Generate a Wipkipedia cite book template for an archive.org identifier (with optional page number + link)

iacite.py

#!/usr/bin/env python

import argparse
import internetarchive as ia
import biblionames
#from isbn_hyphenate import hyphenate
from isbnlib import mask as hyphenate


OCLC_TAG = 'urn:oclc:record:'


def listify(data):
    if not data:
        return
    return data if isinstance(data, list) else [data]


def cite(item, page=None):
    params = {}

    authors = item.metadata.get('creator', [])
    if isinstance(authors, str):
        authors = [authors]
    for i, author in enumerate(authors):
        num = i + 1 if len(authors) > 1 else ''
        first, last = biblionames.Author.ia_to_first_last(author)
        if author and not (first and last):
            params[f'author{num}'] = biblionames.Author.ia_to_natural(author)
        elif author:
            params[f'last{num}'] = last
            params[f'first{num}'] = first
    params['date'] = item.metadata.get('date')
    params['title'] = biblionames.Title.transform_title(item.metadata.get('title')).replace(' : ', ': ')
    url = f'https://archive.org/details/{item.identifier}'
    params['url'] = url
    if 'inlibrary' in item.metadata.get('collection', []):
        params['url-access'] = 'registration'
    params['publication-place'], params['publisher'] = ia_publisher(item.metadata.get('publisher', []))

    # TODO: add volume: e.g. bakersbiographic02slon
    if page:
        if '-' in page:
            page = page.replace('-', '–')
        if '–' in page:
            ptype = 'pages'
            pp = page[:page.find('–')]
            pagelink = f'{url}/page/{pp}'
        else:
            ptype = 'page'
            pagelink = f'{url}/page/{page}'
        params[ptype] = f'[{pagelink} {page}]'
        
    isbn = get_isbn(item)
    params['isbn'] = hyphenate(isbn) if isbn else None
    lccn = item.metadata.get('lccn')
    if isinstance(lccn, list):
        lccn = lccn[0]
    params['lccn'] = lccn.split()[0] if lccn else None
    identifiers = item.metadata.get('external-identifier', [])
    if isinstance(identifiers, str):
        identifiers = [identifiers]
    for id_ in identifiers:
        if OCLC_TAG in id_:
            oclc = id_.replace(OCLC_TAG, '')
            break
    oclc = listify(item.metadata.get('oclc_id'))
    if oclc:
        params['oclc'] = oclc[0]
    return '{{cite book|' + ' |'.join([f'{k}={v}' for k, v in params.items() if v]) + '}}'


def get_isbn(item):
    """Returns the best ISBN."""
    isbns = listify(item.metadata.get('isbn'))
    if item.metadata.get('scribe3_search_catalog') == 'isbn':
        return item.metadata.get('scribe3_search_id')
    if not isbns:
        return None
    for isbn in isbns:
        if isbn.startswith('97'):
            return isbn

    return isbns[0] if isbns else None


def ia_publisher(raw):
    if ';' in raw:  # Multiple publsihers
        publishers = raw.split(';')
        raw = publishers[0]  # Use first
    if ':' in raw:
        location, publisher = raw.split(':')
        return location.strip(), publisher.strip()
    elif ',' in raw:
        location, publisher = raw.split(',')
        return location.strip(), publisher.strip()
    else:
        return None, raw


def main():
    parser = argparse.ArgumentParser(description='archive.org book cite tool.')
    parser.add_argument('item', help='Book item identifier to cite')
    parser.add_argument('-p', '--page', help='Page number (or range)')
    args = parser.parse_args()

    item = ia.get_item(args.item)
    print(item)
    print(cite(item, args.page))


if __name__ == '__main__':
    main()

This uses biblionames which is unfortunately not public :(