Last active
August 16, 2024 21:31
-
-
Save 3nws/b56ef98ca2836ee4c21225351e0f66ca to your computer and use it in GitHub Desktop.
Hastily written script to retrieve the latest chapter from witchculttranslation.com and convert it to an epub file and upload to dropbox
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import html5lib # type: ignore | |
import requests | |
import os | |
import dropbox | |
from ebooklib import epub | |
from bs4 import BeautifulSoup | |
from config import app_folder, app_key, app_secret, oauth2_refresh_token | |
session = requests.session() | |
dbx = dropbox.Dropbox( | |
app_key=app_key, | |
app_secret=app_secret, | |
oauth2_refresh_token=oauth2_refresh_token | |
) | |
try: | |
dbx.files_get_metadata(app_folder) | |
except dropbox.exceptions.ApiError as e: | |
if type(e.error) == dropbox.files.GetMetadataError: | |
dbx.files_create_folder(app_folder) | |
arc = 9 | |
chapters_url = f"https://witchculttranslation.com/arc-{arc}/" | |
def upload_to_dbox(epub_file_name): | |
with open(epub_file_name, "rb",) as f: | |
dbx.files_upload(f.read(), f"{app_folder}/{epub_file_name}") | |
def create_epub(title, url, content, images, cover_url=None): | |
book = epub.EpubBook() | |
cover = session.get(cover_url, stream=True) | |
chapter_slug = list(filter(None, url.split("/")))[-1] | |
chapter_id = chapter_slug | |
chapter_title = title | |
book.set_identifier(chapter_id) | |
book.set_title(chapter_title) | |
book.set_language("en") | |
book.set_cover("image.jpg", (cover.content)) | |
del cover | |
spine = [] | |
chapter = epub.EpubHtml(title=chapter_title, file_name=f"{chapter_slug}.xhtml", lang="en", content=content) | |
book.add_item(chapter) | |
spine.append(chapter) | |
for idx, image in enumerate(images): | |
image_content = open(image, "rb").read() | |
img = epub.EpubImage( | |
uid=f"image_{idx}", | |
file_name=image, | |
content=image_content, | |
) | |
book.add_item(img) | |
os.remove(image) | |
book.add_item(epub.EpubNcx()) | |
book.add_item(epub.EpubNav()) | |
style = "BODY {color: white;}" | |
nav_css = epub.EpubItem( | |
uid="style_nav", | |
file_name="style/nav.css", | |
media_type="text/css", | |
content=style, | |
) | |
book.add_item(nav_css) | |
book.spine = ["nav", *spine] | |
epub_file_name = f"Re: Zero Web Novel Arc {arc} - {chapter_title}.epub".replace(":", "") | |
epub.write_epub(epub_file_name, book, {}) | |
upload_to_dbox(epub_file_name) | |
def get_entry_content(url): | |
res = session.get(url) | |
if res.status_code != 200: | |
return | |
page = res.content | |
soup = BeautifulSoup(page.decode("utf-8"), "html5lib") | |
return soup.select_one(".entry-content") | |
def main(): | |
entry_content = get_entry_content(chapters_url) | |
chapters = entry_content.select("li") | |
latest_chapter = chapters[-1] | |
a_tag = latest_chapter.findChild() | |
chapter_url = a_tag.get("href") | |
chapter_title = a_tag.text | |
filename = './latest_chapter.txt' | |
if not os.path.exists(filename): | |
open(filename, 'w').close() | |
with open(filename, 'r+') as f: | |
latest_chapter_url = f.readline() | |
if latest_chapter_url != chapter_url: | |
f.seek(0) | |
f.write(chapter_url) | |
f.truncate() | |
entry_content = get_entry_content(chapter_url) | |
p_image = entry_content.find("p").findChild() | |
if p_image is None: | |
next_sibling = entry_content.find("p").find_next_sibling() | |
while next_sibling.name != "p" and next_sibling.findChild("img") is None: | |
next_sibling = next_sibling.find_next_sibling() | |
p_image = next_sibling.findChild() | |
cover_url = (p_image.get("src")) | |
images = [] | |
for idx, tag in enumerate(entry_content.contents[:10]): | |
if (tag.find("img")) and tag.find("img") != -1: | |
image = tag.find("img") | |
image_url = image.get("src") | |
temp = session.get(image_url, stream=True) | |
image_path = f"images/local_image_{idx}.jpg" | |
os.makedirs(os.path.dirname(image_path), exist_ok=True) | |
with open(image_path, "wb") as f: | |
f.write(temp.content) | |
images.append(image_path) | |
image["src"] = image_path | |
del temp | |
content = "".join([str(tag) for tag in entry_content.contents]) | |
create_epub(chapter_title, chapter_url, content, images, cover_url) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment