Convert Goodreads CSV export to CSV with only relevant fields

goodriddance.py

import pandas as pd

INPUT_FIELDS = [
    "Book Id",
    "Title",
    "Author",
    "Author l-f",
    "Binding",
    "Original Publication Year",
    "Bookshelves",
    "Owned Copies",
    "Condition",
]
OUTPUT_FIELDS = ["Title", "Author", "Binding", "Condition", "Goodreads Page"]


def process(goodreads_export):
    books = pd.read_csv(goodreads_export, usecols=INPUT_FIELDS)

    # Only keep books in the "to-sell" shelf
    books = books[
        books["Bookshelves"].str.contains("to-sell", na=False, regex=False)
        & (books["Owned Copies"] > 0)
    ]

    # Sort by "Author l-f" and "Original Publication Year"
    books = books.sort_values(by=["Author l-f", "Original Publication Year"])

    # Add Goodreads links
    book_ids = books["Book Id"].astype(str)
    books["Goodreads Page"] = "https://goodreads.com/book/show/" + book_ids

    # Only keep certain columns (in the specified order)
    return books[OUTPUT_FIELDS]


if __name__ == "__main__":
    import sys

    process(sys.stdin).to_csv(sys.stdout, index=False)