Export Calibre library to find each book's ISBN with Google Book API and export to JSON or CSV file

calibre_library.py

import click
import json
import requests
import sys
import time

import pandas as pd
from tqdm.auto import tqdm
from rich.progress import track
from rich.console import Console
from rich.traceback import install

install()
console = Console()


def call_books_api(title, authors):
    api_url = "https://www.googleapis.com/books/v1/volumes"

    def _get_identifier(id_name):
        _id = [
            inf["identifier"]
            for inf in volum["industryIdentifiers"]
            if inf["type"] == id_name
        ]
        if _id:
            return _id[0]
        return None

    info = {}
    try:
        resp = requests.get(api_url, params=[("q", title), ("inauthor", authors)])
        resp.raise_for_status()
        results = resp.json()

        volum = results["items"][0]["volumeInfo"]

        for k in {"ISBN_10", "ISBN_13"}:
            info[k] = _get_identifier(k)

        for k in {"categories", "publisher"}:
            v = volum.get(k)
            if isinstance(v, list):
                v = ", ".join(v)

            info[k] = v

        return info
    except Exception as e:
        console.log(f"[red]Error calling books API: {e}[/red]")

    return info


@click.group()
def cli():
    pass
    # click.echo(f"dummy cli 🤘🏻")


@cli.command("calibre")
@click.argument(
    "calibre_json_file",
    # help="Calibre library JSON export file."
)
def augment_calibre_library_data(calibre_json_file: str):
    """
    Retrieves the ISBN_10 & ISBN_13 for each book in a Calibre library dump.
    To get the Calibre library dump:

        calibredb list -f title,authors,isbn,publisher,rating --for-machine \
            > calibre-library-`date "+%Y-%m-%d"`.json
    """
    with open(calibre_json_file, "r") as f:
        library = json.load(f)

    library = sorted(library, key=lambda x: x["title"])

    for i, book in enumerate(library):
        title = book.get("title")
        authors = book.get("authors")
        console.log(f"Searching [bold]{title}[/bold] ({authors})")

        # Call Google Book API to find ISBn numbers
        book_info = call_books_api(title, authors)
        console.log(f"[magenta]{book_info}[/magenta]")

        library[i].update(book_info)

        time.sleep(0.5)

    console.log(f"[green]Writing updated library file[/green]")
    with open(lib_json, "w", encoding="utf-8") as f:
        f.write(json.dumps(library, indent=2, ensure_ascii=True))

    df = pd.DataFrame.from_dict(library)
    df.fillna("<unk>")
    del df["id"]
    df.to_csv(lib_json.replace(".json", ".csv"), index=False)


@cli.command("books")
@click.argument(
    "libcsv",
    # help="CSV file with the book list. Must have 'Author' and 'Title' columns",
)
@click.argument(
    "outfile",
    # help="output CSV file"
)
def fetch_book_data(libcsv: str, outfile: str):
    """
    Retrieves the ISBN_10 & ISBN_13 for each book in a CSV book list.
    The CSV Must have two columns: Author and Title
    """
    _cols = ["Author", "Title"]

    # Read the CSV
    libdf = pd.read_csv(libcsv)
    headers = list(libdf)
    if not all([h in headers for h in _cols]):
        raise ValueError(f"CSV file must have the following columns: {_cols}")

    book_data = []
    for _, row in tqdm(libdf.iterrows(), total=len(libdf)):
        if isinstance(row.Author, str):
            authors = row.Author.split(",")
        if isinstance(authors, str):
            authors = [authors]
        bdata = call_books_api(row.Title, authors)
        bdata.update(
            {"authors": row.Author, "title": row.Title, "completed": 0, "notes": ""}
        )
        book_data.append(bdata)

    wdf = pd.DataFrame.from_dict(book_data)
    wdf.to_csv(outfile)


if __name__ == "__main__":
    cli()