This repository has been archived on 2024-02-23. You can view files and clone it, but cannot push or open issues or pull requests.
Auberge_Vagabonde/gravesong.py

74 lines
2.3 KiB
Python
Raw Normal View History

2022-01-18 20:43:45 +00:00
import bs4
2022-01-18 21:05:00 +00:00
import logging
2022-01-18 20:43:45 +00:00
import requests
2022-08-18 10:59:02 +00:00
import utils
2022-01-18 20:43:45 +00:00
2022-08-18 10:59:02 +00:00
from ebooklib import epub
2022-01-18 20:43:45 +00:00
2022-08-18 10:59:02 +00:00
@utils.executor
def process(metadatas, output_dir):
book = epub.EpubBook()
book_items = []
book.set_identifier("gravesong")
book.set_title("Gravesong")
book.set_language(metadatas["language"])
book.set_cover("cover.jpg", open(metadatas["cover"], "rb").read())
book.add_metadata("DC", "description", "Advance Patreon Edition")
for author in metadatas["authors"]:
book.add_author(author)
2022-01-18 20:43:45 +00:00
response = requests.post(
"https://wanderinginn.com/wp-pass.php",
data={"post_password": "Iwalkedameadowweary", "Submit": "Enter"},
headers={"Referer": "https://wanderinginn.com/2022/01/11/gravesong/"},
)
html = bs4.BeautifulSoup(response.content, "html.parser")
entry_content = html.select_one("div.entry-content")
2022-01-19 15:04:48 +00:00
content_as = entry_content.find_all("a")
2022-01-18 20:43:45 +00:00
2022-01-19 15:04:48 +00:00
for content_a in content_as:
content_a.decompose()
2022-01-18 20:43:45 +00:00
chapter_title = "Introduction"
chapter_content = ""
2022-08-18 11:43:30 +00:00
chapter_index = 1
2022-01-18 20:43:45 +00:00
for paragraph in entry_content.children:
if paragraph.name == "h1":
2022-01-18 21:05:00 +00:00
logging.log(logging.INFO, f"Gravesong - {chapter_title}")
2022-08-18 10:59:02 +00:00
book_items.append(
epub.EpubHtml(
title=chapter_title,
content=utils.generate_title_html(chapter_title, chapter_content),
2022-08-18 11:43:30 +00:00
file_name=f"{chapter_index}.xhtml",
2022-08-18 10:59:02 +00:00
lang=metadatas["language"],
)
2022-01-18 20:43:45 +00:00
)
2022-01-18 21:53:50 +00:00
chapter_title = paragraph.get_text().strip()
2022-08-18 11:43:30 +00:00
chapter_index += 1
2022-01-18 20:43:45 +00:00
elif paragraph.name == "p":
chapter_content += paragraph.prettify()
2022-01-18 21:05:00 +00:00
logging.log(logging.INFO, f"Gravesong - {chapter_title}")
2022-08-18 10:59:02 +00:00
book_items.append(
epub.EpubHtml(
title=chapter_title,
content=utils.generate_title_html(chapter_title, chapter_content),
2022-08-18 11:43:30 +00:00
file_name=f"{chapter_index}.xhtml",
2022-08-18 10:59:02 +00:00
lang=metadatas["language"],
)
)
2022-01-18 20:43:45 +00:00
2022-01-18 21:05:00 +00:00
logging.log(logging.INFO, "Gravesong - Book")
2022-08-18 10:59:02 +00:00
for book_item in book_items:
book.add_item(book_item)
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
book.toc = book_items
book.spine = ["cover", "nav", *book_items]
epub.write_epub(f"{output_dir}/Gravesong.epub", book)