#
# books.py
# Gera um arquivo .sql com INSERTs de livros obtidos do Project Gutemberg
# https://gutendex.com/
#

import http.client
import json
import time
from urllib.parse import urlparse

API_URL     = "https://gutendex.com/books/"
BOOKS_COUNT = 1000
FETCH_DELAY = 1#s
OUTPUT      = "./books.sql"

def fetch(resource):
    url    = urlparse(resource)
    client = http.client.HTTPSConnection if url.scheme == "https" else http.client.HTTPConnection
    conn   = client(url.netloc)

    conn.request("GET", f"{url.path}?{url.query}")
    res = conn.getresponse()

    if res.status < 200 or res.status > 299:
        return {}

    return json.loads(res.read())

def write_inserts(file, page):
    data  = fetch(f"{API_URL}?page={page}")
    books = data["results"]
    lines = []

    esc = lambda str: str.replace('"', '\\"')

    for book in books:
        summaries = book["summaries"]
        imgs      = [book["formats"][f] for f in book["formats"] if f.startswith("image/")]

        isbn      = ""
        titulo    = book["title"]
        autor     = ",".join([a["name"] for a in book["authors"]])
        genero    = ",".join(book["subjects"])
        descricao = summaries[0] if len(summaries) > 0 else ""
        foto      = imgs[0] if len(imgs) > 0 else ""
        keywords  = ",".join(book["bookshelves"])

        lines.append(f'("{esc(isbn)}", "{esc(titulo)}", "{esc(autor)}", "{esc(genero)}", "{esc(descricao)}", "{esc(foto)}", "{esc(keywords)}", true, NOW(), NOW())')

    values = ",\n".join(lines)
    insert = f"INSERT INTO Livro (Isbn, Titulo, Autor, Genero, Descricao, Foto, Keywords, Ativo, CriadoEm, AtualizadoEm) VALUES {values};\n"

    file.write(insert)

    return len(lines)

def collect(n, file, _page=1):
    if n <= 0:
        return

    written = write_inserts(file, _page)

    time.sleep(FETCH_DELAY)
    collect(n-written, file, _page+1)

def run():
    with open(OUTPUT, "w") as file:
        collect(BOOKS_COUNT, file)

run()