Spaces:

MarcRyan
/

web-crawler

Running

App Files Files Community

MarcRyan commited on May 19, 2025

Commit

49e2901

verified ·

1 Parent(s): 6eb6a36

Add 3 files

Browse files

Files changed (3) hide show

README.md +7 -5
index.html +223 -19
prompts.txt +2 -0

README.md CHANGED Viewed

@@ -1,10 +1,12 @@
 ---
-title: Web Crawler
-emoji: 😻
-colorFrom: red
-colorTo: blue
 sdk: static
 pinned: false
 ---
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

 ---
+title: web-crawler
+emoji: 🐳
+colorFrom: purple
+colorTo: yellow
 sdk: static
 pinned: false
+tags:
+  - deepsite
 ---
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

index.html CHANGED Viewed

@@ -1,19 +1,223 @@
-<!doctype html>
-<html>
-	<head>
-		<meta charset="utf-8" />
-		<meta name="viewport" content="width=device-width" />
-		<title>My static Space</title>
-		<link rel="stylesheet" href="style.css" />
-	</head>
-	<body>
-		<div class="card">
-			<h1>Welcome to your static Space!</h1>
-			<p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
-			<p>
-				Also don't forget to check the
-				<a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
-			</p>
-		</div>
-	</body>
-</html>

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Real Web Crawler Interface</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+    <style>
+        .loading-spinner {
+            border: 4px solid rgba(0, 0, 0, 0.1);
+            border-radius: 50%;
+            border-top: 4px solid #3b82f6;
+            width: 30px;
+            height: 30px;
+            animation: spin 1s linear infinite;
+            margin: 0 auto;
+        }
+        @keyframes spin {
+            0% { transform: rotate(0deg); }
+            100% { transform: rotate(360deg); }
+        }
+    </style>
+</head>
+<body class="bg-gray-50 min-h-screen">
+    <div class="container mx-auto px-4 py-8">
+        <header class="text-center mb-12">
+            <h1 class="text-4xl font-bold text-blue-600 mb-2">
+                <i class="fas fa-spider mr-2"></i> Real Web Crawler
+            </h1>
+            <p class="text-gray-600 max-w-2xl mx-auto">
+                Enter a zip code and keywords to search for business contact information.
+                <br><span class="text-sm text-red-500">Note: Requires backend API implementation</span>
+            </p>
+        </header>
+        <div class="bg-white rounded-xl shadow-lg p-6 max-w-4xl mx-auto mb-12">
+            <form id="crawlerForm" class="space-y-6">
+                <div>
+                    <label for="zipCode" class="block text-sm font-medium text-gray-700 mb-1">
+                        <i class="fas fa-map-marker-alt mr-1 text-blue-500"></i> Zip Code
+                    </label>
+                    <input type="text" id="zipCode" name="zipCode"
+                           class="w-full px-4 py-2 border border-gray-300 rounded-lg focus:ring-2 focus:ring-blue-500 focus:border-blue-500 transition"
+                           placeholder="e.g. 90210" required>
+                </div>
+                <div class="grid grid-cols-1 md:grid-cols-3 gap-4">
+                    <div>
+                        <label for="keyword1" class="block text-sm font-medium text-gray-700 mb-1">
+                            <i class="fas fa-key mr-1 text-blue-500"></i> Keyword 1
+                        </label>
+                        <input type="text" id="keyword1" name="keyword1"
+                               class="w-full px-4 py-2 border border-gray-300 rounded-lg focus:ring-2 focus:ring-blue-500 focus:border-blue-500 transition"
+                               placeholder="e.g. dentist" required>
+                    </div>
+                    <div>
+                        <label for="keyword2" class="block text-sm font-medium text-gray-700 mb-1">
+                            <i class="fas fa-key mr-1 text-blue-500"></i> Keyword 2
+                        </label>
+                        <input type="text" id="keyword2" name="keyword2"
+                               class="w-full px-4 py-2 border border-gray-300 rounded-lg focus:ring-2 focus:ring-blue-500 focus:border-blue-500 transition"
+                               placeholder="e.g. doctor">
+                    </div>
+                    <div>
+                        <label for="keyword3" class="block text-sm font-medium text-gray-700 mb-1">
+                            <i class="fas fa-key mr-1 text-blue-500"></i> Keyword 3
+                        </label>
+                        <input type="text" id="keyword3" name="keyword3"
+                               class="w-full px-4 py-2 border border-gray-300 rounded-lg focus:ring-2 focus:ring-blue-500 focus:border-blue-500 transition"
+                               placeholder="e.g. lawyer">
+                    </div>
+                </div>
+                <div class="flex items-center">
+                    <input type="checkbox" id="deepSearch" name="deepSearch" class="h-4 w-4 text-blue-600 focus:ring-blue-500 border-gray-300 rounded">
+                    <label for="deepSearch" class="ml-2 block text-sm text-gray-700">
+                        Deep Search (crawl more pages, takes longer)
+                    </label>
+                </div>
+                <button type="submit" id="searchButton" class="w-full bg-blue-600 hover:bg-blue-700 text-white font-medium py-3 px-4 rounded-lg transition flex items-center justify-center">
+                    <i class="fas fa-search mr-2"></i> Start Crawling
+                </button>
+            </form>
+        </div>
+        <div id="loadingIndicator" class="hidden text-center py-8">
+            <div class="loading-spinner mb-4"></div>
+            <p class="text-gray-600">Crawling websites. This may take a few minutes...</p>
+            <p class="text-sm text-gray-500 mt-2">Currently processing: <span id="currentUrl" class="font-medium">example.com</span></p>
+        </div>
+        <div id="resultsContainer" class="hidden">
+            <div class="flex justify-between items-center mb-6">
+                <h2 class="text-2xl font-bold text-gray-800">
+                    <i class="fas fa-list-ul mr-2 text-blue-500"></i> Crawl Results
+                </h2>
+                <div class="flex items-center space-x-4">
+                    <div class="bg-blue-100 text-blue-800 px-3 py-1 rounded-full text-sm font-medium">
+                        Found: <span id="resultCount">0</span> items
+                    </div>
+                    <button id="exportBtn" class="bg-green-100 text-green-800 px-3 py-1 rounded-full text-sm font-medium hover:bg-green-200 transition flex items-center">
+                        <i class="fas fa-file-export mr-1"></i> Export CSV
+                    </button>
+                </div>
+            </div>
+            <div id="resultsList" class="space-y-4">
+                <!-- Results will be inserted here by JavaScript -->
+            </div>
+        </div>
+        <div id="noResults" class="hidden text-center py-12">
+            <div class="mx-auto w-24 h-24 bg-gray-100 rounded-full flex items-center justify-center mb-4">
+                <i class="fas fa-exclamation-triangle text-3xl text-yellow-500"></i>
+            </div>
+            <h3 class="text-xl font-medium text-gray-700 mb-2">No Results Found</h3>
+            <p class="text-gray-500 max-w-md mx-auto">
+                We couldn't find any matching results for your search criteria.
+            </p>
+        </div>
+    </div>
+    <script>
+        document.addEventListener('DOMContentLoaded', function() {
+            const crawlerForm = document.getElementById('crawlerForm');
+            const loadingIndicator = document.getElementById('loadingIndicator');
+            const resultsContainer = document.getElementById('resultsContainer');
+            const noResults = document.getElementById('noResults');
+            const resultsList = document.getElementById('resultsList');
+            const resultCount = document.getElementById('resultCount');
+            const currentUrl = document.getElementById('currentUrl');
+            crawlerForm.addEventListener('submit', async function(e) {
+                e.preventDefault();
+                const zipCode = document.getElementById('zipCode').value.trim();
+                const keyword1 = document.getElementById('keyword1').value.trim();
+                const keyword2 = document.getElementById('keyword2').value.trim();
+                const keyword3 = document.getElementById('keyword3').value.trim();
+                const deepSearch = document.getElementById('deepSearch').checked;
+                const keywords = [keyword1, keyword2, keyword3].filter(k => k);
+                if (!zipCode) {
+                    alert('Please enter a zip code');
+                    return;
+                }
+                if (keywords.length === 0) {
+                    alert('Please enter at least one keyword');
+                    return;
+                }
+                // Show loading state
+                loadingIndicator.classList.remove('hidden');
+                resultsContainer.classList.add('hidden');
+                noResults.classList.add('hidden');
+                try {
+                    // In a real implementation, this would call your backend API
+                    // const response = await fetch('/api/crawl', {
+                    //     method: 'POST',
+                    //     headers: {
+                    //         'Content-Type': 'application/json',
+                    //     },
+                    //     body: JSON.stringify({
+                    //         zipCode,
+                    //         keywords,
+                    //         deepSearch
+                    //     })
+                    // });
+                    // const data = await response.json();
+                    // For demonstration, we'll simulate an API delay
+                    await new Promise(resolve => setTimeout(resolve, 3000));
+                    // This is where you would process real data from your backend
+                    // displayResults(data.results);
+                    // For now, show a message about backend implementation
+                    resultsList.innerHTML = `
+                        <div class="bg-white p-6 rounded-lg shadow">
+                            <h3 class="text-lg font-medium text-gray-800 mb-2">
+                                <i class="fas fa-code mr-2 text-blue-500"></i> Backend Implementation Required
+                            </h3>
+                            <p class="text-gray-600">
+                                This interface is ready to connect to a backend API that would perform the actual web crawling.
+                                To implement this, you would need to:
+                            </p>
+                            <ul class="list-disc pl-5 mt-2 space-y-1 text-gray-600">
+                                <li>Set up a server with Node.js, Python, or another backend language</li>
+                                <li>Implement proper web crawling logic respecting robots.txt</li>
+                                <li>Add rate limiting to avoid being blocked</li>
+                                <li>Implement data parsing for emails, phone numbers, etc.</li>
+                                <li>Set up the API endpoint this frontend would call</li>
+                            </ul>
+                            <div class="mt-4 p-4 bg-blue-50 rounded border border-blue-200">
+                                <p class="text-blue-800">
+                                    <i class="fas fa-info-circle mr-2"></i>
+                                    The search parameters received were:<br>
+                                    Zip Code: ${zipCode}<br>
+                                    Keywords: ${keywords.join(', ')}<br>
+                                    Deep Search: ${deepSearch ? 'Yes' : 'No'}
+                                </p>
+                            </div>
+                        </div>
+                    `;
+                    resultsContainer.classList.remove('hidden');
+                    loadingIndicator.classList.add('hidden');
+                } catch (error) {
+                    console.error('Error:', error);
+                    alert('An error occurred. Check console for details.');
+                    loadingIndicator.classList.add('hidden');
+                }
+            });
+        });
+    </script>
+<p style="border-radius: 8px; text-align: center; font-size: 12px; color: #fff; margin-top: 16px;position: fixed; left: 8px; bottom: 8px; z-index: 10; background: rgba(0, 0, 0, 0.8); padding: 4px 8px;">Made with <img src="https://enzostvs-deepsite.hf.space/logo.svg" alt="DeepSite Logo" style="width: 16px; height: 16px; vertical-align: middle;display:inline-block;margin-right:3px;filter:brightness(0) invert(1);"><a href="https://enzostvs-deepsite.hf.space" style="color: #fff;text-decoration: underline;" target="_blank" >DeepSite</a> - 🧬 <a href="https://enzostvs-deepsite.hf.space?remix=MarcRyan/web-crawler" style="color: #fff;text-decoration: underline;" target="_blank" >Remix</a></p></body>
+</html>

prompts.txt ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ lets build a webcrawler where i input a zip code and array of 3 keywords inputs and it outputs a list of all the emails and names and phone numbers and weblinks that are discovered during the crawl
2	+ ENSURE THE RESULTS ARE REAL LIFE AND TRUE FUNCTIONING DATA THAT IS REAL LIFE DATA AND NOT SIMULATED