Example for how to fix json content in CLTK Perseus file

fix-iliad-16-cltk-perseus-json.py

import json
from cltkreaders.grc import GreekTesseraeCorpusReader

T = GreekTesseraeCorpusReader()

BOOK = 16
file = f"homer.iliad.part.{BOOK}.tess"

output = dict()


def get_line_number_from_citation(citation):
    # e.g. '<hom. il. 16.840>'
    return citation.split(".")[-1].replace(">", "")


doc_rows = next(T.doc_rows(file))

for citation, line in doc_rows.items():
    line_number = get_line_number_from_citation(citation)
    output[line_number] = line

book_output = {"16": output}

with open(f"iliad-{BOOK}.json", "w") as f:
    json.dump(book_output, f, ensure_ascii=False)