:
+                prefix = self.get_identifier_string()
+            return file_safe_string(self.__name__ + " - " + prefix)
+
+    @abstractmethod
+    def get_package_path(self, base_path: Path):
+        """
+        Obtains the path to save the book to.
+
+        :param base_path: The folder to save books to.
+        :returns: The path to save to.
+        """
+        pass
+
+    def load_data(self):
+        super().load_data()
+        index_strip(self)
+
+    @abstractmethod
+    def _load_data(self):
+        """
+        Queries the source to obtain information on the comic.
+
+        Implementing methods need to find the following information:
+        The title of the comic, loaded to `title`.
+        The publish date (or datetime) of the comic, loaded to `date`.
+        A list of panel images, loaded into `image_urls`.
+        A list of captions, loaded into `captions`. Any captions beyond the list of images can be added to new pages without comics.
+        """
+        pass
+
+    @abstractmethod
+    def _transform_images(self):
+        """
+        Called by the packaging method to create a series of locally-transformed
+        images and returning the ordered list of them.
+
+        This method is meant to do things like add alt text, descriptions, title pages, etc.
+        to the final comic. Simpler implementations can simply return a list of the
+        unmodified images with the comic headers from #comic at the beginning.
+
+        All implementations should assign the ordered list to #transformed_images. If this
+        field is not set, then packaging will default to just package the comic strip
+        images.
+        """
+        self.transformed_images = self.images
+
+    @abstractmethod
+    def package_data(self, base_path: Path, plain: bool = False):
+        """
+        Compresses all of the raw downloaded data into a single archive, saving it to a location in the base path.
+
+        :param base_path: The path to save the archive to.
+        :param plain: If true, we will save the images as downloaded, without any transformations.
+        """
+        pass
+
+    def __repr__(self):
+        if self.title:
+            return "<" + str(self.__class__.__name__) + " " + self.title + " (" + self.get_identifier_string() + ")>"
+        else:
+            return "<" + str(self.__class__.__name__) + " " + self.get_identifier_string() + ">"
+
+class EPUBBook(Book, ABC):
+    """
+    A generic representation of a single EPUB book.
+    """
+
+    def __init__(self, identifier):
+        """
+        Creates an ebook.
+
+        :param indentifier: The globally unique identifier used to find the strip on the website. Can be a tuple.
+        """
+        super().__init__(identifier, dict)
+
+    @classmethod
+    def create_from_url(cls, url):
+        """
+        Creates a Comic instance from a given URL
+        """
+        pass
+
+    def get_package_path(self, base_path: Path):
+        """
+        Obtains the path to save the comic archive to.
+
+        :param base_path: The folder to save comics to.
+        :returns: The path to save to.
+        """
+        filename = self.get_filename()
+        return Path(base_path, filename, f"{filename}.epub")
+
+    def package_data(self, base_path: Path, plain: bool = False):
+        if not self.is_loaded():
+            raise SequenceException("Cannot package book before data has been fully loaded.")
+        if not self.is_downloaded():
+            raise SequenceException("Cannot package book before data has been fully downloaded.")
+        if not self.transformed_images:
+            if plain:
+                self.transformed_images = self.images
+            else:
+                if not self._transformed:
+                    if self._transform_lock._lock.locked():
+                        # Await for the existing transform to complete
+                        self._transform_lock.wait()
+                    else:
+                        # Run the transformation outselves
+                        with self._transform_lock:
+                            self._transform_images()
+                            self._transformed = True
+                            self._transform_lock.notify_all()
+        save_path = self.get_package_path(base_path)
+        save_path.parent.mkdir(parents=True, exist_ok=True)
+        if len(self.transformed_images.keys()) == 1:
+            file = list(self.transformed_images.values)[0]
+            if hasattr(file, "name"):
+                with open(file.name, 'rb') as download_stream:
+                    download_cont = download_stream.read()
+            elif isinstance(file, io.IOBase):
+                download_cont = file.read()
+                download_cont.close()
+            elif isinstance(file, Path) or type(file) == str and len(file) < 250 and Path(file).exists():
+                with open(Path(file), 'rb') as download_stream:
+                    download_cont = download_stream.read()
+            else:
+                download_cont = file
+            if type(download_cont) == str:
+                download_cont = bytes(download_cont, 'utf-8')
+            with open(save_path, 'wb') as save_stream, open(file.name, 'rb') as download_stream:
+                logging.info("Packaging single download of %s" % retr(self))
+                save_stream.write(download_cont)
+        else:
+            with ZipFile(self.get_package_path(base_path), 'w') as book_zip:
+                with book_zip.open("mimetype", 'w') as zip_stream:
+                    zip_stream.write(bytes('application/epub+zip', 'ascii'))
+                for path, file in self.transformed_images.items():
+                    if hasattr(file, "name"):
+                        logging.info("Packaging temporary file %s", path)
+                        with open(file.name, 'rb') as download_stream:
+                            download_cont = download_stream.read()
+                    elif isinstance(file, io.IOBase):
+                        logging.info("Packaging stream %s", path)
+                        download_cont = file.read()
+                        download_cont.close()
+                    elif isinstance(file, Path) or type(file) == str and len(file) < 250 and Path(file).exists():
+                        logging.info("Packaging path %s", path)
+                        with open(Path(file), 'rb') as download_stream:
+                            download_cont = download_stream.read()
+                    else:
+                        logging.info("Packaging string %s", path)
+                        download_cont = file
+                    if type(download_cont) == str:
+                        download_cont = bytes(download_cont, 'utf-8')
+                    with book_zip.open(path, 'w') as zip_stream:
+                        zip_stream.write(download_cont)
+        # Delete the base images, as they are no longer needed.
+        # We cannot touch the transformed images, since some
+        # of them may come directly from the base comic, and
+        # we have no way of telling.
+        for file in self.images.values():
+            file_path = Path(file.name)
+            if file_path.exists():
+                file_path.unlink()
+                    
+        
+
+
+class ComicBook(Book, ABC):
+    """
+    A generic representation of a single comic strip or issue.
+    """
+
+    def __init__(self, identifier):
+        """
+        Creates a comic strip
+
+        :param indentifier: The globally unique identifier used to find the strip on the website. Can be a tuple.
+        """
+        super().__init__(identifier)
+                         
+        self.captions = []
+        """A list of captions for each panel."""
+
+    @classmethod
+    def create_from_url(cls, url):
+        """
+        Creates a Comic instance from a given URL
+        """
+        pass
+
+    def get_package_path(self, base_path: Path):
+        """
+        Obtains the path to save the comic archive to.
+
+        :param base_path: The folder to save comics to.
+        :returns: The path to save to.
+        """
+        filename = self.get_filename()
+        return Path(base_path, filename, f"{filename}.cbz")
+
+    def create_comic_info(self) -> str:
+        """
+        Creates the contents of a ComicInfo.xml file.
+        """        
+        soup = BeautifulSoup('<?xml version="1.0" encoding="utf-8"?><ComicInfo></ComicInfo>', features="xml")
+        info_tag = soup.find("ComicInfo")
+        info_tag.append(soup.new_tag("Title", string=self.title))
+        info_tag.append(soup.new_tag("Series", string=self.series))
+        number_el = soup.new_tag("Number")
+        if type(self.identifier) == int:
+            number_el.string = str(self.identifier)
+        elif (type(self.identifier) == list or type(self.identifier) == tuple) and type(self.identifier[-1]) == int:
+            number_el.string = str(self.identifier[-1])
+        if number_el.string:
+            info_tag.append(number_el)
+        if self.date:
+            info_tag.append(soup.new_tag("Year", string=str(self.date.year)))
+            info_tag.append(soup.new_tag("Month", string=str(self.date.month)))
+            info_tag.append(soup.new_tag("Day", string=str(self.date.day)))
+        if self.author:
+            if type(self.author) == str:
+                info_tag.append(soup.new_tag("Writer", string=self.author))
+            elif type(self.author) == list:
+                authors = {}
+                writer_string = ""
+                for author in self.author:
+                    author_class = None
+                    if type(author) == str:
+                        author_name = author
+                        author_class = "Writer"
+                    elif type(author) == dict:
+                        author_name = author["name"]
+                        if author["role"].lower() in ("writer", "author", "creator"):
+                            author_class = "Writer"
+                        elif author["role"].lower() in ("penciller"):
+                            author_class = "Penciller"
+                        elif author["role"].lower() in ("inker"):
+                            author_class = "Inker"
+                        elif author["role"].lower() in ("colorist"):
+                            author_class = "Colorist"
+                        elif author["role"].lower() in ("letterer"):
+                            author_class = "Letterer"
+                        elif author["role"].lower() in ("coverartist", "conver_artist"):
+                            author_class = "CoverArtist"
+                        elif author["role"].lower() in ("editor"):
+                            author_class = "Editor"
+                        elif author["role"].lower() in ("translator"):
+                            author_class = "Translator"
+                    if author_class not in authors:
+                        authors[author_class] = author_name
+                    else:
+                        authors[author_class] += "," + author_name
+                for author_class, author_list in authors.items():
+                    info_tag.append(soup.new_tag(author_class, string=author_list))
+        info_tag.append(soup.new_tag("Format", string="Web"))
+        info_tag.append(soup.new_tag("PageCount", string=str(len(self.transformed_images))))
+        return str(soup)
+
+    def package_data(self, base_path: Path, plain: bool = False):
+        """
+        Compresses all the data into a cbz file.
+
+        :param base_path: The path to save all downloads to.
+        :param plain: If true, we will save the images as downloaded, without any transformations.
+        """
+        if not self.is_loaded():
+            raise SequenceException("Cannot package comic book before data has been fully loaded.")
+        if not self.is_downloaded():
+            raise SequenceException("Cannot package comic book before data has been fully downloaded.")
+        if not self.transformed_images:
+            if plain:
+                self.transformed_images = self.images
+            else:
+                if not self._transformed:
+                    if self._transform_lock._lock.locked():
+                        # Await for the existing transform to complete
+                        self._transform_lock.wait()
+                    else:
+                        # Run the transformation outselves
+                        with self._transform_lock:
+                            self._transform_images()
+                            self._transformed = True
+                            self._transform_lock.notify_all()
+        save_path = self.get_package_path(base_path)
+        save_path.parent.mkdir(parents=True, exist_ok=True)
+        with ZipFile(self.get_package_path(base_path), 'w') as comic_zip:
+            for i in range(len(self.transformed_images)):
+                image = self.transformed_images[i]
+                if hasattr(image, "name"):
+                    with open(image.name, 'rb') as download_stream:
+                        download_cont = download_stream.read()
+                    image_path = Path(image.name)
+                    suffix = image_path.suffix
+                    if len(suffix) > 5:
+                        # There is something fishy going on, so let us just use the default
+                        suffix = None
+                    if not suffix:
+                        suffix = ".png"
+                elif isinstance(image, io.IOBase):
+                    download_cont = image.read()
+                    download_cont.close()
+                    suffix = ".png"
+                elif isinstance(image, Path) or type(image) == str and len(image) < 250 and Path(image).exists():
+                    with open(Path(image), 'rb') as download_stream:
+                        download_cont = download_stream.read()
+                    suffix = image.suffix
+                    if len(suffix) > 5:
+                        # There is something fishy going on, so let us just use the default
+                        suffix = None
+                    if not suffix:
+                        suffix = ".png"
+                else:
+                    download_cont = image
+                    suffix = ".png"
+                if type(download_cont) == str:
+                    download_cont = bytes(download_cont, 'utf-8')
+                logging.info("Packaging resource %d" % i)
+                with comic_zip.open(str(i + 1) + (suffix), 'w') as zip_stream:
+                    zip_stream.write(download_cont)
+            # Add a ComicInfo file
+            comic_info = self.create_comic_info()
+            if comic_info:
+                with comic_zip.open("ComicInfo.xml", 'w') as zip_stream:
+                    zip_stream.write(comic_info.encode("utf-8"));
+        # Delete the base images, as they are no longer needed.
+        # We cannot touch the transformed images, since some
+        # of them may come directly from the base comic, and
+        # we have no way of telling.
+        for image in self.images:
+            image_path = Path(image.name)
+            if image_path.exists():
+                image_path.unlink()
+
+class ComicStrip(ComicBook, ABC):
+    """
+    A generic representation of an issue in a comic series. Unlike the base
+    ComicBook class, these objects are tied to a ComicCollection instance
+    and derive some data from that class.
+    """
+    def __init__(self, comic, identifier):
+        """
+        Creates a comic strip.
+
+        :param comic: The `ComicCollection` object that this strip is part of.
+        :param indentifier: The collection-unique identifier used to find the strip on the website. Can be a tuple.
+        """
+        super().__init__(identifier)
+
+        self.comic = comic
+
+    @classmethod
+    def create_from_url(cls, url, collection):
+        """
+        Creates a Comic instance from a given URL
+        """
+        return collection.create_from_url(url)
+
+    @property
+    def author(self):
+        """
+        The author(s) of the comic. Can be a string for a name, a list of names, or a list of objects containing the names under "name" and role under "role".
+
+        For Comic Strips, this references back to the main comic series author.
+        """
+        return self.comic.author
+
+    @author.setter
+    def author(self, x):
+        pass
+
+    @property
+    def series(self) -> str:
+        """The series that this comic is a part of."""
+        return self.comic.title
+
+    @series.setter
+    def series(self, x):
+        pass
+
     def get_filename(self):
         """
         Obtains the name of the final export (not including the stem). Calling this method requires the data be loaded first.
@@ -495,7 +909,6 @@ class ComicStrip(ImageRepo, ABC):
     def load_data(self):
         self.comic.load_data()
         super().load_data()
-        index_strip(self)
 
     def download_data(self):
         self.comic.download_data()
@@ -509,138 +922,28 @@ class ComicStrip(ImageRepo, ABC):
         self.comic.await_download()
         super().await_download()
 
-    @abstractmethod
-    def _load_data(self):
-        """
-        Queries the source to obtain information on the comic.
-
-        Implementing methods need to find the following information:
-        The title of the comic, loaded to `title`.
-        The publish date (or datetime) of the comic, loaded to `date`.
-        A list of panel images, loaded into `image_urls`.
-        A list of captions, loaded into `captions`. Any captions beyond the list of images can be added to new pages without comics.
-        """
-        pass
-
-    @abstractmethod
-    def _transform_images(self):
-        """
-        Called by the packaging method to create a series of locally-transformed
-        images and returning the ordered list of them.
-
-        This method is meant to do things like add alt text, descriptions, title pages, etc.
-        to the final comic. Simpler implementations can simply return a list of the
-        unmodified images with the comic headers from #comic at the beginning.
-
-        All implementations should assign the ordered list to #transformed_images. If this
-        field is not set, then packaging will default to just package the comic strip
-        images.
-        """
-        self.transformed_images = self.images
-
-    def create_comic_info(self) -> str:
-        """
-        Creates the contents of a ComicInfo.xml file.
-        """        
-        soup = BeautifulSoup('<?xml version="1.0" encoding="utf-8"?><ComicInfo></ComicInfo>', features="xml")
-        info_tag = soup.find("ComicInfo")
-        info_tag.append(soup.new_tag("Title", string=self.title))
-        info_tag.append(soup.new_tag("Series", string=self.comic.title))
-        number_el = soup.new_tag("Number")
-        if type(self.identifier) == int:
-            number_el.string = str(self.identifier)
-        elif (type(self.identifier) == list or type(self.identifier) == tuple) and type(self.identifier[-1]) == int:
-            number_el.string = str(self.identifier[-1])
-        if number_el.string:
-            info_tag.append(number_el)
-        if self.date:
-            info_tag.append(soup.new_tag("Year", string=str(self.date.year)))
-            info_tag.append(soup.new_tag("Month", string=str(self.date.month)))
-            info_tag.append(soup.new_tag("Day", string=str(self.date.day)))
-        if self.comic.author:
-            if type(self.comic.author) == str:
-                info_tag.append(soup.new_tag("Writer", string=self.comic.author))
-            elif type(self.comic.author) == list:
-                authors = {}
-                writer_string = ""
-                for author in self.comic.author:
-                    author_class = None
-                    if type(author) == str:
-                        author_name = author
-                        author_class = "Writer"
-                    elif type(author) == dict:
-                        author_name = author["name"]
-                        if author["role"].lower() in ("writer", "author", "creator"):
-                            author_class = "Writer"
-                        elif author["role"].lower() in ("penciller"):
-                            author_class = "Penciller"
-                        elif author["role"].lower() in ("inker"):
-                            author_class = "Inker"
-                        elif author["role"].lower() in ("colorist"):
-                            author_class = "Colorist"
-                        elif author["role"].lower() in ("letterer"):
-                            author_class = "Letterer"
-                        elif author["role"].lower() in ("coverartist", "conver_artist"):
-                            author_class = "CoverArtist"
-                        elif author["role"].lower() in ("editor"):
-                            author_class = "Editor"
-                        elif author["role"].lower() in ("translator"):
-                            author_class = "Translator"
-                    if author_class not in authors:
-                        authors[author_class] = author_name
-                    else:
-                        authors[author_class] += "," + author_name
-                for author_class, author_list in authors.items():
-                    info_tag.append(soup.new_tag(author_class, string=author_list))
-        info_tag.append(soup.new_tag("Format", string="Web"))
-        info_tag.append(soup.new_tag("PageCount", string=str(len(self.transformed_images))))
-        return str(soup)
-
-    def package_data(self, base_path: Path):
-        """
-        Compresses all the data into a cbz file.
-        """
-        if not self.is_loaded():
-            raise SequenceException("Cannot package comic strip before strip data has been fully loaded.")
-        if not self.is_downloaded():
-            raise SequenceException("Cannot package comic strip before strip data has been fully downloaded.")
+    def package_data(self, base_path: Path, plain: bool = False):
         if not self.comic.is_loaded():
             raise SequenceException("Cannot package comic strip before comic data has been fully loaded.")
         if not self.comic.is_downloaded():
             raise SequenceException("Cannot package comic strip before comic data has been fully downloaded.")
-        if not self.transformed_images:
-            if not self._transformed:
-                if self._transform_lock._lock.locked():
-                    # Await for the existing transform to complete
-                    self._transform_lock.wait()
-                else:
-                    # Run the transformation outselves
-                    with self._transform_lock:
-                        self._transform_images()
-                        self._transformed = True
-                        self._transform_lock.notify_all()
-        save_path = self.get_package_path(base_path)
-        save_path.parent.mkdir(parents=True, exist_ok=True)
-        with ZipFile(self.get_package_path(base_path), 'w') as comic_zip:
-            for i in range(len(self.transformed_images)):
-                image = self.transformed_images[i]
-                image_path = Path(image.name)
-                logging.info("Packaging %s" % image_path.suffix)
-                with open(image.name, 'rb') as image_stream, comic_zip.open(str(i + 1) + (image_path.suffix or '.png'), 'w') as zip_stream:
-                    zip_stream.write(image_stream.read())
-            # Add a ComicInfo file
-            comic_info = self.create_comic_info()
-            if comic_info:
-                with comic_zip.open("ComicInfo.xml", 'w') as zip_stream:
-                    zip_stream.write(comic_info.encode("utf-8"));
-        # Delete the base images, as they are no longer needed.
-        # We cannot touch the transformed images, since some
-        # of them may come directly from the base comic, and
-        # we have no way of telling.
-        for image in self.images:
-            image_path = Path(image.name)
-            if image_path.exists():
-                image_path.unlink()
+        super().package_data(base_path, plain)
+
+    def __str__(self):
+        return self.__class__.__name__ + "__" + self.comic.get_identifier_string() + "__" + self.get_identifier_string()
+
+    def __repr__(self):
+        representation = "<" + str(self.__class__.__name__) + " "
+        if self.comic.title:
+            representation += self.comic.title + " (" + self.comic.get_identifier_string() + "): "
+        else:
+            representation += self.comic.get_identifier_string() + ": "
+        if self.title:
+            representation += self.title + " (" + self.get_identifier_string() + ")"
+        else:
+            representation += self.comic.get_identifier_string()
+        representation += ">"
+        return representation
 
 class URLFormat:
     """An internal class used to help sort URLs based on subdomains and paths"""
@@ -723,7 +1026,7 @@ comic_registry = {}
 _registry_subdomains = []
 """An internal list keeping track of the order we should use to find the right parser (priority is last)"""
 
-def register_comic_class(url: str, comic_cls: type[Comic]):
+def register_comic_class(url: str, comic_cls: type[ComicBook]):
     """
     Registers a comic type.
 
@@ -756,7 +1059,7 @@ def register_comic_class(url: str, comic_cls: type[Comic]):
     comic_registry[url_f] = comic_cls
     bisect.insort(_registry_subdomains, url_f)
 
-def find_comic_class(url: str) -> type[Comic]:
+def find_comic_class(url: str) -> type[ComicBook]:
     """
     Finds the appropriate comic for a given URL.
 

src/comic_download/dinosaur_comics.py

@@ -0,0 +1,219 @@
+#!/usr/bin/env python3
+
+#   This CLI tool allows for the download and packaging of various internet comics into .cbz files.
+#   Copyright (C) 2025  Markil 3
+#   http://www.singlepilot.net
+#
+#   This program is free software: you can redistribute it and/or modify
+#   it under the terms of the GNU General Public License as published by
+#   the Free Software Foundation, either version 3 of the License, or
+#   (at your option) any later version.
+#
+#   This program is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#   GNU General Public License for more details.
+#
+#   You should have received a copy of the GNU General Public License
+#   along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+import logging
+import datetime
+import textwrap
+import json
+import re
+from urllib.parse import urlparse, parse_qs
+
+from importlib import resources
+from pathlib import Path
+from tempfile import NamedTemporaryFile
+
+import requests
+from PIL import Image, ImageDraw, ImageFont
+from bs4 import BeautifulSoup
+
+from comic_download.comic_strip import ComicCollection as Comic, ComicStrip, register_comic_class
+
+class DinosaurComic(Comic):
+    """
+    The Dinosaur Comics strip
+    """
+
+    def __init__(self):
+        super().__init__("dinosaur_comics")
+
+    @classmethod
+    def create_from_url(cls, url):
+        return cls()
+
+    def _load_data(self):
+        self.title = "Dinosaur Comics!"
+        self.author = "Ryan North"
+        self.image_urls = {
+            "header": "https://www.qwantz.com/logo.png",
+            "background": "https://www.qwantz.com/sky.png"
+        }
+        self.description = "this comic... might be the best comic?"
+
+        result = requests.get("https://www.qwantz.com/archive.php")
+        result.raise_for_status()
+
+        content = BeautifulSoup(result.content, features="lxml")
+        archives = content.find_all("ul", class_="archive")
+        self.strips = []
+        self.strip_index = {}
+        date_pat = re.compile(r'(\d+)(st|nd|rd|th)')
+        for archive_month in archives:
+            for line_item in archive_month.find_all("li"):
+                link_el = line_item.find("a")
+                if link_el:
+                    parsed_index = urlparse(link_el["href"])
+                    identifier = int(parse_qs(parsed_index.query)["comic"][0])
+                    date_str = link_el.get_text()
+                    date = datetime.datetime.strptime(date_pat.sub(r'\1', date_str), '%B %d, %Y').date()
+                    self.strips.append({
+                        "identifier": identifier,
+                        "date": date,
+                        "description": link_el.next_sibling.get_text()[2:]
+                    })
+        self.strips.sort(key=lambda x: x["date"])
+        for i in range(len(self.strips)):
+            self.strip_index[self.strips[i]["identifier"]] = i
+
+    def get_first_strip(self):
+        return self.strips[0]["identifier"]
+
+    def get_latest_strip(self):
+        return self.strips[-1]["identifier"]
+
+    def get_all_strips(self) -> list:
+        return [strip["identifier"] for strip in self.strips]
+
+    def __new__(cls):
+        if not hasattr(cls, 'instance'):
+            cls.instance = super(DinosaurComic, cls).__new__(cls)
+        return cls.instance
+        
+
+class DinosaurComicStrip(ComicStrip):
+    """
+    A comic strip object that represents a single Existential Comic strip.
+    """
+    
+    def __init__(self, comic, index: int):
+        super().__init__(comic, index)
+        self.url = f"https://qwantz.com/index.php?comic={index}"
+        self.title =  None
+        strip_data = comic.strips[comic.strip_index[index]]
+        self.date = strip_data["date"]
+        self.description = strip_data["description"]
+
+    @property
+    def index(self):
+        # Alias
+        return self.identifier
+
+    def _load_data(self):
+        logging.info("Loading data for comic %s from %s", self.index, self.url)
+        result = requests.get(self.url)
+        result.raise_for_status()
+
+        content = BeautifulSoup(result.content, features="lxml")
+        title = content.find("meta", property="og:title")
+        if title and title["content"]:
+            self.title = title["content"]
+        for img in content.find_all("img", class_="comic"):
+            self.image_urls.append(f'https://qwantz.com/{img["src"]}')
+            if img.get("title"):
+                self.captions.append(img["title"])
+            else:
+                self.captions.append("")
+
+        
+    def _transform_images(self):
+        """
+        Takes the raw image data from #download_data and transforms it to add a title, captions, etc. This function is not idempotent.
+        """
+        f_width = 780
+        title_size = 21
+        description_spacing = 10
+        description_size = 18
+        caption_size = 12
+
+        with resources.path("comic_download", "Lucida Sans Bold.ttf") as luc_sans_bold, resources.path("comic_download", "Lucida Sans.ttf") as luc_sans:
+            title_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), title_size, layout_engine=ImageFont.Layout.RAQM)
+            description_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), description_size, layout_engine=ImageFont.Layout.RAQM)
+            caption_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans.ttf"), caption_size)
+
+        title_box = title_font.getbbox(self.title)
+        title_box = (title_box[2] - title_box[0], title_box[3] - title_box[1])
+        caption_spacing = 4
+
+        url_box = caption_font.getbbox(self.url)
+        url_box = (url_box[2] - url_box[0], url_box[3] - url_box[1])
+        date_box = caption_font.getbbox(self.date.isoformat())
+        date_box = (date_box[2] - date_box[0], date_box[3] - date_box[1])
+        text_margin = 20
+
+        self.transformed_images = []
+        header_img = Image.open(self.comic.images["header"].name)
+        background_img = Image.open(self.comic.images["background"].name)
+        for i in range(len(self.images)):
+            img = Image.open(self.images[i].name)
+            comic_width = max(img.width, header_img.width)
+            if self.captions[i]:
+                # Take measurements of the page caption, if one is present. 
+                # Pillow's bbox functions do not handle newline characters properly, so we have to
+                # split the text, find the widest line, and use that.
+                caption = textwrap.wrap(self.captions[i], width = comic_width // caption_size)
+                caption_lines = len(caption)
+                caption_box = caption_font.getbbox(max(caption, key=len))
+                caption_box = (caption_box[2] - caption_box[0], (caption_box[3] - caption_box[1] + caption_spacing) * len(caption))
+                caption = "\n".join(caption)
+            else:
+                caption_box = (0, 0)
+            # The first page requires extra vertical space for the headers
+            if i == 0:
+                description = textwrap.wrap(self.description, width=comic_width // description_size)
+                description_lines = len(description)
+                description_box = description_font.getbbox(max(description, key=len))
+                description_box = (description_box[2] - description_box[0], (description_box[3] - description_box[1] + description_spacing) * (len(description) + 1))
+                description = "\n".join(description)
+                
+                f_offset = header_img.height + description_box[1] + max(date_box[1], url_box[1]) + text_margin * 2
+                # Grab the image size while we are at it, for use outside of the loop
+                img_size = img.size
+            else:
+                f_offset = 0
+            f_img_size = (comic_width, f_offset + img.height + caption_box[1] + text_margin)
+            f_img = Image.new("RGBA", f_img_size, (255, 255, 255, 255))
+            # Draw the headers as needed
+            if i == 0:
+                #f_img.paste(background_img, (0, 0))
+                f_img.paste(header_img, ((comic_width - header_img.width) // 2, 0))
+
+            # Draw the actual comic
+            f_img.paste(img, ((comic_width - img.width) // 2, f_offset))
+
+            draw = ImageDraw.Draw(f_img)
+            if i == 0:
+                # Draw the description
+                draw.multiline_text(((comic_width - description_box[0]) // 2, header_img.height + 20), description, (0, 0, 0), spacing=description_spacing, font=description_font, align="center")
+                # Draw the URL
+                draw.text((text_margin, header_img.height + description_box[1] + text_margin), self.url, (0, 0, 0), font=caption_font)
+                # Draw the date
+                draw.text((comic_width - date_box[0] - text_margin, header_img.height + description_box[1] + text_margin), self.date.isoformat(), (0, 0, 0), align="right", font=caption_font)
+            # Draw the caption
+            if self.captions[i]:
+                draw.multiline_text(((comic_width - caption_box[0]) // 2, f_offset + img.height), caption, (0, 0, 0), spacing=caption_spacing, font=caption_font, align="center")
+            # Save the image
+            f_image_path = NamedTemporaryFile(mode='wb', suffix=f"f_{i}.png", prefix=self.get_identifier_string(), delete = False)
+            f_image_path.close()
+            f_img.save(f_image_path.name)
+            self.transformed_images.append(f_image_path)
+
+DinosaurComicStrip.collection_cls = DinosaurComic
+register_comic_class("qwantz.com", DinosaurComicStrip)
+register_comic_class("dinosaurcomics.com", DinosaurComicStrip)
+register_comic_class("exotica.ca", DinosaurComicStrip)
+register_comic_class("chewbac.ca", DinosaurComicStrip)

src/comic_download/existential_comics.py

@@ -24,6 +24,7 @@ import json
 import re
 from urllib.parse import urlparse
 
+from importlib import resources
 from pathlib import Path
 from tempfile import NamedTemporaryFile
 
@@ -31,7 +32,7 @@ import requests
 from PIL import Image, ImageDraw, ImageFont
 from bs4 import BeautifulSoup
 
-from comic_download.comic_strip import Comic, ComicStrip, register_comic_class
+from comic_download.comic_strip import ComicCollection as Comic, ComicStrip, register_comic_class
 
 class ExistentialComic(Comic):
     """
@@ -139,9 +140,10 @@ class ExistentialComicStrip(ComicStrip):
         safety_size = 24
         caption_size = 15
         f_size = (1000, 1500)
-        title_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), title_size)
-        safety_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), safety_size)
-        caption_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans.ttf"), caption_size)
+        with resources.path("comic_download", "Lucida Sans Bold.ttf") as luc_sans_bold, resources.path("comic_download", "Lucida Sans.ttf") as luc_sans:
+            title_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), title_size)
+            safety_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), safety_size)
+            caption_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans.ttf"), caption_size)
         title_box = title_font.getbbox(self.title)
         title_box = (title_box[2] - title_box[0], title_box[3] - title_box[1])
         caption_spacing = 4
@@ -233,5 +235,5 @@ class ExistentialComicStrip(ComicStrip):
             f_img.save(f_image_path.name)
             self.transformed_images.append(f_image_path)
 
-ExistentialComic.strip_cls = ExistentialComicStrip
-register_comic_class("existentialcomics.com", ExistentialComic)
+ExistentialComicStrip.collection_cls = ExistentialComic
+register_comic_class("existentialcomics.com", ExistentialComicStrip)

src/comic_download/xkcd.py

@@ -24,6 +24,7 @@ import textwrap
 from zipfile import ZipFile
 from urllib.parse import urlparse
 
+from importlib import resources
 from pathlib import Path
 from tempfile import NamedTemporaryFile
 
@@ -31,7 +32,7 @@ import requests
 from PIL import Image, ImageDraw, ImageFont
 from bs4 import BeautifulSoup
 
-from comic_download.comic_strip import Comic, ComicStrip, register_comic_class
+from comic_download.comic_strip import ComicCollection as Comic, ComicStrip, register_comic_class
 
 class XKCDComic(Comic):
     """
@@ -110,8 +111,10 @@ class XKCDComicStrip(ComicStrip):
         f_width = 780
         title_size = 21
         caption_size = 12
-        title_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), title_size, layout_engine=ImageFont.Layout.RAQM)
-        caption_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans.ttf"), caption_size)
+
+        with resources.path("comic_download", "Lucida Sans Bold.ttf") as luc_sans_bold, resources.path("comic_download", "Lucida Sans.ttf") as luc_sans:
+            title_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans Bold.ttf"), title_size, layout_engine=ImageFont.Layout.RAQM)
+            caption_font = ImageFont.truetype(Path(Path(__file__).parent, "Lucida Sans.ttf"), caption_size)
 
         title_box = title_font.getbbox(self.title)
         title_box = (title_box[2] - title_box[0], title_box[3] - title_box[1])
@@ -152,5 +155,5 @@ class XKCDComicStrip(ComicStrip):
                 self.transformed_images.append(f_image)
 
 
-XKCDComic.strip_cls = XKCDComicStrip
-register_comic_class("xkcd.com", XKCDComic)
+XKCDComicStrip.collection_cls = XKCDComic
+register_comic_class("xkcd.com", XKCDComicStrip)