Upload 3 files

app.py

@@ -0,0 +1,85 @@
+from flask import Flask, request, render_template, jsonify
+from nltk.tokenize import word_tokenize, sent_tokenize
+from urllib.request import urlopen
+from bs4 import BeautifulSoup
+import nltk
+from difflib import SequenceMatcher
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.cluster import KMeans
+
+nltk.download('punkt')
+
+app = Flask(__name__)
+
+def simple_summary(text, max_sentences=3):
+    sents = sent_tokenize(text)
+    return " ".join(sents[:max_sentences]) if sents else text[:200] + "..."
+
+@app.route("/")
+def home():
+    return render_template("index.html")
+
+@app.route("/process_urls", methods=["POST"])
+def process_urls():
+    data = request.form
+    selected_sites = request.form.getlist("sites")
+    mode = data.get("mode", "tokenize")
+
+    articles = {}
+    for url in selected_sites:
+        try:
+            page = urlopen(url)
+            soup = BeautifulSoup(page, "html.parser")
+            text = soup.get_text(separator=" ")
+            articles[url] = text
+        except Exception as e:
+            articles[url] = f"Error fetching: {str(e)}"
+
+    # -----------------------------
+    # Compare articles side-by-side
+    # -----------------------------
+    comparison_results = []
+    urls = list(articles.keys())
+    for i in range(len(urls)):
+        for j in range(i+1, len(urls)):
+            a, b = articles[urls[i]], articles[urls[j]]
+            sents_a, sents_b = sent_tokenize(a), sent_tokenize(b)
+            diff_a = []
+            for sent in sents_a:
+                if any(SequenceMatcher(None, sent, s).ratio() < 0.8 for s in sents_b):
+                    diff_a.append(sent)
+            comparison_results.append({
+                "site1": urls[i],
+                "site2": urls[j],
+                "diff_sentences_site1": diff_a
+            })
+
+    # -----------------------------
+    # Cluster articles by topic
+    # -----------------------------
+    clusters = {}
+    if len(articles) > 0:
+        vectorizer = TfidfVectorizer(stop_words='english')
+        X = vectorizer.fit_transform(list(articles.values()))
+        n_clusters = min(3, len(articles))
+        kmeans = KMeans(n_clusters=n_clusters, random_state=42).fit(X)
+        for idx, label in enumerate(kmeans.labels_):
+            clusters.setdefault(int(label), []).append(urls[idx])
+
+
+    # -----------------------------
+    # Summarize each article using NLTK simple summary
+    # -----------------------------
+    summaries = {}
+    for url, text in articles.items():
+        summaries[url] = simple_summary(text, max_sentences=3)
+
+    return jsonify({
+        "articles": articles,
+        "comparisons": comparison_results,
+        "clusters": clusters,
+        "summaries": summaries
+    })
+
+if __name__ == "__main__":
+    app.run(debug=True)

static/styles.css

@@ -0,0 +1,159 @@
+:root {
+    --bg: #111;
+    --text: #fff;
+    --accent: cyan;
+    --card: rgba(15,15,15,0.6);
+}
+
+body {
+    font-family: Arial, sans-serif;
+    background: var(--bg);
+    color: var(--text);
+    padding: 30px;
+}
+
+.container {
+    max-width: 900px;
+    margin: auto;
+    background: #222;
+    padding: 25px;
+    border-radius: 12px;
+    box-shadow: 0 0 25px rgba(0,255,255,0.1);
+}
+
+/* ========== HOLOGRAPHIC MULTI-SELECT CARDS ========== */
+.site-card-container {
+    margin-top: 25px;
+}
+
+.section-title {
+    font-size: 22px;
+    margin-bottom: 20px;
+    text-align: center;
+    font-weight: 600;
+}
+
+.site-cards {
+    display: flex;
+    justify-content: center;
+    flex-wrap: wrap;
+    gap: 22px;
+}
+
+.site-cards input[type="checkbox"] {
+    display: none;
+}
+
+.holo-card {
+    width: 150px;
+    padding: 22px 12px;
+    border-radius: 18px;
+    text-align: center;
+    cursor: pointer;
+    background: var(--card);
+    backdrop-filter: blur(12px);
+    border: 2px solid rgba(0,255,255,0.25);
+    box-shadow: 0 0 20px rgba(0,255,255,0.15), inset 0 0 15px rgba(0,255,255,0.05);
+    position: relative;
+    overflow: hidden;
+    transition: transform 0.25s ease, box-shadow 0.3s ease, border 0.3s ease;
+}
+
+.holo-card:hover {
+    transform: translateY(-8px) scale(1.04);
+    animation: rainbow-border 2.5s infinite linear;
+}
+
+@keyframes rainbow-border {
+    0%   { border-color: #00ffff; }
+    25%  { border-color: #ff00ff; }
+    50%  { border-color: #ffcc00; }
+    75%  { border-color: #00ff66; }
+    100% { border-color: #00ffff; }
+}
+
+.holo-card::before {
+    content: "";
+    position: absolute;
+    top: -30%;
+    left: -60%;
+    width: 250%;
+    height: 250%;
+    background: linear-gradient(120deg, transparent 20%, rgba(255,255,255,0.12) 50%, transparent 80%);
+    transform: rotate(20deg);
+    animation: shimmer 3s infinite;
+    pointer-events: none;
+}
+
+@keyframes shimmer {
+    0%   { transform: translateX(-200%) rotate(20deg); }
+    100% { transform: translateX(200%) rotate(20deg); }
+}
+
+.holo-card::after {
+    content: "";
+    position: absolute;
+    inset: 0;
+    border-radius: 18px;
+    box-shadow: 0 0 20px rgba(0,255,255,0.15), 0 0 30px rgba(0,255,255,0.05), inset 0 0 20px rgba(0,255,255,0.05);
+    z-index: -1;
+}
+
+.holo-card .icon {
+    font-size: 34px;
+    margin-bottom: 12px;
+    animation: pulse-glow 2s infinite alternate;
+}
+
+@keyframes pulse-glow {
+    from { text-shadow: 0 0 4px cyan; }
+    to   { text-shadow: 0 0 12px cyan; }
+}
+
+.holo-card .site-name {
+    color: var(--text);
+    font-size: 16px;
+    font-weight: 600;
+    text-shadow: 0 0 8px rgba(0,255,255,0.4);
+}
+
+.site-cards input:checked + .holo-card {
+    background: rgba(0,40,40,0.85);
+    border: 2px solid cyan;
+    box-shadow: 0 0 35px rgba(0,255,255,0.75), inset 0 0 30px rgba(0,255,255,0.45), 0 0 15px rgba(0,255,255,0.35);
+    transform: translateY(-10px) scale(1.06);
+}
+
+.holo-card:active {
+    transform: scale(0.97);
+}
+
+/* ========== RESULT CARDS ========== */
+.result-container {
+    margin-top: 30px;
+}
+
+.result-card {
+    background: rgba(0,0,0,0.7);
+    border-radius: 12px;
+    padding: 15px;
+    margin-bottom: 18px;
+    box-shadow: 0 0 12px rgba(0,255,255,0.3);
+    border: 1px solid rgba(0,255,255,0.2);
+    transition: transform 0.25s ease, box-shadow 0.25s ease;
+}
+
+.result-card:hover {
+    transform: translateY(-5px);
+    box-shadow: 0 0 25px rgba(0,255,255,0.6);
+}
+
+.result-card h3 {
+    color: cyan;
+    margin-bottom: 10px;
+}
+
+.result-card ul {
+    margin: 0;
+    padding-left: 18px;
+}

templates/index.html

@@ -0,0 +1,105 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Ultra News Tokenizer</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='styles.css') }}">
+</head>
+<body>
+
+<div class="container">
+    <h1>Ultra News Tokenizer</h1>
+
+    <form id="urlForm" method="POST">
+        <div class="site-card-container">
+            <label class="section-title">Select News Sites</label>
+
+            <div class="site-cards">
+                <input type="checkbox" name="sites" id="indianexpress" value="https://indianexpress.com/">
+                <label for="indianexpress" class="site-card holo-card">
+                    <div class="icon">📰</div>
+                    <div class="site-name">Indian Express</div>
+                </label>
+
+                <input type="checkbox" name="sites" id="ndtv" value="https://www.ndtv.com/">
+                <label for="ndtv" class="site-card holo-card">
+                    <div class="icon">🔵</div>
+                    <div class="site-name">NDTV</div>
+                </label>
+
+                <input type="checkbox" name="sites" id="toi" value="https://timesofindia.indiatimes.com/">
+                <label for="toi" class="site-card holo-card">
+                    <div class="icon">🟣</div>
+                    <div class="site-name">Times of India</div>
+                </label>
+
+                <input type="checkbox" id="selectall">
+                <label for="selectall" class="site-card holo-card special">
+                    <div class="icon">⭐</div>
+                    <div class="site-name">Select All</div>
+                </label>
+            </div>
+        </div>
+
+        <label>Select Mode:</label>
+        <select name="mode">
+            <option value="tokenize">Tokenize Text</option>
+            <option value="raw_text">Raw Text</option>
+        </select>
+
+        <button type="submit">Submit</button>
+    </form>
+
+    <div id="output" class="result-container"></div>
+</div>
+
+<script>
+document.getElementById("selectall").addEventListener("change", function() {
+    const checked = this.checked;
+    document.querySelectorAll('.site-cards input[type="checkbox"]').forEach(cb => {
+        if(cb.id !== "selectall") cb.checked = checked;
+    });
+});
+
+const form = document.getElementById("urlForm");
+form.addEventListener("submit", async function(e) {
+    e.preventDefault();
+    const formData = new FormData(form);
+    const response = await fetch("/process_urls", {
+        method: "POST",
+        body: formData
+    });
+    const data = await response.json();
+
+    let html = "";
+
+    html += "<h2>Article Summaries</h2>";
+    for (const url in data.summaries) {
+        html += `<div class="result-card">
+                    <h3>${url}</h3>
+                    <p>${data.summaries[url]}</p>
+                 </div>`;
+    }
+
+    html += "<h2>Comparisons (Changed Sentences)</h2>";
+    data.comparisons.forEach(c => {
+        html += `<div class="result-card">
+                    <h3>${c.site1} VS ${c.site2}</h3>
+                    <ul>`;
+        c.diff_sentences_site1.forEach(s => {
+            html += `<li>${s}</li>`;
+        });
+        html += `</ul></div>`;
+    });
+
+    html += "<h2>Clusters</h2>";
+    for (const label in data.clusters) {
+        html += `<div class="result-card"><strong>Cluster ${label}:</strong> ${data.clusters[label].join(", ")}</div>`;
+    }
+
+    document.getElementById("output").innerHTML = html;
+});
+</script>
+
+</body>
+</html>