Files
idriz/scripts/test_summary.py

41 lines
1.7 KiB
Python

"""Ručni test: Wikipedia -> (opciono) sažetak -> PDF. Bez ključa radi sa sirovim tekstom članka i slikom sa Wikipedije."""
import asyncio
import html
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
from idriz import render, textgen, wiki # noqa: E402
from idriz.config import load # noqa: E402
async def main(topic: str, age: str) -> None:
cfg = load()
art = wiki.find_article(topic)
if not art:
print("nema članka"); return
print("članak:", art.title, art.url, len(art.text), "znakova")
out = Path("out"); out.mkdir(exist_ok=True)
url = wiki.page_image_url(art.title)
image = None
if url:
raw = out / ("test-wiki" + Path(url).suffix.lower())
if wiki.download(url, raw):
image = render.prepare_image(raw, out / "test-img.png")
print("slika:", url, "->", image)
if cfg.openai_api_key:
from openai import AsyncOpenAI
s = await textgen.summarize(AsyncOpenAI(api_key=cfg.openai_api_key), cfg.text_model, art, topic, age)
title, body, facts, caption = s.title, s.html, s.facts, s.caption
else:
paras = [p for p in art.text.split("\n\n") if p and not p.startswith("==")][:5]
title, body = art.title, "".join(f"<p>{html.escape(p[:600])}</p>" for p in paras)
facts = ["Ovo je probna zanimljivost broj jedan.", "Druga zanimljivost, kratka.", "Treća, još kraća."]
caption = "Probni potpis ispod slike."
pdf = render.render_summary(title, body, facts, caption, image, art.title, out / "test-sazetak.pdf", cfg.max_pages)
print("PDF:", pdf)
if __name__ == "__main__":
asyncio.run(main(sys.argv[1] if len(sys.argv) > 1 else "Volcano", sys.argv[2] if len(sys.argv) > 2 else "10"))