app.py

# app.py
import gradio as gr
import trafilatura
import jieba
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np
import re

def clean_text(text):
    # 移除過多空白、保留中文/英文/數字/標點
    text = re.sub(r'\s+', ' ', text)
    return text.strip()

def textrank_summary(text, target_min=300, target_max=500):
    # 以句號、換行切分句子
    sentences = re.split(r'[。！？\n]', text)
    sentences = [s.strip() for s in sentences if len(s.strip()) > 10]  # 過濾太短句
    
    if not sentences:
        return text[:500]
    
    # 若全文太短，直接回傳
    if len(text) <= target_max:
        return text

    # 中文分詞（用 jieba）
    tokenized = [' '.join(jieba.cut(sent)) for sent in sentences]
    
    # TF-IDF 向量化
    vectorizer = TfidfVectorizer()
    try:
        tfidf = vectorizer.fit_transform(tokenized)
    except ValueError:
        return ' '.join(sentences)[:500]
    
    # 計算句子相似度
    sim_mat = cosine_similarity(tfidf)
    
    # 簡化 TextRank：用相似度均值當分數
    scores = np.mean(sim_mat, axis=1)
    
    # 按分數排序
    ranked = sorted(zip(sentences, scores), key=lambda x: x[1], reverse=True)
    
    # 拼接句子直到達到目標長度
    result = []
    total_len = 0
    for sent, _ in ranked:
        if total_len >= target_min:
            break
        if total_len + len(sent) > target_max:
            # 截斷最後一句
            remaining = target_max - total_len
            result.append(sent[:remaining])
            break
        result.append(sent)
        total_len += len(sent)
    
    return ''.join([s + '。' for s in result if s])

def summarize_url(url):
    if not url or not url.startswith("http"):
        return "請輸入有效網址（需包含 http:// 或 https://）"
    
    try:
        downloaded = trafilatura.fetch_url(url)
        if not downloaded:
            return "無法載入該網頁，請確認網址是否正確。"
        
        text = trafilatura.extract(
            downloaded,
            include_comments=False,
            include_tables=False,
            output_format="txt"
        )
        
        if not text or len(text.strip()) < 100:
            return "無法提取足夠的文字內容（可能不是文章頁面）。"
        
        text = clean_text(text)
        summary = textrank_summary(text, target_min=300, target_max=500)
        return summary
    
    except Exception as e:
        return f"處理錯誤：{str(e)}"

# Gradio UI
with gr.Blocks(title="中文網頁重點整理（300–500字）") as demo:
    gr.Markdown("## 🌐 中文網頁重點整理 Agent\n輸入網址，自動提取 **300–500 字重點內容**（CPU 友好，無需模型）")
    url_input = gr.Textbox(label="請輸入網址", placeholder="https://example.com/chinese-article")
    output = gr.Textbox(label="重點摘要", lines=10)
    btn = gr.Button("開始整理")
    btn.click(fn=summarize_url, inputs=url_input, outputs=output)
    gr.Markdown("💡 適用於新聞、報告、部落格等文字型網頁。")

demo.launch()