Summary layout for kids: Wikipedia lead image, airy text, facts box, generated illustration fallback

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LzKpYaEsuWDevuNnvSjcFW
This commit is contained in:
idriz
2026-09-02 18:47:23 +02:00
parent 78967e15f9
commit 881ad46c11
6 changed files with 172 additions and 43 deletions

View File

@@ -1,4 +1,4 @@
"""Ručni test: Wikipedia -> (opciono) sažetak -> PDF. Bez ključa radi samo sa sirovim tekstom članka."""
"""Ručni test: Wikipedia -> (opciono) sažetak -> PDF. Bez ključa radi sa sirovim tekstom članka i slikom sa Wikipedije."""
import asyncio
import html
import sys
@@ -16,13 +16,23 @@ async def main(topic: str, age: str) -> None:
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
title, body = await textgen.summarize(AsyncOpenAI(api_key=cfg.openai_api_key), cfg.text_model, art, topic, age)
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:
title = art.title
body = "".join(f"<p>{html.escape(p)}</p>" for p in art.text.split("\n\n")[:12])
pdf = render.render_summary(title, body, art.title, out / "test-sazetak.pdf", cfg.max_pages)
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)