export-book-wishlist

#!/usr/bin/env python3
import json
import re
from argparse import ArgumentParser
from typing import Iterator, List, NamedTuple, Optional

import pandas as pd
from dateutil.parser import parse as parse_date

date_pattern = re.compile(r'^(?:([0-9]{2})/)?(?:([0-9]{2})/)?([0-9]{4})$')


if True:
    sheet_owned_books = 'Books'
    sheet_owned_comics = 'Comics'
    sheet_wishlist_books = 'Books - Wishlist'
    sheet_wishlist_comics = 'Comics - Wishlist'

    column_title = 'Title'
    column_authors = 'Authors'
    column_categories = 'Categories'
    column_published_date = 'Published date'
    column_isbn = 'ISBN'
    column_read = 'Read'

    bool_true = 'Yes'
else:
    sheet_owned_books = 'Livres'
    sheet_owned_comics = 'Bandes Dessinées'
    sheet_wishlist_books = 'Livres - Liste de souhaits'
    sheet_wishlist_comics = 'Bandes Dessinées - Liste de sou'

    column_title = 'Titre'
    column_authors = 'Auteurs'
    column_categories = 'Genres'
    column_published_date = 'Date de publication'
    column_isbn = 'ISBN'
    column_read = 'Lu'

    bool_true = 'Oui'


class Book(NamedTuple):
    title: str
    authors: List[str]
    genres: List[str]
    publication_year: Optional[int]
    isbn: str
    comic: bool
    read: bool
    owned: bool


def parse_book(book: pd.Series, comic: bool, owned: bool) -> dict:
    publication = book[column_published_date]
    publication_date = None
    publication_year = None
    if publication:
        try:
            publication_year = int(publication)
        except ValueError:
            publication_dt = parse_date(publication)
            publication_date = publication_dt.date().isoformat()
            publication_year = publication_dt.year
    return Book(
        title=book[column_title],
        authors=book[column_authors].split(', '),
        genres=book[column_categories].split(', '),
        publication_year=publication_year,
        isbn=book[column_isbn],
        comic=comic,
        read=book[column_read] == bool_true,
        owned=owned,
    )._asdict()


def parse_books(books: pd.DataFrame, comic: bool, owned: bool) -> Iterator[dict]:
    for _, book in books.iterrows():
        yield parse_book(book, comic=comic, owned=owned)


def main() -> None:
    parser = ArgumentParser()
    parser.add_argument(
        'filename', help='XLS files from MyLibrary, e.g. MyLibrary.xls'
    )
    args = parser.parse_args()

    df = pd.read_excel(args.filename, na_filter=False, sheet_name=None)
    books: list[dict] = []
    books += parse_books(df[sheet_owned_books], comic=False, owned=True)
    books += parse_books(df[sheet_wishlist_books], comic=False, owned=False)
    books += parse_books(df[sheet_owned_comics], comic=True, owned=True)
    books += parse_books(df[sheet_wishlist_comics], comic=True, owned=False)
    print(json.dumps(books))


if __name__ == '__main__':
    main()