fix(api): Carry over paragraph styling (#51)

* fix(api): Typo fix

* fix(api): Remove chapitre/chapter class

.gitignore

@@ -1,6 +1,12 @@
 __pycache__
 venv
 *epub
+*pdf
+*html
 data
 *ipynb
 build
+.vscode
+.venv
+.env
+*log

.vscode/launch.json

@@ -0,0 +1,24 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python Debugger: FastAPI",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "args": [
+                "main:app",
+                "--reload",
+                "--host",
+                "0.0.0.0",
+                "--port",
+                "8086"
+            ],
+            "jinja": true,
+            "cwd": "${workspaceFolder}/src/api/src"
+        }
+    ]
+}

Dockerfile

@@ -12,14 +12,42 @@ RUN npm run build
 FROM python:3.10-slim
 
 WORKDIR /app
+
+# Install apt-fast, git, exiftool
+
+COPY --from=nobodyxu/apt-fast:latest-debian-buster-slim /usr/local/ /usr/local/
+
+RUN apt update
+RUN apt install -y aria2
+RUN apt-fast install -y git build-essential libpango-1.0-0 libpangoft2-1.0-0 wget
+
+ENV EXIFTOOL_VERSION="13.06"
+RUN wget "https://exiftool.org/Image-ExifTool-${EXIFTOOL_VERSION}.tar.gz"
+RUN gzip -dc "Image-ExifTool-${EXIFTOOL_VERSION}.tar.gz" | tar -xf -
+WORKDIR /app/Image-ExifTool-${EXIFTOOL_VERSION}
+RUN perl Makefile.PL
+RUN make test
+RUN make install
+
+RUN rm -rf /var/lib/apt/lists/* /app/Image-ExifTool-${EXIFTOOL_VERSION}
+
+WORKDIR /app
+
+# --- #
+
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
+
 COPY src/api/requirements.txt requirements.txt
-RUN pip3 install -r requirements.txt
-COPY --from=0 /build/build /app/build
-# COPY src/api/src/.env .env
-COPY src/api/src .
+COPY src/api/exiftool.config exiftool.config
+RUN uv pip install -r requirements.txt --system
+COPY --from=0 /build/build /app/src/build
+COPY src/api/src src
+
+# Is this still needed?
+RUN ln -s /app/src/pdf/fonts /tmp/fonts
+
+WORKDIR /app/src
 
 EXPOSE 80
-# ENV PORT=80
 
 CMD [ "python3", "main.py"]
-

README.md

@@ -2,20 +2,24 @@ WattpadDownloader ([Demo](https://wpd.rambhat.la))
 ---
 Straightforward, Extendable WebApp to download Wattpad Books as EPUB Files.
 
-![image](https://github.com/TheOnlyWayUp/WattpadDownloader/assets/76237496/8a3fda0b-b851-4c5f-9306-ba9c17cdcc8b)
+![image](https://github.com/user-attachments/assets/b9d87d6b-5302-4561-98b0-d7f95bff9f04)
 
 
 Stars ⭐ are appreciated. Thanks!
 
 ## Features
-- ⚡ Lightweight Frontend and Minimal Javascript.
+- ⚡ Lightweight Frontend.
+- 🪙 Supports Authentication (Download paid stories from your account!)
 - 🌐 API Support (Visit the `/docs` path on your instance for more.)
-- 🐇 Fast Generation, Basic Ratelimit Handling.
+- 🐇 Fast Generation
+- 🗃️ Caching, Ratelimit handling
 - 🐳 Docker Support
-- 🏷️ Generated EPUB File includes Metadata. (Dublin Core Spec)
-- 📖 Plays well with E-Readers. (Kindle Support if KOReader present)
+- 🏷️ Generated books contain metadata, supported by Calibre and other E-Book Software.
+- 📖 Plays well with E-Readers. (Send2Kindle, KOReader, ReMarkable, KOBO, Calibre Reader...)
 - 💻 Easily Hackable. Extend with ease.
 
+Still not convinced? Take a look some [sample downloads](./samples/).
+
 
 ## Set Up
 1. Clone the repository: `git clone https://github.com/TheOnlyWayUp/WattpadDownloader/ && cd WattpadDownloader`
@@ -24,6 +28,24 @@ Stars ⭐ are appreciated. Thanks!
 
 That's it! You can use your instance at `http://localhost:5042`. API Documentation is available at `http://localhost:5042/docs`.
 
+### Concurrent Requests
+The file-based cache struggles with concurrent requests (discussed in TheOnlyWayUp/WattpadDownloader#2 and TheOnlyWayUp/WattpadDownloader#22). If you're downloading a large number of books concurrently, switch to the Redis cache. Assuming you've built the image already:
+1. Fill the .env file. Localhost will not work in a docker container unless [`host.docker.internal`](https://docs.docker.com/desktop/features/networking/#i-want-to-connect-from-a-container-to-a-service-on-the-host) or a platform-specific variant is provided.
+```
+USE_CACHE=true
+CACHE_TYPE=redis
+REDIS_CONNECTION_URL=redis://username:password@host:port
+```
+
+
+2. Run the container and supply the .env file, `docker run -d -p 5042:80 --env-file .env wp_downloader`
+Alternatively, if Redis is running on localhost
+2. Modify your `.env` file, replacing `localhost` with `host.docker.internal`. `redis://localhost:6379` should become `redis://host.docker.internal:6379`. Then, start the container, `docker run -d -p 5042:80 --env-file .env --add-host host.docker.internal:host-gateway wp_downloader`
+
+## Development
+- Developers, ensure you have `wkhtmltopdf` available on your PATH. 
+- Run `wkhtmltopdf` on your terminal, if you see "Reduced Functionality", run [this script](https://raw.githubusercontent.com/JazzCore/python-pdfkit/b7bf798b946fa5655f8e82f0d80dec6b6b13d414/ci/before-script.sh) to install a fully featured compilation of `wkhtmltopdf.
+
 ---
 
 My thanks to [aerkalov/ebooklib](https://github.com/aerkalov/ebooklib) for a fast and well-documented package.
@@ -31,5 +53,5 @@ My thanks to [aerkalov/ebooklib](https://github.com/aerkalov/ebooklib) for a fas
 ---
 
 <div align="center">
-    <p>TheOnlyWayUp © 2023</p>
+    <p>TheOnlyWayUp © 2024</p>
 </div>

src/api/.env_template

@@ -0,0 +1,3 @@
+USE_CACHE=true
+CACHE_TYPE=file
+REDIS_CONNECTION_URL=

src/api/.python-version

@@ -0,0 +1 @@
+3.10

src/api/exiftool.config

@@ -0,0 +1,26 @@
+
+%Image::ExifTool::UserDefined = (
+    'Image::ExifTool::XMP::xmp' => {
+        Completed => {
+            Writable => 'boolean',  # Can be a boolean (True/False)
+            Groups => { 2 => 'Content' },
+        },
+        MatureContent => {
+            Writable => 'boolean',  # Can be a boolean (True/False)
+            Groups => { 2 => 'Content' },
+        },
+    },
+    
+    'Image::ExifTool::IPTC::ApplicationRecord' => {
+        161 => {
+            Name => 'Completed',
+            Format => 'string[0,16]',  # Store as a string (e.g., "Yes"/"No")
+        },
+        162 => {
+            Name => 'MatureContent',
+            Format => 'string[0,16]',  # Store as a string (e.g., "Yes"/"No")
+        },
+    },
+);
+
+1;  # End

src/api/pyproject.toml

@@ -0,0 +1,28 @@
+[project]
+name = "api"
+version = "0.1.0"
+description = "Wattpad Downloader API"
+readme = "../../README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "aiohttp>=3.9.1",
+    "rich>=13.9.4",
+    "fastapi>=0.115.5",
+    "ebooklib>=0.18",
+    "python-dotenv>=1.0.1",
+    "pydantic-settings>=2.6.1",
+    "eliot>=1.16.0",
+    "type-extensions>=0.1.2",
+    "backoff>=2.2.1",
+    "aiohttp-client-cache[all]",
+    "bs4>=0.0.2",
+    "uvicorn>=0.32.1",
+    "pyexiftool>=0.5.6",
+    "weasyprint>=63.0",
+]
+
+[tool.ruff.lint]
+ignore = ['E402']
+
+[tool.uv.sources]
+aiohttp-client-cache = { git = "https://github.com/TheOnlyWayUp/aiohttp-client-cache.git", rev = "keydb-ttl" }

src/api/requirements.txt

@@ -1,62 +1,75 @@
-aiofiles==23.2.1
-aiohttp==3.9.1
-aiohttp-client-cache==0.10.0
+aioboto3==13.2.0
+aiobotocore==2.15.2
+aiofiles==24.1.0
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.9
+aiohttp-client-cache @ git+https://github.com/TheOnlyWayUp/aiohttp-client-cache.git@1f94f1d751e7320c0ea981d532ff02924782dae6
+aioitertools==0.12.0
 aiosignal==1.3.1
-aiosqlite==0.19.0
-annotated-types==0.6.0
-anyio==4.2.0
-asttokens==2.4.1
+aiosqlite==0.20.0
+annotated-types==0.7.0
+anyio==4.6.2.post1
 async-timeout==4.0.3
 attrs==23.1.0
 backoff==2.2.1
 beautifulsoup4==4.12.3
+boltons==24.1.0
+boto3==1.35.36
+botocore==1.35.36
+brotli==1.1.0
 bs4==0.0.2
+cffi==1.17.1
 click==8.1.7
-comm==0.2.0
-debugpy==1.8.0
-decorator==5.1.1
-EbookLib==0.18
-exceptiongroup==1.2.0
-executing==2.0.1
-fastapi==0.108.0
+cssselect2==0.7.0
+dnspython==2.7.0
+ebooklib==0.18
+eliot==1.16.0
+exceptiongroup==1.2.2
+fastapi==0.115.5
+fonttools==4.55.2
 frozenlist==1.4.1
 h11==0.14.0
 idna==3.6
-ipykernel==6.28.0
-ipython==8.19.0
-itsdangerous==2.1.2
-jedi==0.19.1
-jupyter_client==8.6.0
-jupyter_core==5.5.1
-lxml==4.9.4
+itsdangerous==2.2.0
+jmespath==1.0.1
+lxml==5.3.0
 markdown-it-py==3.0.0
-matplotlib-inline==0.1.6
 mdurl==0.1.2
+motor==3.6.0
 multidict==6.0.4
-nest-asyncio==1.5.8
-packaging==23.2
-parso==0.8.3
-pexpect==4.9.0
-platformdirs==4.1.0
-prompt-toolkit==3.0.43
-psutil==5.9.7
-ptyprocess==0.7.0
-pure-eval==0.2.2
-pydantic==2.5.3
-pydantic_core==2.14.6
-Pygments==2.17.2
-python-dateutil==2.8.2
-pyzmq==25.1.2
-rich==13.7.0
+orjson==3.10.12
+pillow==10.4.0
+propcache==0.2.1
+pycparser==2.22
+pydantic==2.10.2
+pydantic-core==2.27.1
+pydantic-settings==2.6.1
+pydyf==0.11.0
+pyexiftool==0.5.6
+pygments==2.18.0
+pymongo==4.9.2
+pyphen==0.15.0
+pyrsistent==0.20.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+redis==5.2.0
+rich==13.9.4
+s3transfer==0.10.4
+setuptools==75.6.0
 six==1.16.0
-sniffio==1.3.0
-soupsieve==2.5
-stack-data==0.6.3
-starlette==0.32.0.post1
-tornado==6.4
-traitlets==5.14.0
-typing_extensions==4.9.0
+sniffio==1.3.1
+soupsieve==2.6
+starlette==0.41.3
+tinycss2==1.4.0
+tinyhtml5==2.0.0
+type-extensions==0.1.2
+typing-extensions==4.12.2
 url-normalize==1.4.3
-uvicorn==0.25.0
-wcwidth==0.2.12
-yarl==1.9.4
+urllib3==2.2.3
+uvicorn==0.32.1
+weasyprint==63.0
+webencodings==0.5.1
+wrapt==1.17.0
+yarl==1.18.3
+zope-interface==7.2
+zopfli==0.2.3.post1

src/api/src/create_book.py

@@ -1,59 +1,196 @@
-import asyncio
-from typing import Optional
-from ebooklib import epub
-import unicodedata
+from __future__ import annotations
+from typing import List, Optional, Tuple, cast
+from typing_extensions import TypedDict
 import re
+import logging
+import tempfile
+import unicodedata
+from os import environ
+from io import BytesIO
+from enum import Enum
+from base64 import b64encode
+import bs4
 import backoff
-from aiohttp import ClientResponseError, ClientSession
-from aiohttp_client_cache.session import CachedSession
-from aiohttp_client_cache import FileBackend
+from weasyprint import HTML, CSS, default_url_fetcher
+from weasyprint.text.fonts import FontConfiguration
+from ebooklib import epub
+from exiftool import ExifTool
+from eliot import to_file, start_action
+from eliot.stdlib import EliotHandler
 from bs4 import BeautifulSoup
+from dotenv import load_dotenv
+from pydantic import TypeAdapter, model_validator, field_validator
+from pydantic_settings import BaseSettings
+from aiohttp import ClientResponseError
+from aiohttp_client_cache.session import CachedSession
+from aiohttp_client_cache import FileBackend, RedisBackend
 
+load_dotenv(override=True)
+
+handler = EliotHandler()
+
+logging.getLogger("fastapi").setLevel(logging.INFO)
+logging.getLogger("fastapi").addHandler(handler)
+
+exiftool_logger = logging.getLogger("exiftool")
+exiftool_logger.addHandler(handler)
+
+logger = logging.Logger("wpd")
+logger.addHandler(handler)
+
+if environ.get("DEBUG"):
+    to_file(open("eliot.log", "wb"))
+
+
+# --- #
+
+
+class CacheTypes(Enum):
+    file = "file"
+    redis = "redis"
+
+
+class Config(BaseSettings):
+    USE_CACHE: bool = True
+    CACHE_TYPE: CacheTypes = CacheTypes.file
+    REDIS_CONNECTION_URL: str = ""
+
+    @field_validator("USE_CACHE", mode="before")
+    def validate_use_cache(cls, value):
+        # Return default if value is an empty string
+        if value == "":
+            return True  # Default value for USE_CACHE
+        return value
+
+    @field_validator("CACHE_TYPE", mode="before")
+    def validate_cache_type(cls, value):
+        # Thanks https://stackoverflow.com/a/78157474
+        if value == "":
+            return "file"
+        return value
+
+    @model_validator(mode="after")
+    def prevent_mismatched_redis_url(self):
+        match self.CACHE_TYPE:
+            case CacheTypes.file:
+                if self.REDIS_CONNECTION_URL:
+                    raise ValueError(
+                        "REDIS_CONNECTION_URL provided when File cache selected. To use Redis as a cache, set CACHE_TYPE=redis."
+                    )
+            case CacheTypes.redis:
+                if not self.REDIS_CONNECTION_URL:
+                    raise ValueError(
+                        "REDIS_CONNECTION_URL not provided when Redis cache selected. To use File cache, set CACHE_TYPE=file."
+                    )
+        return self
+
+
+config = Config()
+
+# --- #
 
 headers = {
     "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36"
 }
 
-cache = FileBackend(use_temp=True, expire_after=43200)  # 12 hours
+if config.USE_CACHE:
+    match config.CACHE_TYPE:
+        case CacheTypes.file:
+            cache = FileBackend(use_temp=True, expire_after=43200)  # 12 hours
+        case CacheTypes.redis:
+            cache = RedisBackend(
+                cache_name="wpd-aiohttp-cache",
+                address=config.REDIS_CONNECTION_URL,
+                expire_after=43200,  # 12 hours
+            )
+else:
+    cache = None
+
+logger.info(f"Using {cache=}")
 
 # --- Utilities --- #
 
 
-async def wp_get_cookies(username: str, password: str) -> dict:
-    # source: https://github.com/TheOnlyWayUp/WP-DM-Export/blob/dd4c7c51cb43f2108e0f63fc10a66cd24a740e4e/src/API/src/main.py#L25-L58
-    """Retrieves authorization cookies from Wattpad by logging in with user creds.
+def smart_trim(text: str, max_length: int = 400) -> str:
+    """Truncate a string intelligently at newlines. Coherence and max-length adherence."""
+    chunks = [t for t in text.split("\n") if t]
 
-    Args:
-        username (str): Username.
-        password (str): Password.
+    to_return = ""
+    for chunk in chunks:
+        if len(to_return) + len(chunk) < max_length:
+            to_return = chunk + "<br />"
+        else:
+            to_return = to_return.rstrip("<br />")
+            break
 
-    Raises:
-        ValueError: Bad status code.
-        ValueError: No cookies returned.
+    return to_return
 
-    Returns:
-        dict: Authorization cookies.
-    """
-    async with ClientSession(headers=headers) as session:
-        async with session.post(
-            "https://www.wattpad.com/auth/login?nextUrl=%2F&_data=routes%2Fauth.login",
-            data={
-                "username": username.lower(),
-                "password": password,
-            },  # the username.lower() is for caching
-        ) as response:
-            if response.status != 204:
-                raise ValueError("Not a 204.")
 
-            cookies = {
-                k: v.value
-                for k, v in response.cookies.items()  # Thanks https://stackoverflow.com/a/32281245
-            }
+def generate_clean_part_html(part: Part, content: str) -> bs4.Tag:
+    """Rebuild HTML Structure for a Part."""
+    chapter_title = part["title"]
+    chapter_id = part["id"]
 
-            if not cookies:
-                raise ValueError("No cookies.")
+    clean = BeautifulSoup(
+        f"""
+    <section id="section_{chapter_id}">
+        <h1 id="{chapter_id}" class="chapter-title">{chapter_title}</h1>
+    </section>
+    """,
+        "html.parser",
+    )  # html.parser doesn't create <html>/<body> tags automatically
 
-            return cookies
+    html = BeautifulSoup(content, "lxml")
+    for br in html.find_all("br"):
+        # Check if no content after br
+        if not br.next_sibling or br.next_sibling.name in ["br", None]:
+            br.decompose()
+
+    section = cast(bs4.Tag, clean.find("section"))
+    if not section:
+        raise Exception()
+
+    for child in html.find_all("p"):
+        current_paragraph = clean.new_tag("p")
+
+        # Attempt to carry over paragraph styling
+        try:
+            current_paragraph["style"] = child["style"]
+        except:
+            current_paragraph["style"] = "text-align: left;"
+
+        for p_child in list(child.children):
+            if not p_child:
+                continue
+            if isinstance(p_child, bs4.element.Tag):
+                if p_child.name == "br":
+                    p_child.decompose()
+                elif p_child.name == "img":
+                    src = p_child["src"]
+                    img_tag = clean.new_tag("img")
+                    img_tag["src"] = src
+                    section.append(img_tag)
+                    section.append(clean.new_tag("br"))
+                elif p_child.name in ["b", "i"]:
+                    styled_tag = clean.new_tag(p_child.name)
+                    styled_content = clean.new_string(p_child.text)
+                    styled_tag.append(styled_content)
+                    current_paragraph.append(styled_tag)
+                else:
+                    # Append any other tags as-is
+                    current_paragraph.append(p_child)
+            elif isinstance(p_child, bs4.element.NavigableString):
+                content = clean.new_string(p_child)
+                current_paragraph.append(content)
+
+        if current_paragraph.contents:
+            section.append(current_paragraph)
+
+        if not list(child.children):
+            # Some p tags only contain brs, once brs are removed, they are empty and can be removed as well.
+            child.decompose()
+
+    return section
 
 
 def slugify(value, allow_unicode=False) -> str:
@@ -79,148 +216,571 @@ def slugify(value, allow_unicode=False) -> str:
     return re.sub(r"[-\s]+", "-", value).strip("-_")
 
 
+async def fetch_cookies(username: str, password: str) -> dict:
+    # source: https://github.com/TheOnlyWayUp/WP-DM-Export/blob/dd4c7c51cb43f2108e0f63fc10a66cd24a740e4e/src/API/src/main.py#L25-L58
+    """Retrieves authorization cookies from Wattpad by logging in with user creds.
+
+    Args:
+        username (str): Username.
+        password (str): Password.
+
+    Raises:
+        ValueError: Bad status code.
+        ValueError: No cookies returned.
+
+    Returns:
+        dict: Authorization cookies.
+    """
+    with start_action(action_type="api_fetch_cookies"):
+        async with CachedSession(headers=headers, cache=None) as session:
+            async with session.post(
+                "https://www.wattpad.com/auth/login?nextUrl=%2F&_data=routes%2Fauth.login",
+                data={
+                    "username": username.lower(),
+                    "password": password,
+                },  # the username.lower() is for caching
+            ) as response:
+                if response.status != 204:
+                    raise ValueError("Not a 204.")
+
+                cookies = {
+                    k: v.value
+                    for k, v in response.cookies.items()  # Thanks https://stackoverflow.com/a/32281245
+                }
+
+                if not cookies:
+                    raise ValueError("No cookies.")
+
+                return cookies
+
+
+# --- Models --- #
+
+
+class CopyrightData(TypedDict):
+    name: str
+    statement: str
+    freedoms: str
+    printing: str
+    image_url: Optional[str]
+
+
+class Language(TypedDict):
+    name: str
+
+
+class User(TypedDict):
+    username: str
+    avatar: str
+    description: str
+
+
+class Part(TypedDict):
+    id: int
+    title: str
+
+
+class Story(TypedDict):
+    id: str
+    title: str
+    createDate: str
+    modifyDate: str
+    language: Language
+    user: User
+    description: str
+    cover: str
+    completed: bool
+    tags: List[str]
+    mature: bool
+    url: str
+    parts: List[Part]
+    isPaywalled: bool
+    copyright: int
+
+
+story_ta = TypeAdapter(Story)
+
+
+# --- Exceptions --- #
+
+
+class WattpadError(Exception):
+    """Base Exception class for Wattpad related errors."""
+
+
+class StoryNotFoundError(WattpadError):
+    """Display the "This story was not found" error to the user."""
+
+    ...
+
+
+class PartNotFoundError(StoryNotFoundError): ...
+
+
 # --- API Calls --- #
 
 
 @backoff.on_exception(backoff.expo, ClientResponseError, max_time=15)
-async def retrieve_story(story_id: int, cookies: Optional[dict] = None) -> dict:
-    """Taking a story_id, return its information from the Wattpad API."""
-    async with (
-        CachedSession(headers=headers, cache=cache)
-        if not cookies
-        else ClientSession(headers=headers, cookies=cookies)
-    ) as session:  # Don't cache requests with Cookies.
-        async with session.get(
-            f"https://www.wattpad.com/api/v3/stories/{story_id}?fields=tags,id,title,createDate,modifyDate,language(name),description,completed,mature,url,isPaywalled,user(username),parts(id,title),cover"
-        ) as response:
-            if not response.ok:
-                if response.status in [404, 400]:
-                    return {}
-            response.raise_for_status()
+async def fetch_story_from_partId(
+    part_id: int, cookies: Optional[dict] = None
+) -> Tuple[int, Story]:
+    """Fetch Story metadata from a Part ID."""
+    with start_action(action_type="api_fetch_storyFromPartId"):
+        async with CachedSession(
+            headers=headers, cache=None if cookies else cache
+        ) as session:  # Don't cache requests with Cookies.
+            async with session.get(
+                f"https://www.wattpad.com/api/v3/story_parts/{part_id}?fields=groupId,group(tags,id,title,createDate,modifyDate,language(name),description,completed,mature,url,isPaywalled,user(username,avatar,description),parts(id,title),cover,copyright)"
+            ) as response:
+                body = await response.json()
 
-            body = await response.json()
+                if response.status == 400:
+                    match body.get("error_code"):
+                        case 1020:  # "Story part not found"
+                            logger.info(f"{part_id=} not found on Wattpad, returning.")
+                            raise PartNotFoundError()
 
-    return body
+                response.raise_for_status()
+
+        return int(body["groupId"]), story_ta.validate_python(body["group"])
 
 
 @backoff.on_exception(backoff.expo, ClientResponseError, max_time=15)
-async def fetch_part_content(part_id: int, cookies: Optional[dict] = None) -> str:
-    """Return the HTML Content of a Part."""
-    async with (
-        CachedSession(headers=headers, cache=cache)
-        if not cookies
-        else ClientSession(headers=headers, cookies=cookies)
-    ) as session:  # Don't cache requests with Cookies.
-        async with session.get(
-            f"https://www.wattpad.com/apiv2/?m=storytext&id={part_id}"
-        ) as response:
-            if not response.ok:
-                if response.status in [404, 400]:
-                    return ""
-            response.raise_for_status()
+async def fetch_story(story_id: int, cookies: Optional[dict] = None) -> Story:
+    """Fetch Story metadata from a Story ID."""
+    with start_action(action_type="api_fetch_story", story_id=story_id):
+        async with CachedSession(
+            headers=headers, cookies=cookies, cache=None if cookies else cache
+        ) as session:
+            async with session.get(
+                f"https://www.wattpad.com/api/v3/stories/{story_id}?fields=tags,id,title,createDate,modifyDate,language(name),description,completed,mature,url,isPaywalled,user(username,avatar,description),parts(id,title),cover,copyright"
+            ) as response:
+                body = await response.json()
 
-            body = await response.text()
+                if response.status == 400:
+                    match body.get("error_code"):
+                        case 1017:  # "Story not found"
+                            logger.info(f"{story_id=} not found on Wattpad, returning.")
+                            raise StoryNotFoundError()
 
-    return body
+                response.raise_for_status()
+
+        return story_ta.validate_python(body)
 
 
 @backoff.on_exception(backoff.expo, ClientResponseError, max_time=15)
-async def fetch_cover(url: str, cookies: Optional[dict] = None) -> bytes:
+async def fetch_story_content_zip(
+    story_id: int, cookies: Optional[dict] = None
+) -> BytesIO:
+    """BytesIO Stream of an Archive of Part Contents for a Story."""
+    with start_action(action_type="api_fetch_storyZip", story_id=story_id):
+        async with CachedSession(
+            headers=headers,
+            cookies=cookies,
+            cache=None if cookies else cache,
+        ) as session:
+            async with session.get(
+                f"https://www.wattpad.com/apiv2/?m=storytext&group_id={story_id}&output=zip"
+            ) as response:
+                response.raise_for_status()
+
+                bytes_stream = BytesIO(await response.read())
+
+        return bytes_stream
+
+
+@backoff.on_exception(backoff.expo, ClientResponseError, max_time=15)
+async def fetch_image(url: str, should_cache: bool = False) -> bytes:
     """Fetch image bytes."""
-    async with (
-        CachedSession(headers=headers, cache=cache)
-        if not cookies
-        else ClientSession(headers=headers, cookies=cookies)
-    ) as session:  # Don't cache requests with Cookies.
-        async with session.get(url) as response:
-            if not response.ok:
-                if response.status in [404, 400]:
-                    return bytes()
-            response.raise_for_status()
+    with start_action(action_type="api_fetch_image", url=url):
+        async with CachedSession(
+            headers=headers, cache=cache if should_cache else None
+        ) as session:  # Don't cache images.
+            async with session.get(url) as response:
+                response.raise_for_status()
 
-            body = await response.read()
+                body = await response.read()
 
-    return body
+        return body
 
 
-# --- EPUB Generation --- #
+# --- Generation --- #
 
 
-def set_metadata(book, data):
-    book.add_author(data["user"]["username"])
+class EPUBGenerator:
+    """EPUB Generation utilities"""
 
-    book.add_metadata("DC", "description", data["description"])
-    book.add_metadata("DC", "created", data["createDate"])
-    book.add_metadata("DC", "modified", data["modifyDate"])
-    book.add_metadata("DC", "language", data["language"]["name"])
+    def __init__(self, data: Story, cover: bytes):
+        """Initialize EPUBGenerator. Create epub.EpubBook() and set metadata and cover."""
+        self.epub = epub.EpubBook()
+        self.data = data
+        self.cover = cover
 
-    book.add_metadata(
-        None, "meta", "", {"name": "tags", "content": ", ".join(data["tags"])}
-    )
-    book.add_metadata(
-        None, "meta", "", {"name": "mature", "content": str(int(data["mature"]))}
-    )
-    book.add_metadata(
-        None, "meta", "", {"name": "completed", "content": str(int(data["completed"]))}
-    )
+        # set metadata, defined in https://www.dublincore.org/specifications/dublin-core/dcmi-terms/#section-2
+        self.epub.add_author(data["user"]["username"])
 
+        self.epub.add_metadata("DC", "title", data["title"])
+        self.epub.add_metadata("DC", "description", data["description"])
+        self.epub.add_metadata("DC", "date", data["createDate"])
+        self.epub.add_metadata("DC", "modified", data["modifyDate"])
+        self.epub.add_metadata("DC", "language", data["language"]["name"])
 
-async def set_cover(book, data, cookies: Optional[dict] = None):
-    book.set_cover("cover.jpg", await fetch_cover(data["cover"], cookies=cookies))
-
-
-async def add_chapters(
-    book, data, download_images: bool = False, cookies: Optional[dict] = None
-):
-    chapters = []
-
-    for part in data["parts"]:
-        content = await fetch_part_content(part["id"], cookies=cookies)
-        title = part["title"]
-        clean_title = slugify(title)
-
-        # Thanks https://eu17.proxysite.com/process.php?d=5VyWYcoQl%2BVF0BYOuOavtvjOloFUZz2BJ%2Fepiusk6Nz7PV%2B9i8rs7cFviGftrBNll%2B0a3qO7UiDkTt4qwCa0fDES&b=1
-        chapter = epub.EpubHtml(
-            title=title,
-            file_name=f"{clean_title}.xhtml",
-            lang=data["language"]["name"],
+        self.epub.add_metadata(
+            None, "meta", "", {"name": "tags", "content": ", ".join(data["tags"])}
+        )
+        self.epub.add_metadata(
+            None, "meta", "", {"name": "mature", "content": str(int(data["mature"]))}
+        )
+        self.epub.add_metadata(
+            None,
+            "meta",
+            "",
+            {"name": "completed", "content": str(int(data["completed"]))},
         )
 
-        if download_images:
-            soup = BeautifulSoup(content, "lxml")
-            async with (
-                CachedSession(headers=headers, cache=cache)
-                if not cookies
-                else ClientSession(headers=headers, cookies=cookies)
-            ) as session:  # Don't cache requests with Cookies.
-                for idx, image in enumerate(soup.find_all("img")):
-                    if not image["src"]:
-                        continue
-                    async with session.get(image["src"]) as response:
-                        img = epub.EpubImage(
-                            media_type="image/jpeg",
-                            content=await response.read(),
-                            file_name=f"static/{clean_title}/{idx}.jpeg",
-                        )
-                        book.add_item(img)
-                        content = content.replace(
-                            str(image), f'<img src="static/{clean_title}/{idx}.jpeg"/>'
-                        )
+        # Set cover
+        self.epub.set_cover("cover.jpg", cover)
+        cover_chapter = epub.EpubHtml(
+            file_name="titlepage.xhtml",  # Standard for cover page
+        )
+        cover_chapter.set_content('<img src="cover.jpg">')
+        self.epub.add_item(cover_chapter)
 
-        chapter.set_content(f"<h1>{title}</h1>" + content)
+    async def add_chapters(
+        self, contents: List[bs4.Tag], download_images: bool = False
+    ):
+        """Add chapters to the Epub, downloading images if necessary. Sets the table of contents and spine."""
+        chapters: List[epub.EpubHtml] = []
 
-        chapters.append(chapter)
+        for cidx, (part, content) in enumerate(zip(self.data["parts"], contents)):
+            title = part["title"]
+            title = re.sub(r'[\x00-\x1F\x7F]', '', title) # Remove control characters
 
-        yield title  # Yield the chapter's title upon insertion preceeded by retrieval.
+            # Thanks https://eu17.proxysite.com/process.php?d=5VyWYcoQl%2BVF0BYOuOavtvjOloFUZz2BJ%2Fepiusk6Nz7PV%2B9i8rs7cFviGftrBNll%2B0a3qO7UiDkTt4qwCa0fDES&b=1
+            chapter = epub.EpubHtml(
+                title=title,
+                file_name=f"{cidx}_{part['id']}.xhtml",  # See issue #30
+                lang=self.data["language"]["name"],
+                uid=str(part["id"]).encode(),
+            )
 
-    for chapter in chapters:
-        book.add_item(chapter)
+            str_content = content.prettify()
+            if download_images:
+                soup = content
 
-    book.toc = tuple(chapters)
+                async with CachedSession(
+                    headers=headers, cache=None
+                ) as session:  # Don't cache images.
+                    for idx, image in enumerate(soup.find_all("img")):
+                        if not image["src"]:
+                            continue
+                        # Find all image tags and filter for those with sources
 
-    # Thanks https://github.com/aerkalov/ebooklib/blob/master/samples/09_create_image/create.py
-    book.add_item(epub.EpubNcx())
-    book.add_item(epub.EpubNav())
+                        async with session.get(image["src"]) as response:
+                            img = epub.EpubImage(
+                                media_type="image/jpeg",
+                                content=await response.read(),
+                                file_name=f"static/{cidx}/{idx}.jpeg",
+                            )
+                            self.epub.add_item(img)
+                            # Fetch image and pack
 
-    # create spine
-    book.spine = ["nav"] + chapters
+                            str_content = str_content.replace(
+                                str(image["src"]), f"static/{cidx}/{idx}.jpeg"
+                            )
+
+            chapter.set_content(str_content)
+            self.epub.add_item(chapter)
+
+            chapters.append(chapter)
+
+            yield title
+
+        self.epub.toc = chapters
+
+        # Thanks https://github.com/aerkalov/ebooklib/blob/master/samples/09_create_image/create.py
+        self.epub.add_item(epub.EpubNcx())
+        self.epub.add_item(epub.EpubNav())
+
+        # create spine
+        self.epub.spine = ["nav"] + chapters
+
+    def dump(self) -> BytesIO:
+        # Thanks https://stackoverflow.com/a/75398222
+        buffer = BytesIO()
+        epub.write_epub(buffer, self.epub)
+
+        buffer.seek(0)
+
+        return buffer
+
+
+class PDFGenerator:
+    """PDF Generation utilities"""
+
+    def __init__(self, data: Story, cover: bytes):
+        """Initialize PDGenerator, create PDF Temporary file."""
+        self.data = data
+        self.file = tempfile.NamedTemporaryFile(suffix=".pdf", delete=True)
+        self.cover = cover
+        self.content: str = ""
+        self.copyright = {
+            1: {
+                "name": "All Rights Reserved",
+                "statement": "©️ {published_year} by {username}. All Rights Reserved.",
+                "freedoms": "No reuse, redistribution, or modification without permission.",
+                "printing": "Not allowed without explicit permission.",
+                "image_url": None,
+            },
+            2: {
+                "name": "Public Domain",
+                "statement": "This work is in the public domain. Originally published in {published_year} by {username}.",
+                "freedoms": "Free to use for any purpose without permission.",
+                "printing": "Allowed for personal or commercial purposes.",
+                "image_url": "http://mirrors.creativecommons.org/presskit/buttons/88x31/png/cc-zero.png",
+            },
+            3: {
+                "name": "Creative Commons Attribution (CC-BY)",
+                "statement": "©️ {published_year} by {username}. This work is licensed under a Creative Commons Attribution 4.0 International License.",
+                "freedoms": "Allows reuse, redistribution, and modification with credit to the author.",
+                "printing": "Allowed with proper credit.",
+                "image_url": "https://mirrors.creativecommons.org/presskit/buttons/88x31/png/by.png",
+            },
+            4: {
+                "name": "CC Attribution NonCommercial (CC-BY-NC)",
+                "statement": "©️ {published_year} by {username}. This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.",
+                "freedoms": "Allows reuse and modification for non-commercial purposes with credit.",
+                "printing": "Allowed for non-commercial purposes with proper credit.",
+                "image_url": "http://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-nc.png",
+            },
+            5: {
+                "name": "CC Attribution NonCommercial NoDerivs (CC-BY-NC-ND)",
+                "statement": "©️ {published_year} by {username}. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License.",
+                "freedoms": "Allows sharing in original form for non-commercial purposes with credit; no modifications allowed.",
+                "printing": "Allowed for non-commercial purposes in original form with proper credit.",
+                "image_url": "http://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-nc-nd.png",
+            },
+            6: {
+                "name": "CC Attribution NonCommercial ShareAlike (CC-BY-NC-SA)",
+                "statement": "©️ {published_year} by {username}. This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.",
+                "freedoms": "Allows reuse and modification for non-commercial purposes under the same license, with credit.",
+                "printing": "Allowed for non-commercial purposes with proper credit under the same license.",
+                "image_url": "http://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-nc-sa.png",
+            },
+            7: {
+                "name": "CC Attribution ShareAlike (CC-BY-SA)",
+                "statement": "©️ {published_year} by {username}. This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.",
+                "freedoms": "Allows reuse and modification for any purpose under the same license, with credit.",
+                "printing": "Allowed with proper credit under the same license.",
+                "image_url": "https://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-sa.png",
+            },
+            8: {
+                "name": "CC Attribution NoDerivs (CC-BY-ND)",
+                "statement": "©️ {published_year} by {username}. This work is licensed under a Creative Commons Attribution-NoDerivs 4.0 International License.",
+                "freedoms": "Allows sharing in original form for any purpose with credit; no modifications allowed.",
+                "printing": "Allowed in original form with proper credit.",
+                "image_url": "https://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-nd.png",
+            },
+        }
+
+        with open("./pdf/stylesheet.css") as reader:
+            self.stylesheet = reader.read()
+        with open("./pdf/book.html") as reader:
+            self.template = reader.read()
+
+    async def generate_cover_and_copyright_html(
+        self,
+    ) -> str:
+        """Generate Cover and Copyright file, fetch copyright image (cached), use self.cover for cover."""
+
+        copyright_data = self.copyright[self.data["copyright"]]
+
+        template = self.template
+        about_copyright = (
+            template.replace(
+                "{statement}",
+                copyright_data["statement"].format(
+                    username=self.data["user"]["username"],
+                    published_year=self.data["createDate"].split("-", 2)[0],
+                ),
+            )
+            .replace("{author}", self.data["user"]["username"])
+            .replace("{freedoms}", copyright_data["freedoms"])
+            .replace(
+                "{printing}",
+                copyright_data["printing"],
+            )
+            .replace("{book_id}", self.data["id"])
+            .replace("{book_title}", self.data["title"])
+        )
+
+        copyright_image = (
+            await fetch_image(copyright_data["image_url"], should_cache=True)
+            if copyright_data["image_url"]
+            else None
+        )
+        image_block = (
+            """<img src="{image_url}" 
+alt="{name}" 
+width="88" 
+height="31" 
+id="copyright-license-image">""".format(
+                image_url=f"data:image/jpg;base64,{b64encode(copyright_image).decode()}",
+                name=copyright_data["name"],
+            )
+            if copyright_image
+            else ""
+        )
+        about_copyright = (
+            about_copyright.replace(
+                "{copyright_image}",
+                image_block,
+            )
+            if image_block
+            else about_copyright.replace("{copyright_image}", "")
+        )
+        about_copyright = about_copyright.replace(
+            "{cover}", f"data:image/jpg;base64,{b64encode(self.cover).decode()}"
+        )
+
+        self.template = about_copyright
+        return about_copyright
+
+    async def generate_about_author_chapter(self) -> str:
+        """Generate About the Author file, fetch avatar."""
+        author_avatar = (
+            await fetch_image(
+                self.data["user"]["avatar"].replace("128", "512")
+            )  # Increase image resolution
+            if self.data["user"]["avatar"]
+            else None
+        )
+        about_author = self.template.replace(
+            "{username}", self.data["user"]["username"]
+        ).replace("{description}", smart_trim(self.data["user"]["description"]))
+
+        about_author = (
+            about_author.replace(
+                "{avatar}",
+                f"""
+                <img src="data:image/jpg;base64,{b64encode(author_avatar).decode()}" alt="Author's profile picture" id="author-profile-picture">""",
+            )
+            if author_avatar
+            else about_author.replace("{avatar}", "")
+        )
+
+        self.template = about_author
+        return about_author
+
+    def generate_toc(self):
+        ids = [part["id"] for part in self.data["parts"]]
+        clean = BeautifulSoup(
+            """
+        <section id="contents" class="toc">
+        <h1>Table of Contents</h1>
+        <ul></ul>
+        </section>
+        """,
+            "html.parser",
+        )  # html.parser doesn't create <html>/<body> tags automatically
+
+        ul = cast(bs4.Tag, clean.find("ul"))
+        for part_id in ids:
+            li = clean.new_tag("li")
+            a = clean.new_tag("a")
+            a["href"] = f"#{part_id}"
+            li.append(a)
+            ul.append(li)
+
+        insert_point = cast(bs4.Tag, self.tree.find("div", {"id": "book"}))
+        insert_point.append(clean)
+        return str(clean)
+
+    async def add_chapters(
+        self, contents: List[bs4.Tag], download_images: bool = False
+    ):
+        """Add chapters to the PDF, downloading images if necessary. Also add Cover, Copyright, and About the Author pages."""
+
+        # # Cover and Copyright Page
+        await self.generate_cover_and_copyright_html()
+        await self.generate_about_author_chapter()
+        self.tree = BeautifulSoup(self.template, "lxml")
+
+        self.generate_toc()
+        for part, content in zip(self.data["parts"], contents):
+            insert_point = cast(bs4.Tag, self.tree.find("div", {"id": "book"}))
+            insert_point.append(content)
+
+            yield part["title"]
+
+        # # About the Author page
+        # about_author_html = await self.generate_about_author_chapter()
+
+        # chapters.insert(0, cover_and_copyright_html)
+        # chapters.append(about_author_html)
+
+        with start_action(
+            action_type="generate_pdf",
+            output_filename=self.file.name,
+            title=self.data["title"],
+        ):
+            # PDF Generation with wkhtmltopdf, written to self.file
+
+            # At this stage, we have a bunch of HTML Files representing all the chapters that need to be generated. PDFKit handles ToC generation, so that's not included.
+
+            font_config = FontConfiguration()
+
+            stylesheet_obj = CSS(string=self.stylesheet, font_config=font_config)
+
+            html_obj = HTML(string=str(self.tree))
+            html_obj.write_pdf(
+                self.file.name, stylesheets=[stylesheet_obj], font_config=font_config
+            )
+
+        with start_action(action_type="add_metadata") as action:
+            # Metadata generation with Exiftool
+            clean_description = (
+                self.data["description"].strip().replace("\n", "$/")
+            )  # exiftool doesn't parse \ns correctly, they support $/ for the same instead. `&#xa;` is another option.
+
+            action.log(f"clean_description: {clean_description}")
+
+            metadata = {
+                "Author": self.data["user"]["username"],
+                "Title": self.data["title"],
+                "Subject": clean_description,
+                "CreationDate": self.data["createDate"],
+                "ModDate": self.data["modifyDate"],
+                "Keywords": ",".join(self.data["tags"]),
+                "Language": self.data["language"]["name"],
+                "Completed": self.data["completed"],
+                "MatureContent": self.data["mature"],
+                "Producer": "Dhanush Rambhatla (TheOnlyWayUp - https://rambhat.la) and WattpadDownloader",
+            }  # As per https://exiftool.org/TagNames/PDF.html
+
+            action.log(f"options: {metadata}")
+
+            with ExifTool(
+                config_file="../exiftool.config", logger=exiftool_logger
+            ) as et:
+                # Custom configuration adds Completed and MatureContent tags.
+                # exiftool logger logs executed command
+                et.execute(
+                    *(
+                        [f"-{key}={value}" for key, value in metadata.items()]
+                        + [
+                            "-overwrite_original",
+                            self.file.file.name,
+                        ]
+                    )
+                )
+
+    def dump(self) -> BytesIO:
+        self.file.seek(0)
+        buffer = BytesIO(self.file.read())
+        self.file.close()
+
+        return buffer
+
+
+# ------ #

src/api/src/main.py

@@ -1,92 +1,216 @@
+"""WattpadDownloader API Server."""
+
 from typing import Optional
+import asyncio
 from pathlib import Path
-from fastapi import FastAPI, HTTPException
-from fastapi.responses import FileResponse, HTMLResponse, StreamingResponse
-from ebooklib import epub
-from create_book import (
-    retrieve_story,
-    set_cover,
-    set_metadata,
-    add_chapters,
-    slugify,
-    wp_get_cookies,
+from enum import Enum
+from zipfile import ZipFile
+from eliot import start_action
+from aiohttp import ClientResponseError
+from fastapi import FastAPI, Request
+from fastapi.responses import (
+    FileResponse,
+    HTMLResponse,
+    RedirectResponse,
+    StreamingResponse,
 )
-import tempfile
-from io import BytesIO
 from fastapi.staticfiles import StaticFiles
+from create_book import (
+    EPUBGenerator,
+    PDFGenerator,
+    fetch_story,
+    fetch_story_from_partId,
+    fetch_story_content_zip,
+    fetch_image,
+    fetch_cookies,
+    WattpadError,
+    StoryNotFoundError,
+    generate_clean_part_html,
+    slugify,
+    logger,
+)
+
 
 app = FastAPI()
 BUILD_PATH = Path(__file__).parent / "build"
 
+headers = {
+    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36"
+}
+
+
+class RequestCancelledMiddleware:
+    # Thanks https://github.com/fastapi/fastapi/discussions/11360#discussion-6427734
+    def __init__(self, app):
+        self.app = app
+
+    async def __call__(self, scope, receive, send):
+        if scope["type"] != "http":
+            await self.app(scope, receive, send)
+            return
+
+        # Let's make a shared queue for the request messages
+        queue = asyncio.Queue()
+
+        async def message_poller(sentinel, handler_task):
+            nonlocal queue
+            while True:
+                message = await receive()
+                if message["type"] == "http.disconnect":
+                    handler_task.cancel()
+                    return sentinel  # Break the loop
+
+                # Puts the message in the queue
+                await queue.put(message)
+
+        sentinel = object()
+        handler_task = asyncio.create_task(self.app(scope, queue.get, send))
+        asyncio.create_task(message_poller(sentinel, handler_task))
+
+        try:
+            return await handler_task
+        except asyncio.CancelledError:
+            logger.info("Cancelling task as connection closed")
+
+
+app.add_middleware(RequestCancelledMiddleware)
+
+
+class DownloadFormat(Enum):
+    pdf = "pdf"
+    epub = "epub"
+
+
+class DownloadMode(Enum):
+    story = "story"
+    part = "part"
+
 
 @app.get("/")
 def home():
     return FileResponse(BUILD_PATH / "index.html")
 
 
-@app.get("/download/{story_id}")
-async def download_book(
-    story_id: int,
+@app.exception_handler(ClientResponseError)
+def download_error_handler(request: Request, exception: ClientResponseError):
+    match exception.status:
+        case 400 | 404:
+            return HTMLResponse(
+                status_code=404,
+                content='This story does not exist, or has been deleted. Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
+            )
+        case 429:
+            # Rate-limit by Wattpad
+            return HTMLResponse(
+                status_code=429,
+                content='The website is overloaded. Please try again in a few minutes. Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
+            )
+        case _:
+            # Unhandled error
+            return HTMLResponse(
+                status_code=500,
+                content='Something went wrong. Yell at me on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
+            )
+
+
+@app.exception_handler(WattpadError)
+def download_wp_error_handler(request: Request, exception: WattpadError):
+    if isinstance(exception, StoryNotFoundError):
+        return HTMLResponse(
+            status_code=404,
+            content='This story does not exist, or has been deleted. Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
+        )
+
+
+@app.get("/download/{download_id}")
+async def handle_download(
+    download_id: int,
     download_images: bool = False,
+    mode: DownloadMode = DownloadMode.story,
+    format: DownloadFormat = DownloadFormat.epub,
     username: Optional[str] = None,
     password: Optional[str] = None,
 ):
-    if username and not password or password and not username:
-        return HTMLResponse(
-            status_code=422,
-            content='Include both the username _and_ password, or neither. Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
-        )
-
-    if username and password:
-        try:
-            cookies = await wp_get_cookies(username=username, password=password)
-        except ValueError:
-            return HTMLResponse(
-                status_code=403,
-                content='Incorrect Username and/or Password. Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
-            )
-    else:
-        cookies = None
-
-    data = await retrieve_story(story_id, cookies=cookies)
-    book = epub.EpubBook()
-
-    try:
-        set_metadata(book, data)
-    except KeyError:
-        return HTMLResponse(
-            status_code=404,
-            content='Story not found. Check the ID - Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
-        )
-
-    await set_cover(book, data, cookies=cookies)
-    # print("Metadata Downloaded")
-
-    # Chapters are downloaded
-    async for title in add_chapters(
-        book, data, download_images=download_images, cookies=cookies
+    with start_action(
+        action_type="download",
+        download_id=download_id,
+        download_images=download_images,
+        format=format,
+        mode=mode,
     ):
-        # print(f"Part ({title}) downloaded")
-        ...
+        if username and not password or password and not username:
+            logger.error(
+                "Username with no Password or Password with no Username provided."
+            )
+            return HTMLResponse(
+                status_code=422,
+                content='Include both the username <u>and</u> password, or neither. Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
+            )
 
-    # Book is compiled
-    temp_file = tempfile.NamedTemporaryFile(
-        suffix=".epub", delete=True
-    )  # Thanks https://stackoverflow.com/a/75398222
+        if username and password:
+            # username and password are URL-Encoded by the frontend. FastAPI automatically decodes them.
+            try:
+                cookies = await fetch_cookies(username=username, password=password)
+            except ValueError:
+                logger.error("Invalid username or password.")
+                return HTMLResponse(
+                    status_code=403,
+                    content='Incorrect Username and/or Password. Support is available on the <a href="https://discord.gg/P9RHC4KCwd" target="_blank">Discord</a>',
+                )
+        else:
+            cookies = None
 
-    # create epub file
-    epub.write_epub(temp_file, book, {})
+        match mode:
+            case DownloadMode.story:
+                story_id = download_id
+                metadata = await fetch_story(story_id, cookies)
+            case DownloadMode.part:
+                story_id, metadata = await fetch_story_from_partId(download_id, cookies)
 
-    temp_file.file.seek(0)
-    book_data = temp_file.file.read()
+        cover_data = await fetch_image(
+            metadata["cover"].replace("-256-", "-512-")
+        )  # Increase resolution
 
-    return StreamingResponse(
-        BytesIO(book_data),
-        media_type="application/epub+zip",
-        headers={
-            "Content-Disposition": f'attachment; filename="{slugify(data["title"])}_{story_id}_{"images" if download_images else ""}.epub"'  # Thanks https://stackoverflow.com/a/72729058
-        },
-    )
+        match format:
+            case DownloadFormat.epub:
+                book = EPUBGenerator(metadata, cover_data)
+                media_type = "application/epub+zip"
+            case DownloadFormat.pdf:
+                book = PDFGenerator(metadata, cover_data)
+                media_type = "application/pdf"
+
+        logger.info(f"Retrieved story metadata and cover ({story_id=})")
+
+        story_zip = await fetch_story_content_zip(story_id, cookies)
+        archive = ZipFile(story_zip, "r")
+
+        part_contents = [
+            generate_clean_part_html(
+                part, archive.read(str(part["id"])).decode("utf-8")
+            )
+            for part in metadata["parts"]
+        ]
+
+        async for title in book.add_chapters(
+            part_contents, download_images=download_images
+        ):
+            ...
+
+        book_buffer = book.dump()
+
+        return StreamingResponse(
+            book_buffer,
+            media_type=media_type,
+            headers={
+                "Content-Disposition": f'attachment; filename="{slugify(metadata["title"])}_{story_id}{"_images" if download_images else ""}.{format.value}"'  # Thanks https://stackoverflow.com/a/72729058
+            },
+        )
+
+
+@app.get("/donate")
+def donate():
+    """Redirect to donation URL."""
+    return RedirectResponse("https://buymeacoffee.com/theonlywayup")
 
 
 app.mount("/", StaticFiles(directory=BUILD_PATH), "static")
@@ -95,4 +219,4 @@ app.mount("/", StaticFiles(directory=BUILD_PATH), "static")
 if __name__ == "__main__":
     import uvicorn
 
-    uvicorn.run(app, host="0.0.0.0", port=80)
+    uvicorn.run("main:app", host="0.0.0.0", port=80, workers=16)

src/api/src/pdf/book.html

@@ -0,0 +1,54 @@
+<!DOCTYPE html>
+<html lang="{langcode}">
+
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    
+    <title>{book_title}</title>
+
+    <section class="fullpage">
+        <img src="{cover}" alt="Cover">
+      </section>
+
+      <div id="copyright-container">
+        <h1 id="copyright-notice">Copyright Notice</h1>
+        
+        <h2 id="copyright-title">{book_title}</h2>
+        <p id="copyright-author">By {author}</p>
+
+        <div id="copyright-separator"></div>
+        
+        <p id="copyright-ex-libris">Ex Libris Sapientiae</p>
+        
+        <div id="copyright-separator"></div>
+
+        {copyright_image}
+        
+        <p id="copyright-copyright">{statement}</p>
+        
+        <p id="copyright-rights">{freedoms}</p>
+        
+        <p id="copyright-printing">Printing: {printing}</p>
+
+        <p id="copyright-printing">ID: {book_id}. <a href="https://wattpad.com/story/{book_id}" target="_blank" id="copyright-link">View this Book Online</a></p>
+        
+        
+
+    </div>
+
+    <div id="book">
+
+    </div>
+
+    <h1>About the Author</h1>
+    <div id="author-container">
+        <div id="author-about">
+            {avatar}
+            <h2 id="author-name"><a href="https://wattpad.com/user/{username}" id="author-link">{username}</a></h2>
+            <hr id="author-divider">
+            <p id="author-bio">
+                {description}
+            </p>
+        </div>
+    </div>
+</html>

src/api/src/pdf/fonts/OFL.txt

@@ -0,0 +1,94 @@
+Copyright (c) 2010, ParaType Ltd. (http://www.paratype.com/public),
+with Reserved Font Names "PT Sans", "PT Serif" and "ParaType".
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+https://openfontlicense.org
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded, 
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

src/api/src/pdf/stylesheet.css

@@ -0,0 +1,420 @@
+@font-face {
+  font-family: 'PT Serif';
+  src: url('/tmp/fonts/PTSerif-Regular.ttf') format('truetype');
+  font-weight: 400;
+  font-style: normal;
+}
+
+@font-face {
+  font-family: 'PT Serif';
+  src: url('/tmp/fonts/PTSerif-Bold.ttf') format('truetype');
+  font-weight: 700;
+  font-style: normal;
+}
+
+@font-face {
+  font-family: 'PT Serif';
+  src: url('/tmp/fonts/PTSerif-Italic.ttf') format('truetype');
+  font-weight: 400;
+  font-style: italic;
+}
+
+@font-face {
+  font-family: 'PT Serif';
+  src: url('/tmp/fonts/PTSerif-BoldItalic.ttf') format('truetype');
+  font-weight: 700;
+  font-style: italic;
+}
+
+.pt-serif-regular {
+  font-family: "PT Serif", serif;
+  font-weight: 400;
+  font-style: normal;
+}
+
+.pt-serif-bold {
+  font-family: "PT Serif", serif;
+  font-weight: 700;
+  font-style: normal;
+}
+
+.pt-serif-regular-italic {
+  font-family: "PT Serif", serif;
+  font-weight: 400;
+  font-style: italic;
+}
+
+.pt-serif-bold-italic {
+  font-family: "PT Serif", serif;
+  font-weight: 700;
+  font-style: italic;
+}
+
+
+
+
+
+@page {
+  margin: 2cm 2cm 3cm 2cm;
+  size: 148mm 210mm;
+}
+
+@page :left {
+  @bottom-left {
+    content: counter(page);
+    position: absolute;
+    z-index: -1;
+  }
+  @bottom-right {
+    content: string(heading);
+    position: absolute;
+    z-index: -1;
+  }
+}
+
+@page :right {
+  @bottom-left {
+    content: string(heading);
+    position: absolute;
+    z-index: -1;
+  }
+  @bottom-right {
+    content: counter(page);
+    position: absolute;
+    z-index: -1;
+  }
+}
+
+@page full {
+  @bottom-right {
+    content: none;
+  }
+
+  @bottom-left {
+    content: none;
+  }
+
+  background: black;
+  margin: 0;
+}
+
+@page :blank {
+  @bottom-right {
+    content: none;
+  }
+
+  @bottom-left {
+    content: none;
+  }
+}
+
+@page clean {
+  @bottom-right {
+    content: none;
+  }
+
+  @bottom-left {
+    content: none;
+  }
+}
+
+html {
+  counter-reset: h2-counter;
+  font-size: 10pt;
+}
+body {
+  margin: 0;
+}
+
+p {
+  line-height: 2;
+  text-align: justify;
+}
+img {
+  display: block;
+  margin: 2em auto;
+  max-width: 70%;
+}
+
+
+#contents {
+  border-bottom: 1px dashed rgb(100,000,100);
+  h2 {
+    font-family: "PT Serif", serif;
+    font-weight: 400;
+    font-style: normal;
+  }
+  padding-top: 5px;
+}
+
+.chapter-title {
+  counter-increment: h2-counter;
+  display: flex;
+  flex-direction: column;
+  font-size: 3em;
+  height: 6cm;
+  justify-content: flex-end;
+  margin: 0;
+  string-set: heading content();
+  text-align: center;
+
+  font-family: "PT Serif", serif;
+  font-weight: 700;
+  font-style: normal !important;
+  font-size: 36px !important; /* Uniform size */
+  margin-bottom: 20px; /* Space below the heading */
+  border-bottom: 2px solid rgb(100, 100, 100); /* Black line */
+  padding-bottom: 10px; /* Space between text and line */
+}
+
+
+p {
+  font-size: 16px !important; /* Standardize paragraph size */
+  line-height: 1.6 !important; /* Improve readability */
+  margin: 10px 0 !important; /* Space between paragraphs */
+}
+
+.chapter-title::before {
+  content: "Chapter " counter(h2-counter) " ";
+  display: block;
+  font-size: 1.2rem;
+  font-weight: normal;
+  line-height: 1;
+}
+
+section {
+  break-after: right;
+}
+
+
+
+#contents {
+  page: clean;
+}
+#contents p {
+  font-size: 2em;
+}
+#contents ul {
+  display: block;
+  margin: 1em 0;
+  padding: 0;
+}
+#contents li {
+  display: block;
+}
+#contents a {
+  color: inherit;
+  text-decoration: none;
+  display: flex;
+  justify-content: space-between;
+}
+#contents a::before {
+  content: target-counter(attr(href), h2-counter) '. ' target-text(attr(href));
+  width: 100%;
+}
+#contents a::after {
+  content: target-counter(attr(href), page);
+  text-align: end;
+}
+
+.outro {
+  border-radius: 50% 50% 0 0 / 15mm 15mm 0 0;
+  display: block;
+  height: 90mm;
+  left: -30mm;
+  max-width: none;
+  object-fit: cover;
+  position: absolute;
+  top: 120mm;
+  width: 168mm;
+  z-index: -1;
+}
+
+.fullpage {
+  page: full;
+}
+.fullpage img {
+  bottom: 0;
+  height: 210mm;
+  left: 0;
+  margin: 0;
+  max-width: none;
+  object-fit: cover;
+  position: absolute;
+  width: 148mm;
+  z-index: 1;
+}
+.fullpage:last-child {
+  break-before: left;
+}
+
+a {
+  font-size: 0.9rem;
+  color: #3182ce;
+  text-decoration: none;
+  display: inline-block;
+  margin-top: 1rem;
+  
+  /* Cross-browser transition */
+  -webkit-transition: all 0.2s ease;
+  -moz-transition: all 0.2s ease;
+  -o-transition: all 0.2s ease;
+  transition: all 0.2s ease;
+}
+
+a:hover {
+  text-decoration: underline;
+  color: #2c5282;
+}
+
+
+/* Container centering for older browsers */
+#author-container {
+  position: absolute;
+  top: 50%;
+  left: 50%;
+  -webkit-transform: translate(-50%, -50%); /* Old WebKit */
+  transform: translate(-50%, -50%);
+  width: 90%;
+  max-width: 400px;
+  text-align: center;
+  }
+  
+  #author-about {
+  padding: 20px;
+  /* Fallback for older browsers */
+  display: block;
+  margin: 0 auto;
+  }
+  
+  #author-profile-picture {
+  width: 200px;
+  height: 200px;
+  -webkit-border-radius: 100px; /* Old WebKit */
+  border-radius: 100px;
+  margin: 0 auto 20px auto;
+  display: block;
+  }
+  
+  #author-name {
+  font-size: 24px;
+  font-weight: bold;
+  margin: 0 0 10px 0;
+  padding: 0;
+  }
+  
+  #author-link {
+  color: #1a202c;
+  text-decoration: none;
+  }
+  
+  #author-link:hover {
+  color: #4a5568;
+  text-decoration: underline;
+  }
+  
+  #author-divider {
+  width: 60px;
+  height: 2px;
+  background-color: #d1d5db;
+  border: none;
+  margin: 0 auto 20px auto;
+  }
+  
+  #author-bio {
+  color: #4b5563;
+  line-height: 1.6;
+  margin: 0;
+  padding: 0;
+  }
+
+#copyright-container {
+    max-width: 600px;
+    margin: 60px auto;
+    text-align: center !important;
+    font-family: Georgia, serif !important;
+    line-height: 1.6 !important;
+    color: #333 !important;
+}
+
+#copyright-notice {
+    font-size: 24px;
+    margin-bottom: 4px;
+    border-bottom: 1px solid #333;
+    padding-bottom: 8px;
+    color: #1a1a1a;
+}
+
+#copyright-title {
+    font-size: 28px;
+    margin: 24px 0 4px 0;
+    color: #1a1a1a;
+}
+
+#copyright-author {
+    font-size: 18px;
+    margin: 0 0 32px 0;
+    color: #444;
+    text-align: center;
+}
+
+#copyright-license-image {
+    margin: 20px 0;
+    width: 88px;
+    height: 31px;
+
+    display: block;
+    margin-left: auto;
+    margin-right: auto;
+}
+
+#copyright-copyright {
+    font-size: 16px;
+    margin: 16px 0;
+    text-align: center;
+
+}
+
+#copyright-rights {
+    font-size: 14px;
+    color: #666;
+    margin: 8px 0;
+    text-align: center;
+
+}
+
+#copyright-printing {
+    font-size: 14px;
+    color: #666;
+    margin: 8px 0;
+    text-align: center;
+
+}
+
+#copyright-separator {
+  width: 100%;
+  max-width: 400px;
+  height: 1px;
+  background: #e2e8f0;
+  position: relative;
+  margin: 2rem 1rem;
+  
+  /* Gradient fallback */
+  background: -webkit-gradient(linear, left top, right top, from(transparent), color-stop(#718096), to(transparent));
+  background: -webkit-linear-gradient(left, transparent, #718096, transparent);
+  background: -moz-linear-gradient(left, transparent, #718096, transparent);
+  background: -o-linear-gradient(left, transparent, #718096, transparent);
+  background: linear-gradient(to right, transparent, #718096, transparent);
+}
+
+#copyright-ex-libris {
+  font-size: 1.5rem;
+  font-style: italic;
+  color: #4a5568;
+  margin: 2rem 0;
+  text-align: center;
+}
+
+#copyright-link { 
+  font-size: 14px;
+}

src/api/src/pdf/toc.xsl

@@ -0,0 +1,120 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet version="2.0"
+                xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                xmlns:outline="http://wkhtmltopdf.org/outline"
+                xmlns="http://www.w3.org/1999/xhtml">
+  <xsl:output doctype-public="-//W3C//DTD XHTML 1.0 Strict//EN"
+              doctype-system="http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"
+              indent="yes" />
+  <xsl:template match="outline:outline">
+    <html>
+      <head>
+<style>
+@font-face {
+  font-family: 'PT Serif';
+  src: url('./fonts/PTSerif-Regular.ttf') format('truetype');
+  font-weight: 400;
+  font-style: normal;
+}
+
+@font-face {
+  font-family: 'PT Serif';
+  src: url('./fonts/PTSerif-Bold.ttf') format('truetype');
+  font-weight: 700;
+  font-style: normal;
+}
+
+@font-face {
+  font-family: 'PT Serif';
+  src: url('./fonts/PTSerif-Italic.ttf') format('truetype');
+  font-weight: 400;
+  font-style: italic;
+}
+
+@font-face {
+  font-family: 'PT Serif';
+  src: url('./fonts/PTSerif-BoldItalic.ttf') format('truetype');
+  font-weight: 700;
+  font-style: italic;
+}
+
+.pt-serif-regular {
+  font-family: "PT Serif", serif;
+  font-weight: 400;
+  font-style: normal;
+}
+
+.pt-serif-bold {
+  font-family: "PT Serif", serif;
+  font-weight: 700;
+  font-style: normal;
+}
+
+.pt-serif-regular-italic {
+  font-family: "PT Serif", serif;
+  font-weight: 400;
+  font-style: italic;
+}
+
+.pt-serif-bold-italic {
+  font-family: "PT Serif", serif;
+  font-weight: 700;
+  font-style: italic;
+}
+
+
+h1 {
+  text-align: center;
+  font-family: "PT Serif", serif !important;
+  font-weight: 700 !important;
+  font-style: normal !important;
+  font-size: 36px !important; /* Uniform size */
+  margin-bottom: 20px; /* Space below the heading */
+  border-bottom: 4px solid black; /* Black line */
+  padding-bottom: 10px; /* Space between text and line */
+}
+
+
+          div {border-bottom: 1px dashed rgb(100,000,100);
+          padding-top: 5px;}
+          span {float: right;}
+          li {list-style: none;}
+          ul {
+            font-size: 22px;
+            font-family: arial;
+          }
+          ul ul {font-size: 80%; }
+          ul {padding-left: 0em;}
+          ul ul {padding-left: 1em;}
+          a {text-decoration:none; color: black;}
+        </style>
+      </head>
+      <body>
+        <h1>Table of Contents</h1>
+        <ul><xsl:apply-templates select="outline:item/outline:item"/></ul>
+      </body>
+    </html>
+  </xsl:template>
+  <xsl:template match="outline:item">
+    <li>
+      <xsl:if test="@title!=''">
+        <div>
+          <a class="pt-serif-regular">
+            <xsl:if test="@link">
+              <xsl:attribute name="href"><xsl:value-of select="@link"/></xsl:attribute>
+            </xsl:if>
+            <xsl:if test="@backLink">
+              <xsl:attribute name="name"><xsl:value-of select="@backLink"/></xsl:attribute>
+            </xsl:if>
+            <xsl:value-of select="@title" /> 
+          </a>
+          <span> <xsl:value-of select="@page" /> </span>
+        </div>
+      </xsl:if>
+      <ul>
+        <xsl:comment>added to prevent self-closing tags in QtXmlPatterns</xsl:comment>
+        <xsl:apply-templates select="outline:item"/>
+      </ul>
+    </li>
+  </xsl:template>
+</xsl:stylesheet>

src/frontend/src/app.html

@@ -7,26 +7,24 @@
 
 		<title>Wattpad Downloader</title>
 		<meta name="title" content="Wattpad Downloader" />
-		<meta name="description" content="Read your way, download Wattpad Books as EPUBs in seconds. Have an Ad-Free experience with Unlimited Offline Reading. Try it now!" />
+		<meta name="description" content="Read your way, download Wattpad Books as PDFs or EPUBs in seconds. Have an Ad-Free experience with Unlimited Offline Reading. Try it now!" />
 
 		<!-- Open Graph / Facebook -->
 		<meta property="og:type" content="website" />
 		<meta property="og:url" content="https://wpd.rambhat.la/" />
 		<meta property="og:title" content="Wattpad Downloader" />
-		<meta property="og:description" content="Read your way, download Wattpad Books as EPUBs in seconds. Have an Ad-Free experience with Unlimited Offline Reading. Try it now!" />
+		<meta property="og:description" content="Read your way, download Wattpad Books as PDFs or EPUBs in seconds. Have an Ad-Free experience with Unlimited Offline Reading. Try it now!" />
 		<meta property="og:image" content="https://wpd.rambhat.la/embed.png" />
 
 		<!-- Twitter -->
 		<meta property="twitter:card" content="summary_large_image" />
 		<meta property="twitter:url" content="https://wpd.rambhat.la/" />
 		<meta property="twitter:title" content="Wattpad Downloader" />
-		<meta property="twitter:description" content="Read your way, download Wattpad Books as EPUBs in seconds. Have an Ad-Free experience with Unlimited Offline Reading. Try it now!" />
+		<meta property="twitter:description" content="Read your way, download Wattpad Books as PDFs or EPUBs in seconds. Have an Ad-Free experience with Unlimited Offline Reading. Try it now!" />
 		<meta property="twitter:image" content="https://wpd.rambhat.la/embed.png" />
 
 		<!-- Meta Tags Generated with https://metatags.io -->
 
-		<script defer src="https://feedback.fish/ff.js?pid=f8df016d4ffdfb"></script>
-
 		%sveltekit.head%		  
 	</head>
 	<body data-sveltekit-preload-data="hover">

src/frontend/src/routes/+layout.svelte

@@ -16,17 +16,17 @@
   class="footer footer-center p-4 bg-base-300 text-base-content bottom-0 fixed"
 >
   <aside>
-    <div class="grid grid-cols-3 max-w-lg w-full">
+    <div class="flex flex-row max-w-lg w-full">
       <a
-        href="https://liberapay.com/TheOnlyWayUp/"
+        href="/donate"
         target="_blank"
         class="link"
-        data-umami-event="Footer Donate">Donate</a
+        data-umami-event="Footer Donate">Buy me a Coffee!</a
       >
       <a
         href="https://rambhat.la"
         target="_blank"
-        class="link"
+        class="link flex-1"
         data-umami-event="Footer AboutMe">About Me</a
       >
       <a

src/frontend/src/routes/+page.svelte

@@ -1,32 +1,92 @@
 <script>
-  let story_id = "";
   let download_images = false;
+  let download_as_pdf = false; // 0 = epub, 1 = pdf
   let is_paid_story = false;
+  let invalid_url = false;
+  let after_download_page = false;
   let credentials = {
     username: "",
     password: "",
   };
-
-  let after_download_page = false;
-  let url = "";
+  let download_id = "";
+  let mode = "";
+  let input_url = "";
 
   let button_disabled = false;
   $: button_disabled =
-    !story_id ||
+    !input_url ||
     (is_paid_story && !(credentials.username && credentials.password));
 
   $: url =
-    `/download/${story_id}?om=1` +
+    `/download/` +
+    download_id +
+    `?om=1` +
     (download_images ? "&download_images=true" : "") +
     (is_paid_story
-      ? `&username=${credentials.username}&password=${credentials.password}`
-      : "");
+      ? `&username=${encodeURIComponent(credentials.username)}&password=${encodeURIComponent(credentials.password)}`
+      : "") +
+    `&mode=${mode}` +
+    (download_as_pdf ? "&format=pdf" : "&format=epub");
+
+  $: {
+    if (input_url.length) {
+      input_url = input_url.toLowerCase();
+
+      invalid_url = false;
+
+      if (/^\d+$/.test(input_url)) {
+        // All numbers
+        download_id = input_url;
+        mode = "story";
+      } else if (input_url.includes("wattpad.com/")) {
+        // Is a string and contains contain wattpad.com/
+
+        if (input_url.includes("/story/")) {
+          // https://wattpad.com/story/237369078-wattpad-books-presents
+          input_url = input_url.split("-")[0].split("?")[0].split("/story/")[1]; // removes tracking fields and title
+          download_id = input_url;
+          mode = "story";
+        } else if (input_url.includes("/stories/")) {
+          // https://www.wattpad.com/api/v3/stories/237369078?fields=...
+          input_url = input_url.split("?")[0].split("/stories/")[1]; // removes params
+          download_id = input_url;
+          mode = "story";
+        } else {
+          // https://www.wattpad.com/939051741-wattpad-books-presents-the-qb-bad-boy-and-me
+          input_url = input_url
+            .split("-")[0]
+            .split("?")[0]
+            .split("wattpad.com/")[1]; // removes tracking fields and title
+          download_id = input_url;
+          if (/^\d+$/.test(download_id)) {
+            // If "wattpad.com/{download_id}" contains only numbers
+            mode = "part";
+          } else {
+            invalid_url = true;
+            input_url = "";
+            download_id = "";
+          }
+        }
+      } else {
+        invalid_url = true;
+      }
+
+      input_url = input_url.match(/\d+/g)?.join("") || "";
+      download_id = input_url;
+
+      // Originally, I was going to call the Wattpad API (wattpad.com/api/v3/stories/${story_id}), but Wattpad kept blocking those requests. I suspect it has something to do with the Origin header, I wasn't able to remove it.
+      // In the future, if this is considered, it would be cool if we could derive the Story ID from a pasted Part URL. Refer to @AaronBenDaniel's https://github.com/AaronBenDaniel/WattpadDownloader/blob/49b29b245188149f2d24c0b1c59e4c7f90f289a9/src/api/src/create_book.py#L156 (https://www.wattpad.com/api/v3/story_parts/{part_id}?fields=url).
+    } else {
+      invalid_url = false;
+      download_id = "";
+    }
+  }
 </script>
 
 <div>
   <div class="hero min-h-screen">
     <div
-      class="hero-content flex-col lg:flex-row-reverse bg-base-100/50 p-16 rounded shadow-sm"
+      class="hero-content flex-col lg:flex-row-reverse bg-base-100/50 lg:p-16 py-32 rounded shadow-sm"
     >
       {#if !after_download_page}
         <div class="text-center lg:text-left lg:p-10">
@@ -35,32 +95,78 @@
           >
             Wattpad Downloader
           </h1>
+          <!-- <div role="alert" class="alert bg-cyan-300 mt-5">
+            <svg
+              xmlns="http://www.w3.org/2000/svg"
+              fill="none"
+              viewBox="0 0 24 24"
+              class="h-6 w-6 shrink-0 stroke-current"
+            >
+              <path
+                stroke-linecap="round"
+                stroke-linejoin="round"
+                stroke-width="2"
+                d="M13 16h-1v-4h-1m1-4h.01M21 12a9 9 0 11-18 0 9 9 0 0118 0z"
+              ></path>
+            </svg>
+            <span class="text-lg">Please Donate</span>
+          </div> -->
           <p class="pt-6 text-lg">
             Download your favourite books with a single click!
           </p>
           <ul class="pt-4 list list-inside text-xl">
-            <li>06/24 - 🎉 Image Downloading!</li>
+            <!-- TODO: 'max-lg: hidden' to hide on screen sizes smaller than lg. I'll do this when I figure out how to make this show up _below_ the card on smaller screen sizes. -->
+            <li>12/24 - ⚡ Super-fast Downloads!</li>
+            <li>12/24 - 📑 PDF Downloads!</li>
+            <li>12/24 - 📂 Improved Performance</li>
+            <li>11/24 - 🔗 Paste Links!</li>
+            <li>11/24 - 📨 Send to Kindle Support!</li>
+
+            <li>11/24 - ⚒️ Fix Image Downloads</li>
+            <li>
+              10/24 - 👾 Add the <a
+                href="https://discord.com/oauth2/authorize?client_id=1292173380065296395&permissions=274878285888&scope=bot%20applications.commands"
+                target="_blank"
+                class="link underline">Discord Bot</a
+              >!
+            </li>
+            <li>07/24 - 🔡 RTL Language support! (Arabic, etc.)</li>
+            <li>06/24 - 🔑 Authenticated Downloads!</li>
+            <li>06/24 - 🖼️ Image Downloading!</li>
           </ul>
         </div>
         <div class="card shrink-0 w-full max-w-sm shadow-2xl bg-base-100">
           <form class="card-body">
             <div class="form-control">
               <input
-                type="number"
-                placeholder="Story ID"
+                type="text"
+                placeholder="Story URL"
                 class="input input-bordered"
-                bind:value={story_id}
+                class:input-warning={invalid_url}
+                bind:value={input_url}
                 required
-                name="story_id"
+                name="input_url"
               />
-              <label class="label" for="story_id">
-                <button
-                  class="label-text link font-semibold"
-                  onclick="StoryIDTutorialModal.showModal()"
-                  data-umami-event="StoryIDTutorialModal Open"
-                  >How to get a Story ID</button
-                >
+              <label class="label" for="input_url">
+                {#if invalid_url}
+                  <p class=" text-red-500">
+                    Refer to (<button
+                      class="link font-semibold"
+                      onclick="StoryURLTutorialModal.showModal()"
+                      data-umami-event="Part StoryURLTutorialModal Open"
+                      >How to get a Story URL</button
+                    >).
+                  </p>
+                {:else}
+                  <button
+                    class="label-text link font-semibold"
+                    onclick="StoryURLTutorialModal.showModal()"
+                    data-umami-event="StoryURLTutorialModal Open"
+                    >How to get a Story URL</button
+                  >
+                {/if}
               </label>
+
               <label class="cursor-pointer label">
                 <span class="label-text"
                   >This is a Paid Story, and I've purchased it</span
@@ -99,13 +205,25 @@
 
             <div class="form-control mt-6">
               <a
-                class="btn btn-primary rounded-l-none"
+                class="btn rounded-l-none"
+                class:btn-primary={!download_as_pdf}
+                class:btn-secondary={download_as_pdf}
                 class:btn-disabled={button_disabled}
                 data-umami-event="Download"
                 href={url}
                 on:click={() => (after_download_page = true)}>Download</a
               >
 
+              <label class="swap w-fit label mt-2">
+                <input type="checkbox" bind:checked={download_as_pdf} />
+                <div class="swap-on">
+                  Downloading as <span class=" underline text-bold">PDF</span> (Click)
+                </div>
+                <div class="swap-off">
+                  Downloading as <span class=" underline text-bold">EPUB</span> (Click)
+                </div>
+              </label>
+
               <label class="cursor-pointer label">
                 <span class="label-text"
                   >Include Images (<strong>Slower Download</strong>)</span
@@ -151,7 +269,21 @@
               >, where we release features early and discuss updates.
             </p>
           </div>
-          <a href="/" class="btn btn-outline btn-lg mt-10">Download More</a>
+          <div class="grid justify-center grid-rows-2 gap-y-10">
+            <a
+              href="/donate"
+              target="_blank"
+              class="btn bg-cyan-200 btn-lg mt-10 hover:bg-green-200"
+              >Buy me a Coffee! 🍵</a
+            >
+            <button
+              on:click={() => {
+                after_download_page = false;
+                input_url = "";
+              }}
+              class="btn btn-outline btn-lg">Download More</button
+            >
+          </div>
         </div>
       {/if}
     </div>
@@ -160,32 +292,31 @@
 
 <!-- Open the modal using ID.showModal() method -->
 
-<dialog id="StoryIDTutorialModal" class="modal">
+<dialog id="StoryURLTutorialModal" class="modal">
   <div class="modal-box">
     <form method="dialog">
       <button class="btn btn-sm btn-circle btn-ghost absolute right-2 top-2"
         >✕</button
       >
     </form>
-    <h3 class="font-bold text-lg">Downloading a Story</h3>
-    <ol class="list list-disc list-inside py-4 space-y-2">
+    <h3 class="font-bold text-lg">Finding the Story URL</h3>
+    <ol class="list list-disc list-inside py-4 space-y-4">
       <li>
-        Open the Story URL (For example, <span
-          class="font-mono bg-slate-100 p-1"
-          >wattpad.com/story/237369078-wattpad-books-presents</span
-        >)
+        Copy the URL from the Website, or hit share and copy the URL on the App.
       </li>
       <li>
-        Copy the numbers after the <span class="font-mono bg-slate-100 p-1"
-          >/</span
-        >
-        (In the example, that'd be,
+        For example,
         <span class="font-mono bg-slate-100 p-1"
-          >wattpad.com/story/<span class="bg-amber-200 p-1">237369078</span
-          >-wattpad-books-presents</span
-        >)
+          >wattpad.com/<span class="bg-amber-200 rounded-sm">story</span
+          >/237369078-wattpad-books-presents</span
+        >.
       </li>
-      <li>Paste the Story ID and hit Download!</li>
+      <li>
+        <span class="font-mono bg-slate-100 p-1"
+          >https://www.wattpad.com/939103774-given</span
+        > is okay too.
+      </li>
+      <li>Paste the URL and hit Download!</li>
     </ol>
   </div>
   <form method="dialog" class="modal-backdrop">