app.py

import requests
from bs4 import BeautifulSoup
import pandas as pd
import jieba
from keybert import KeyBERT
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
import streamlit as st
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
from wordcloud import WordCloud
from gensim import corpora, models

# 下載字體
def download_font(url, save_path):
    response = requests.get(url)
    with open(save_path, 'wb') as f:
        f.write(response.content)

# 字體URL和保存路徑
font_url = 'https://drive.google.com/uc?id=1eGAsTN1HBpJAkeVM57_C7ccp7hbgSz3_&export=download'
font_path = 'TaipeiSansTCBeta-Regular.ttf'

# 下載字體
download_font(font_url, font_path)

# 設置字體
font_prop = FontProperties(fname=font_path)

# 抓取Yahoo新聞標題和內容
def fetch_yahoo_news(url):
    response = requests.get(url)
    web_content = response.content
    soup = BeautifulSoup(web_content, 'html.parser')
    title = soup.find('h1').text
    content = soup.find('article').text
    return title, content

# 斷詞函數
def jieba_tokenizer(text):
    return jieba.lcut(text)

# 初始化CountVectorizer並定義KeyBERT模型
vectorizer = CountVectorizer(tokenizer=jieba_tokenizer)
kw_model = KeyBERT()

# 提取關鍵詞的函數（使用MMR）
def extract_keywords(doc, diversity=0.7):
    keywords = kw_model.extract_keywords(doc, vectorizer=vectorizer, use_mmr=True, diversity=diversity)
    return keywords

# 畫圖函數
def plot_keywords(keywords, title):
    words = [kw[0] for kw in keywords]
    scores = [kw[1] for kw in keywords]

    plt.figure(figsize=(10, 6))
    bars = plt.barh(words, scores, color='skyblue', edgecolor='black', linewidth=1.2)
    plt.xlabel('分數', fontproperties=font_prop, fontsize=14)
    plt.title(title, fontproperties=font_prop, fontsize=16)
    plt.gca().invert_yaxis()  # 反轉Y軸，使得分數最高的關鍵詞在最上面
    plt.xticks(fontproperties=font_prop, fontsize=12)
    plt.yticks(fontproperties=font_prop, fontsize=12)
    plt.grid(axis='x', linestyle='--', alpha=0.7)
    
    # 添加分數標籤
    for bar in bars:
        plt.gca().text(bar.get_width() + 0.01, bar.get_y() + bar.get_height() / 2,
                       f'{bar.get_width():.4f}', va='center', ha='left', fontsize=12, fontproperties=font_prop)

    st.pyplot(plt)

# 生成TF-IDF文字雲的函數
def plot_wordcloud(text):
    tfidf_vectorizer = TfidfVectorizer(tokenizer=jieba_tokenizer)
    tfidf_matrix = tfidf_vectorizer.fit_transform([text])
    tfidf_scores = dict(zip(tfidf_vectorizer.get_feature_names_out(), tfidf_matrix.toarray().flatten()))
    
    wordcloud = WordCloud(font_path=font_path, background_color='white', max_words=100, width=800, height=400)
    wordcloud.generate_from_frequencies(tfidf_scores)

    plt.figure(figsize=(10, 6))
    plt.imshow(wordcloud, interpolation='bilinear')
    plt.axis('off')
    plt.title('TF-IDF文字雲', fontproperties=font_prop, fontsize=16)
    st.pyplot(plt)

# LDA主題模型函數
def lda_topic_modeling(text, num_topics=5):
    # 斷詞並創建字典和語料庫
    tokens = jieba_tokenizer(text)
    dictionary = corpora.Dictionary([tokens])
    corpus = [dictionary.doc2bow(tokens)]
    
    # 生成LDA模型
    lda_model = models.LdaModel(corpus, num_topics=num_topics, id2word=dictionary, passes=15)
    
    # 提取主題
    topics = lda_model.print_topics(num_words=5)
    return topics

# 建立Streamlit網頁應用程式
st.title("🤙🤙🤙YAHOO新聞關鍵詞提取工具👂👂")

# 設置MMR多樣性參數
diversity = st.slider("選擇MMR多樣性參數", 0.0, 1.0, 0.7)

# 抓取Yahoo新聞的URL輸入框
url = st.text_input("請輸入Yahoo新聞的URL：")

if st.button("抓取並提取關鍵詞"):
    if url:
        title, content = fetch_yahoo_news(url)
        st.write("新聞標題：", title)
        st.write("新聞內容：", content)
        
        # 將內容轉為DataFrame
        data = {'Title': [title], 'Content': [content]}
        df = pd.DataFrame(data)
        st.write("新聞內容的DataFrame：")
        st.write(df)
        
        # 提取關鍵詞
        keywords = extract_keywords(content, diversity=diversity)
        st.write("關鍵詞提取結果：")
        for keyword in keywords:
            st.write(f"{keyword[0]}: {keyword[1]:.4f}")
        
        plot_keywords(keywords, "關鍵詞提取結果")

        # 使用另一個模型進行關鍵詞提取
        kw_model_multilingual = KeyBERT(model='distiluse-base-multilingual-cased-v1')
        keywords_multilingual = kw_model_multilingual.extract_keywords(content, vectorizer=vectorizer, use_mmr=True, diversity=diversity)
        st.write("多語言模型關鍵詞提取結果：")
        for keyword in keywords_multilingual:
            st.write(f"{keyword[0]}: {keyword[1]:.4f}")
        
        plot_keywords(keywords_multilingual, "多語言模型關鍵詞提取結果")
        
        # 生成TF-IDF文字雲
        plot_wordcloud(content)

        # LDA主題模型
        num_topics = st.slider("選擇LDA主題數量", 1, 10, 5)
        lda_topics = lda_topic_modeling(content, num_topics=num_topics)
        st.write("LDA主題模型結果：")
        for topic in lda_topics:
            st.write(f"主題 {topic[0]}: {topic[1]}")
    else:
        st.write("請輸入有效的Yahoo新聞URL。")