Spaces:

simran40
/

webscrapping

Runtime error

+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <title>Smart Web Scraper</title>
+  <style>
+    @import url('https://fonts.googleapis.com/css2?family=Poppins:wght@400;600&display=swap');
+    * { margin: 0; padding: 0; box-sizing: border-box; }
+    body {
+      font-family: 'Poppins', sans-serif;
+      background: linear-gradient(135deg, #283c86, #45a247);
+      height: 100vh;
+      display: flex;
+      flex-direction: column;
+      justify-content: center;
+      align-items: center;
+      color: #fff;
+    }
+    .card {
+      background: rgba(255, 255, 255, 0.15);
+      padding: 40px 50px;
+      border-radius: 20px;
+      backdrop-filter: blur(12px);
+      box-shadow: 0 8px 25px rgba(0,0,0,0.3);
+      text-align: center;
+      animation: fadeIn 1.2s ease-in-out;
+    }
+    h1 {
+      font-size: 42px;
+      margin-bottom: 10px;
+      letter-spacing: 1px;
+    }
+    p {
+      font-size: 18px;
+      margin-bottom: 25px;
+      color: #f2f2f2;
+    }
+    input[type="text"] {
+      width: 380px;
+      padding: 12px;
+      border-radius: 8px;
+      border: none;
+      outline: none;
+      font-size: 16px;
+      margin-bottom: 20px;
+    }
+    .tag-buttons {
+      margin: 10px 0 25px 0;
+    }
+    .tag-buttons button {
+      background: rgba(255,255,255,0.2);
+      border: 1px solid #fff;
+      color: #fff;
+      border-radius: 8px;
+      margin: 5px;
+      padding: 8px 16px;
+      cursor: pointer;
+      font-size: 15px;
+      transition: all 0.3s;
+    }
+    .tag-buttons button:hover,
+    .tag-buttons button.active {
+      background-color: #00c9a7;
+      transform: scale(1.05);
+      color: #222;
+    }
+    input[type="submit"] {
+      padding: 12px 30px;
+      background: linear-gradient(90deg, #00c9ff, #92fe9d);
+      border: none;
+      border-radius: 30px;
+      color: #222;
+      font-size: 17px;
+      cursor: pointer;
+      transition: all 0.3s;
+    }
+    input[type="submit"]:hover {
+      transform: scale(1.07);
+      background: linear-gradient(90deg, #92fe9d, #00c9ff);
+    }
+    footer {
+      position: absolute;
+      bottom: 15px;
+      color: #e0e0e0;
+      font-size: 14px;
+    }
+    @keyframes fadeIn {
+      from {opacity: 0; transform: translateY(40px);}
+      to {opacity: 1; transform: translateY(0);}
+    }
+  </style>
+  <script>
+    function setTag(tagName) {
+      document.getElementById('selectedTag').value = tagName;
+      const buttons = document.querySelectorAll('.tag-buttons button');
+      buttons.forEach(btn => btn.classList.remove('active'));
+      event.target.classList.add('active');
+    }
+  </script>
+</head>
+<body>
+  <div class="card">
+    <h1>🌐 Smart Web Scraper</h1>
+    <p>Enter a website and select which tag you want to scrape (H1, H2, etc.)</p>
+    <form method="POST" action="/">
+      <input type="text" name="url" placeholder="https://indianexpress.com/" required><br>
+      <div class="tag-buttons">
+        <button type="button" onclick="setTag('h1')">H1</button>
+        <button type="button" onclick="setTag('h2')" class="active">H2</button>
+        <button type="button" onclick="setTag('h3')">H3</button>
+        <button type="button" onclick="setTag('p')">P</button>
+        <button type="button" onclick="setTag('span')">SPAN</button>
+      </div>
+      <input type="hidden" name="tag" id="selectedTag" value="h2">
+      <input type="submit" value="Scrape Now 🚀">
+    </form>
+  </div>
+  <footer>Made with ❤️ using Flask & BeautifulSoup</footer>
+</body>
+</html>

__pycache__/templates/result.html ADDED Viewed

	@@ -0,0 +1,89 @@

+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <title>Scraped Results</title>
+  <style>
+    @import url('https://fonts.googleapis.com/css2?family=Poppins:wght@400;600&display=swap');
+    body {
+      font-family: 'Poppins', sans-serif;
+      background: linear-gradient(135deg, #1a2a6c, #b21f1f, #fdbb2d);
+      color: #fff;
+      min-height: 100vh;
+      margin: 0;
+      text-align: center;
+      padding: 40px 0;
+    }
+    h1 {
+      margin-bottom: 15px;
+      font-size: 30px;
+    }
+    h2 {
+      font-size: 18px;
+      margin-bottom: 25px;
+      color: #ffecb3;
+    }
+    .results {
+      display: flex;
+      flex-direction: column;
+      align-items: center;
+      gap: 10px;
+      width: 85%;
+      margin: auto;
+    }
+    .item {
+      background: rgba(255,255,255,0.15);
+      backdrop-filter: blur(10px);
+      border-radius: 12px;
+      padding: 12px 20px;
+      text-align: left;
+      width: 80%;
+      transition: transform 0.3s, box-shadow 0.3s;
+    }
+    .item:hover {
+      transform: scale(1.03);
+      box-shadow: 0 4px 15px rgba(0,0,0,0.3);
+    }
+    .buttons {
+      margin-top: 30px;
+    }
+    a, button {
+      text-decoration: none;
+      border: none;
+      color: #fff;
+      background: linear-gradient(90deg, #00c6ff, #0072ff);
+      padding: 10px 25px;
+      border-radius: 25px;
+      margin: 10px;
+      font-size: 16px;
+      cursor: pointer;
+      transition: transform 0.2s, background 0.3s;
+    }
+    a:hover, button:hover {
+      transform: scale(1.05);
+      background: linear-gradient(90deg, #0072ff, #00c6ff);
+    }
+  </style>
+</head>
+<body>
+  <h1>📰 Scraped Data from {{ url }}</h1>
+  <h2>Selected Tag: &lt;{{ tag.upper() }}&gt;</h2>
+  <div class="results">
+    {% if titles %}
+      {% for title in titles %}
+        <div class="item">{{ title }}</div>
+      {% endfor %}
+    {% else %}
+      <p>No data found or error occurred.</p>
+    {% endif %}
+  </div>
+  <div class="buttons">
+    <a href="/">⬅ Home</a>
+    <form method="POST" action="/" style="display:inline;">
+      <input type="hidden" name="url" value="{{ url }}">
+      <input type="hidden" name="tag" value="{{ tag }}">
+      <button type="submit">🔄 Re-scrape</button>
+    </form>
+  </div>
+</body>
+</html>

main.py ADDED Viewed

	@@ -0,0 +1,16 @@

+from flask import Flask, render_template, request
+from scraper import scrape_blog
+app = Flask(__name__)
+@app.route('/', methods=['GET', 'POST'])
+def home():
+    if request.method == 'POST':
+        url = request.form.get('url')
+        tag = request.form.get('tag') or 'h2'
+        data = scrape_blog(url, tag)
+        return render_template('result.html', titles=data, url=url, tag=tag)
+    return render_template('index.html')
+if __name__ == '__main__':
+    app.run(debug=True)

requirements.txt ADDED Viewed

	@@ -0,0 +1,3 @@

+flask
+requests
+beautifulsoup4

scraper.py ADDED Viewed

	@@ -0,0 +1,29 @@

+import requests
+from bs4 import BeautifulSoup
+def scrape_blog(url="https://indianexpress.com/", tag="h2"):
+    try:
+        headers = {
+            "User-Agent": (
+                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/91.0.4472.124 Safari/537.36"
+            )
+        }
+        response = requests.get(url, headers=headers, timeout=10)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, "html.parser")
+        titles = []
+        for element in soup.find_all(tag):
+            text = element.get_text(strip=True)
+            if text and len(text) > 20:
+                titles.append(text)
+        clean_titles = list(dict.fromkeys(titles))
+        if not clean_titles:
+            return [f"No <{tag}> content found. Try another tag."]
+        return clean_titles[:25]
+    except Exception as e:
+        return [f"Error: {e}"]