import nltk
nltk.download("punkt")
nltk.download("punkt_tab")

import gradio as gr
import trafilatura
import requests
from markdownify import markdownify as md
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.text_rank import TextRankSummarizer
import re

def summarize_text(text, sentence_count=3):
    parser = PlaintextParser.from_string(text, Tokenizer("english"))
    summarizer = TextRankSummarizer()
    summary_sentences = summarizer(parser.document, sentence_count)
    return [str(sentence) for sentence in summary_sentences]

def paraphrase_text(sentences):
    # 간단한 로컬 paraphrase: 동의어 치환 + 문장 구조 변경
    # (LLM 없이 동작, 품질은 기본 수준)
    paraphrased = []
    replacements = {
        "노조": "노동조합",
        "성과급": "성과 보상금",
        "요구": "요청",
        "불만": "이의 제기",
        "합의안": "협상 결과안"
    }
    for s in sentences:
        new_s = s
        for k, v in replacements.items():
            new_s = re.sub(k, v, new_s)
        # 어순 살짝 변경 예시
        if "는" in new_s:
            parts = new_s.split("는", 1)
            new_s = f"{parts[1].strip()} — {parts[0].strip()}는"
        paraphrased.append(new_s)
    return paraphrased

def extract_summarize_paraphrase(url):
    headers = {"User-Agent": "Mozilla/5.0"}
    try:
        r = requests.get(url, headers=headers, timeout=10)
        r.raise_for_status()

        html_content = trafilatura.extract(
            r.text,
            output_format="html",
            include_tables=True,
            favor_recall=True
        )

        if not html_content:
            return "본문을 추출할 수 없습니다.", "", ""

        markdown_text = md(html_content, heading_style="ATX")

        summary_sentences = summarize_text(markdown_text, sentence_count=3)
        paraphrased_sentences = paraphrase_text(summary_sentences)

        return markdown_text, "\n".join(summary_sentences), "\n".join(paraphrased_sentences)

    except Exception as e:
        return f"에러 발생: {e}", "", ""

iface = gr.Interface(
    fn=extract_summarize_paraphrase,
    inputs=gr.Textbox(label="URL 입력", placeholder="https://example.com"),
    outputs=[
        gr.Markdown(label="추출된 본문"),
        gr.Textbox(label="자동 요약", lines=5),
        gr.Textbox(label="자동 재작성", lines=5)
    ],
    title="본문 추출기 + 자동 요약 + 자동 재작성",
    description="웹페이지 URL을 입력하면 본문을 추출하고, 3문장 요약과 재작성(Paraphrasing) 결과를 제공합니다."
)

if __name__ == "__main__":
    iface.launch()