Add Crawl4AI Assistant Chrome Extension

- Created manifest.json for the Crawl4AI Assistant extension.
- Added popup HTML, CSS, and JS files for the extension interface.
- Included icons and favicon for the extension.
- Implemented functionality for schema capture and code generation.
- Updated index.md to reflect the availability of the new extension.
- Enhanced LLM Context Builder layout and styles for consistency.
- Adjusted global styles for better branding and responsiveness.
This commit is contained in:
UncleCode
2025-06-08 18:34:05 +08:00
parent 6f3a0ea38e
commit 926592649e
32 changed files with 3056 additions and 36 deletions

View File

@@ -4,7 +4,11 @@
"Bash(cd:*)",
"Bash(python3:*)",
"Bash(python:*)",
"Bash(grep:*)"
"Bash(grep:*)",
"Bash(mkdir:*)",
"Bash(cp:*)",
"Bash(rm:*)",
"Bash(true)"
]
},
"enableAllProjectMcpServers": false

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@@ -0,0 +1,123 @@
# Crawl4AI Chrome Extension
Visual schema and script builder for Crawl4AI - Build extraction schemas by clicking on webpage elements!
## 🚀 Features
- **Visual Schema Builder**: Click on elements to build extraction schemas
- **Smart Element Selection**: Container and field selection with visual feedback
- **Code Generation**: Generates complete Python code with LLM integration
- **Beautiful Dark UI**: Consistent with Crawl4AI's design language
- **One-Click Download**: Get your generated code instantly
## 📦 Installation
### Method 1: Load Unpacked Extension (Recommended for Development)
1. Open Chrome and navigate to `chrome://extensions/`
2. Enable "Developer mode" in the top right corner
3. Click "Load unpacked"
4. Select the `crawl4ai-assistant` folder
5. The extension icon (🚀🤖) will appear in your toolbar
### Method 2: Generate Icons First
If you want proper icons:
1. Open `icons/generate_icons.html` in your browser
2. Right-click each canvas and save as:
- `icon-16.png`
- `icon-48.png`
- `icon-128.png`
3. Then follow Method 1 above
## 🎯 How to Use
### Building a Schema
1. **Navigate to any website** you want to extract data from
2. **Click the Crawl4AI extension icon** in your toolbar
3. **Click "Schema Builder"** to start the capture mode
4. **Select a container element**:
- Hover over elements (they'll highlight in blue)
- Click on a repeating container (e.g., product card, article block)
5. **Select fields within the container**:
- Elements will now highlight in green
- Click on each piece of data you want to extract
- Name each field (e.g., "title", "price", "description")
6. **Generate the code**:
- Click "Generate Code" in the extension popup
- A Python file will automatically download
### Running the Generated Code
The downloaded Python file contains:
```python
# 1. The HTML snippet of your selected container
HTML_SNIPPET = """..."""
# 2. The extraction query based on your selections
EXTRACTION_QUERY = """..."""
# 3. Functions to generate and test the schema
async def generate_schema():
# Generates the extraction schema using LLM
async def test_extraction():
# Tests the schema on the actual website
```
To use it:
1. Install Crawl4AI: `pip install crawl4ai`
2. Run the script: `python crawl4ai_schema_*.py`
3. The script will generate a `generated_schema.json` file
4. Use this schema in your Crawl4AI projects!
## 🎨 Visual Feedback
- **Blue dashed outline**: Container selection mode
- **Green dashed outline**: Field selection mode
- **Solid blue outline**: Selected container
- **Solid green outline**: Selected fields
- **Floating toolbar**: Shows current mode and selection status
## ⌨️ Keyboard Shortcuts
- **ESC**: Cancel current capture session
## 🔧 Technical Details
- Built with Manifest V3 for security and performance
- Pure client-side - no data sent to external servers
- Generates code that uses Crawl4AI's LLM integration
- Smart selector generation prioritizes stable attributes
## 🐛 Troubleshooting
### Extension doesn't load
- Make sure you're in Developer Mode
- Check the console for any errors
- Ensure all files are in the correct directories
### Can't select elements
- Some websites may block extensions
- Try refreshing the page
- Make sure you clicked "Schema Builder" first
### Generated code doesn't work
- Ensure you have Crawl4AI installed
- Check that you have an LLM API key configured
- Make sure the website structure hasn't changed
## 🤝 Contributing
This extension is part of the Crawl4AI project. Contributions are welcome!
- Report issues: [GitHub Issues](https://github.com/unclecode/crawl4ai/issues)
- Join discussion: [Discord](https://discord.gg/crawl4ai)
## 📄 License
Same as Crawl4AI - see main project for details.

View File

@@ -0,0 +1,539 @@
/* Crawl4AI Assistant Landing Page Styles */
/* Font Face Definitions */
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
font-display: swap;
}
:root {
--primary-green: #0fbbaa;
--primary-pink: #f380f5;
--bg-dark: #070708;
--bg-secondary: #1a1a1a;
--bg-tertiary: #3f3f44;
--text-primary: #e8e9ed;
--text-secondary: #a3abba;
--text-accent: #d5cec0;
--border-color: #3f3f44;
--code-bg: #070708;
--font-primary: 'Dank Mono', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, monospace;
--font-code: 'Dank Mono', 'Monaco', 'Menlo', 'Consolas', monospace;
}
* {
box-sizing: border-box;
margin: 0;
padding: 0;
}
body {
background-color: var(--bg-dark);
color: var(--text-primary);
font-family: var(--font-primary);
line-height: 1.6;
overflow-x: hidden;
}
/* Terminal Container */
.terminal-container {
min-height: 100vh;
display: flex;
flex-direction: column;
}
/* Header */
.header {
background: var(--bg-secondary);
border-bottom: 1px solid var(--border-color);
padding: 1.5rem 0;
position: sticky;
top: 0;
z-index: 100;
backdrop-filter: blur(10px);
background: rgba(26, 26, 26, 0.95);
}
.header-content {
max-width: 1200px;
margin: 0 auto;
padding: 0 2rem;
display: flex;
justify-content: space-between;
align-items: center;
}
.logo-section {
display: flex;
align-items: center;
gap: 1rem;
}
.logo {
width: 48px;
height: 48px;
}
.logo-section h1 {
font-size: 1.75rem;
font-weight: 700;
color: var(--text-primary);
}
.tagline {
font-size: 0.875rem;
color: var(--text-secondary);
margin-top: 0.25rem;
}
.nav-links {
display: flex;
gap: 2rem;
}
.nav-link {
color: var(--text-secondary);
text-decoration: none;
font-size: 0.875rem;
transition: color 0.2s ease;
}
.nav-link:hover {
color: var(--primary-green);
}
/* Content */
.content {
flex: 1;
max-width: 1200px;
margin: 0 auto;
padding: 0 2rem;
width: 100%;
}
/* Video Section */
.video-section {
margin: 3rem 0;
}
.video-wrapper {
position: relative;
border-radius: 12px;
overflow: hidden;
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.6);
border: 1px solid var(--border-color);
}
.demo-video {
width: 100%;
height: auto;
display: block;
}
/* Terminal Windows */
.terminal-window {
background: var(--bg-secondary);
border: 1px solid var(--border-color);
border-radius: 8px;
overflow: hidden;
margin-bottom: 2rem;
box-shadow: 0 4px 16px rgba(0, 0, 0, 0.4);
}
.terminal-header {
background: #2a2a2a;
padding: 0.75rem 1rem;
border-bottom: 1px solid var(--border-color);
display: flex;
align-items: center;
gap: 0.5rem;
}
.terminal-header::before {
content: '';
display: flex;
gap: 8px;
align-items: center;
}
.terminal-header::before {
content: '● ● ●';
color: #ff5f57;
font-size: 12px;
letter-spacing: 8px;
}
.terminal-title {
font-size: 0.875rem;
color: var(--text-secondary);
margin-left: 1rem;
}
.terminal-content {
padding: 2rem;
}
/* Features Grid */
.features-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
gap: 1.5rem;
margin-top: 2rem;
}
.feature-card {
background: var(--bg-tertiary);
padding: 1.5rem;
border-radius: 8px;
border: 1px solid var(--border-color);
transition: all 0.2s ease;
}
.feature-card:hover {
border-color: var(--primary-green);
transform: translateY(-2px);
box-shadow: 0 4px 16px rgba(15, 187, 170, 0.2);
}
.feature-icon {
font-size: 2rem;
margin-bottom: 1rem;
display: block;
}
.feature-card h3 {
font-size: 1.125rem;
margin-bottom: 0.5rem;
color: var(--text-primary);
}
.feature-card p {
font-size: 0.875rem;
color: var(--text-secondary);
}
/* Installation Steps */
.installation-steps {
margin-top: 1.5rem;
}
.step {
display: flex;
gap: 1.5rem;
margin-bottom: 2rem;
align-items: flex-start;
}
.step-number {
background: var(--primary-green);
color: var(--bg-dark);
width: 40px;
height: 40px;
border-radius: 50%;
display: flex;
align-items: center;
justify-content: center;
font-weight: bold;
flex-shrink: 0;
}
.step-content h4 {
margin-bottom: 0.5rem;
color: var(--text-primary);
}
.step-content p {
color: var(--text-secondary);
margin-bottom: 1rem;
}
.download-button {
display: inline-flex;
align-items: center;
gap: 0.75rem;
background: var(--primary-green);
color: var(--bg-dark);
padding: 0.75rem 1.5rem;
border-radius: 6px;
text-decoration: none;
font-weight: 600;
transition: all 0.2s ease;
margin-top: 1rem;
}
.download-button:hover {
background: #1fcbba;
transform: translateY(-2px);
box-shadow: 0 4px 16px rgba(15, 187, 170, 0.3);
}
.button-icon {
font-size: 1.25rem;
}
/* Usage Flow */
.usage-flow {
margin-top: 1.5rem;
}
.usage-step {
background: var(--bg-tertiary);
padding: 1.5rem;
border-radius: 8px;
margin-bottom: 1rem;
border: 1px solid var(--border-color);
}
.usage-header {
display: flex;
align-items: center;
gap: 1rem;
margin-bottom: 0.75rem;
}
.usage-icon {
font-size: 1.5rem;
}
.usage-step h4 {
margin: 0;
color: var(--text-primary);
}
.usage-step p {
color: var(--text-secondary);
margin-bottom: 0.5rem;
}
/* Code Snippets */
.code-snippet {
background: var(--code-bg);
padding: 0.75rem;
border-radius: 4px;
margin-top: 0.5rem;
font-family: var(--font-code);
font-size: 0.875rem;
border: 1px solid var(--border-color);
}
.comment {
color: var(--text-secondary);
font-style: italic;
}
/* Code Section */
pre {
margin: 0;
overflow-x: auto;
}
code {
font-family: var(--font-code);
font-size: 0.875rem;
line-height: 1.6;
}
.keyword {
color: var(--primary-green);
font-weight: bold;
}
.string {
color: var(--primary-pink);
}
.function {
color: #ff3c74;
}
/* Coming Soon Section */
.coming-soon-section {
margin: 4rem 0;
}
.coming-soon-section h2 {
font-size: 2rem;
margin-bottom: 2rem;
color: var(--text-primary);
}
.intro-text {
font-size: 1.125rem;
color: var(--text-secondary);
margin-bottom: 2rem;
}
.coming-features {
display: grid;
gap: 1.5rem;
margin-top: 2rem;
}
.coming-feature {
background: var(--bg-tertiary);
padding: 2rem;
border-radius: 12px;
border: 1px solid var(--border-color);
transition: all 0.3s ease;
}
.coming-feature:hover {
border-color: var(--primary-green);
transform: translateY(-2px);
box-shadow: 0 8px 24px rgba(15, 187, 170, 0.2);
}
.feature-header {
display: flex;
align-items: center;
gap: 1rem;
margin-bottom: 1rem;
}
.feature-badge {
background: var(--primary-green);
color: var(--bg-dark);
padding: 0.25rem 0.75rem;
border-radius: 20px;
font-size: 0.75rem;
font-weight: 600;
text-transform: uppercase;
}
.coming-feature h3 {
font-size: 1.25rem;
color: var(--text-primary);
margin: 0;
}
.coming-feature p {
color: var(--text-secondary);
margin-bottom: 1rem;
line-height: 1.6;
}
.feature-preview {
background: var(--bg-secondary);
padding: 1rem;
border-radius: 6px;
font-family: var(--font-code);
font-size: 0.875rem;
color: var(--text-accent);
border: 1px solid var(--border-color);
}
.stay-tuned {
text-align: center;
margin-top: 3rem;
padding: 2rem;
background: var(--bg-tertiary);
border-radius: 12px;
border: 1px solid var(--border-color);
}
.stay-tuned p {
font-size: 1.125rem;
color: var(--text-primary);
}
.stay-tuned a {
color: var(--primary-green);
text-decoration: none;
font-weight: 600;
}
.stay-tuned a:hover {
text-decoration: underline;
}
/* Footer */
.footer {
background: var(--bg-secondary);
border-top: 1px solid var(--border-color);
margin-top: 4rem;
padding: 3rem 0 2rem;
}
.footer-content {
max-width: 1200px;
margin: 0 auto;
padding: 0 2rem;
display: grid;
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
gap: 3rem;
}
.footer-section h4 {
margin-bottom: 1rem;
color: var(--text-primary);
}
.footer-section ul {
list-style: none;
}
.footer-section li {
margin-bottom: 0.5rem;
}
.footer-section a {
color: var(--text-secondary);
text-decoration: none;
transition: color 0.2s ease;
}
.footer-section a:hover {
color: var(--primary-green);
}
.footer-bottom {
text-align: center;
margin-top: 2rem;
padding-top: 2rem;
border-top: 1px solid var(--border-color);
color: var(--text-secondary);
}
/* Responsive */
@media (max-width: 768px) {
.header-content {
flex-direction: column;
gap: 1.5rem;
}
.nav-links {
gap: 1rem;
}
.features-grid {
grid-template-columns: 1fr;
}
.step {
flex-direction: column;
gap: 1rem;
}
.coming-soon-section h2 {
font-size: 1.5rem;
}
}

View File

@@ -0,0 +1,39 @@
// Service worker for Crawl4AI Assistant
// Handle messages from content script
chrome.runtime.onMessage.addListener((message, sender, sendResponse) => {
if (message.action === 'downloadCode') {
try {
// Create a data URL for the Python code
const dataUrl = 'data:text/plain;charset=utf-8,' + encodeURIComponent(message.code);
// Download the file
chrome.downloads.download({
url: dataUrl,
filename: message.filename || 'crawl4ai_schema.py',
saveAs: true
}, (downloadId) => {
if (chrome.runtime.lastError) {
console.error('Download failed:', chrome.runtime.lastError);
sendResponse({ success: false, error: chrome.runtime.lastError.message });
} else {
console.log('Download started with ID:', downloadId);
sendResponse({ success: true, downloadId: downloadId });
}
});
} catch (error) {
console.error('Error creating download:', error);
sendResponse({ success: false, error: error.message });
}
return true; // Keep the message channel open for async response
}
return false;
});
// Clean up on extension install/update
chrome.runtime.onInstalled.addListener(() => {
// Clear any stored state
chrome.storage.local.clear();
});

View File

@@ -0,0 +1,738 @@
// Content script for Crawl4AI Assistant
class SchemaBuilder {
constructor() {
this.mode = null;
this.container = null;
this.fields = [];
this.overlay = null;
this.toolbar = null;
this.highlightBox = null;
this.selectedElements = new Set();
this.isPaused = false;
this.codeModal = null;
this.handleMouseMove = this.handleMouseMove.bind(this);
this.handleClick = this.handleClick.bind(this);
this.handleKeyPress = this.handleKeyPress.bind(this);
}
start() {
this.mode = 'container';
this.createOverlay();
this.createToolbar();
this.attachEventListeners();
this.updateToolbar();
}
stop() {
this.detachEventListeners();
this.overlay?.remove();
this.toolbar?.remove();
this.highlightBox?.remove();
this.removeAllHighlights();
this.mode = null;
this.container = null;
this.fields = [];
this.selectedElements.clear();
}
createOverlay() {
// Create highlight box
this.highlightBox = document.createElement('div');
this.highlightBox.className = 'c4ai-highlight-box';
document.body.appendChild(this.highlightBox);
}
createToolbar() {
this.toolbar = document.createElement('div');
this.toolbar.className = 'c4ai-toolbar';
this.toolbar.innerHTML = `
<div class="c4ai-toolbar-titlebar">
<div class="c4ai-titlebar-dots">
<button class="c4ai-dot c4ai-dot-close" id="c4ai-close"></button>
<button class="c4ai-dot c4ai-dot-minimize"></button>
<button class="c4ai-dot c4ai-dot-maximize"></button>
</div>
<img src="${chrome.runtime.getURL('icons/icon-16.png')}" class="c4ai-titlebar-icon" alt="Crawl4AI">
<div class="c4ai-titlebar-title">Crawl4AI Schema Builder</div>
</div>
<div class="c4ai-toolbar-content">
<div class="c4ai-toolbar-status">
<div class="c4ai-status-item">
<span class="c4ai-status-label">Mode:</span>
<span class="c4ai-status-value" id="c4ai-mode">Select Container</span>
</div>
<div class="c4ai-status-item">
<span class="c4ai-status-label">Container:</span>
<span class="c4ai-status-value" id="c4ai-container">Not selected</span>
</div>
</div>
<div class="c4ai-fields-list" id="c4ai-fields-list" style="display: none;">
<div class="c4ai-fields-header">Selected Fields:</div>
<ul class="c4ai-fields-items" id="c4ai-fields-items"></ul>
</div>
<div class="c4ai-toolbar-hint" id="c4ai-hint">
Click on a container element (e.g., product card, article, etc.)
</div>
<div class="c4ai-toolbar-actions">
<button id="c4ai-pause" class="c4ai-action-btn c4ai-pause-btn">
<span class="c4ai-pause-icon">⏸</span> Pause
</button>
<button id="c4ai-generate" class="c4ai-action-btn c4ai-generate-btn">
<span class="c4ai-generate-icon">⚡</span> Generate Code
</button>
</div>
</div>
`;
document.body.appendChild(this.toolbar);
// Add event listeners for toolbar buttons
document.getElementById('c4ai-pause').addEventListener('click', () => this.togglePause());
document.getElementById('c4ai-generate').addEventListener('click', () => this.stopAndGenerate());
document.getElementById('c4ai-close').addEventListener('click', () => this.stop());
// Make toolbar draggable
this.makeDraggable(this.toolbar);
}
attachEventListeners() {
document.addEventListener('mousemove', this.handleMouseMove, true);
document.addEventListener('click', this.handleClick, true);
document.addEventListener('keydown', this.handleKeyPress, true);
}
detachEventListeners() {
document.removeEventListener('mousemove', this.handleMouseMove, true);
document.removeEventListener('click', this.handleClick, true);
document.removeEventListener('keydown', this.handleKeyPress, true);
}
handleMouseMove(e) {
if (this.isPaused) return;
const element = document.elementFromPoint(e.clientX, e.clientY);
if (element && !this.isOurElement(element)) {
this.highlightElement(element);
}
}
handleClick(e) {
if (this.isPaused) return;
const element = e.target;
if (this.isOurElement(element)) {
return;
}
e.preventDefault();
e.stopPropagation();
if (this.mode === 'container') {
this.selectContainer(element);
} else if (this.mode === 'field') {
this.selectField(element);
}
}
handleKeyPress(e) {
if (e.key === 'Escape') {
this.stop();
}
}
isOurElement(element) {
return element.classList.contains('c4ai-highlight-box') ||
element.classList.contains('c4ai-toolbar') ||
element.closest('.c4ai-toolbar') ||
element.closest('.c4ai-field-dialog') ||
element.closest('.c4ai-code-modal');
}
makeDraggable(element) {
let isDragging = false;
let startX, startY, initialX, initialY;
const titlebar = element.querySelector('.c4ai-toolbar-titlebar');
titlebar.addEventListener('mousedown', (e) => {
// Don't drag if clicking on buttons
if (e.target.classList.contains('c4ai-dot')) return;
isDragging = true;
startX = e.clientX;
startY = e.clientY;
const rect = element.getBoundingClientRect();
initialX = rect.left;
initialY = rect.top;
element.style.transition = 'none';
titlebar.style.cursor = 'grabbing';
});
document.addEventListener('mousemove', (e) => {
if (!isDragging) return;
const deltaX = e.clientX - startX;
const deltaY = e.clientY - startY;
element.style.left = `${initialX + deltaX}px`;
element.style.top = `${initialY + deltaY}px`;
element.style.right = 'auto';
});
document.addEventListener('mouseup', () => {
if (isDragging) {
isDragging = false;
element.style.transition = '';
titlebar.style.cursor = 'grab';
}
});
}
togglePause() {
this.isPaused = !this.isPaused;
const pauseBtn = document.getElementById('c4ai-pause');
if (this.isPaused) {
pauseBtn.innerHTML = '<span class="c4ai-play-icon">▶</span> Resume';
pauseBtn.classList.add('c4ai-paused');
this.highlightBox.style.display = 'none';
} else {
pauseBtn.innerHTML = '<span class="c4ai-pause-icon">⏸</span> Pause';
pauseBtn.classList.remove('c4ai-paused');
}
}
stopAndGenerate() {
if (!this.container || this.fields.length === 0) {
alert('Please select a container and at least one field before generating code.');
return;
}
const code = this.generateCode();
this.showCodeModal(code);
}
highlightElement(element) {
const rect = element.getBoundingClientRect();
this.highlightBox.style.cssText = `
left: ${rect.left + window.scrollX}px;
top: ${rect.top + window.scrollY}px;
width: ${rect.width}px;
height: ${rect.height}px;
display: block;
`;
if (this.mode === 'container') {
this.highlightBox.className = 'c4ai-highlight-box c4ai-container-mode';
} else {
this.highlightBox.className = 'c4ai-highlight-box c4ai-field-mode';
}
}
selectContainer(element) {
// Remove previous container highlight
if (this.container) {
this.container.element.classList.remove('c4ai-selected-container');
}
this.container = {
element: element,
html: element.outerHTML,
selector: this.generateSelector(element),
tagName: element.tagName.toLowerCase()
};
element.classList.add('c4ai-selected-container');
this.mode = 'field';
this.updateToolbar();
this.updateStats();
}
selectField(element) {
// Don't select the container itself
if (element === this.container.element) {
return;
}
// Check if already selected - if so, deselect it
if (this.selectedElements.has(element)) {
this.deselectField(element);
return;
}
// Must be inside the container
if (!this.container.element.contains(element)) {
return;
}
this.showFieldDialog(element);
}
deselectField(element) {
// Remove from fields array
this.fields = this.fields.filter(f => f.element !== element);
// Remove from selected elements set
this.selectedElements.delete(element);
// Remove visual selection
element.classList.remove('c4ai-selected-field');
// Update UI
this.updateToolbar();
this.updateStats();
}
showFieldDialog(element) {
const dialog = document.createElement('div');
dialog.className = 'c4ai-field-dialog';
const rect = element.getBoundingClientRect();
dialog.style.cssText = `
left: ${rect.left + window.scrollX}px;
top: ${rect.bottom + window.scrollY + 10}px;
`;
dialog.innerHTML = `
<div class="c4ai-field-dialog-content">
<h4>Name this field:</h4>
<input type="text" id="c4ai-field-name" placeholder="e.g., title, price, description" autofocus>
<div class="c4ai-field-preview">
<strong>Content:</strong> ${element.textContent.trim().substring(0, 50)}...
</div>
<div class="c4ai-field-actions">
<button id="c4ai-field-save">Save</button>
<button id="c4ai-field-cancel">Cancel</button>
</div>
</div>
`;
document.body.appendChild(dialog);
const input = dialog.querySelector('#c4ai-field-name');
const saveBtn = dialog.querySelector('#c4ai-field-save');
const cancelBtn = dialog.querySelector('#c4ai-field-cancel');
const save = () => {
const fieldName = input.value.trim();
if (fieldName) {
this.fields.push({
name: fieldName,
value: element.textContent.trim(),
element: element,
selector: this.generateSelector(element, this.container.element)
});
element.classList.add('c4ai-selected-field');
this.selectedElements.add(element);
this.updateToolbar();
this.updateStats();
}
dialog.remove();
};
const cancel = () => {
dialog.remove();
};
saveBtn.addEventListener('click', save);
cancelBtn.addEventListener('click', cancel);
input.addEventListener('keypress', (e) => {
if (e.key === 'Enter') save();
if (e.key === 'Escape') cancel();
});
input.focus();
}
generateSelector(element, context = document) {
// Try to generate a robust selector
if (element.id) {
return `#${CSS.escape(element.id)}`;
}
// Check for data attributes (most stable)
const dataAttrs = ['data-testid', 'data-id', 'data-test', 'data-cy'];
for (const attr of dataAttrs) {
const value = element.getAttribute(attr);
if (value) {
return `[${attr}="${value}"]`;
}
}
// Check for aria-label
if (element.getAttribute('aria-label')) {
return `[aria-label="${element.getAttribute('aria-label')}"]`;
}
// Try semantic HTML elements with text
const tagName = element.tagName.toLowerCase();
if (['button', 'a', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'].includes(tagName)) {
const text = element.textContent.trim();
if (text && text.length < 50) {
// Use tag name with partial text match
return `${tagName}`;
}
}
// Check for simple, non-utility classes
const classes = Array.from(element.classList)
.filter(c => !c.startsWith('c4ai-')) // Exclude our classes
.filter(c => !c.includes('[') && !c.includes('(') && !c.includes(':')) // Exclude utility classes
.filter(c => c.length < 30); // Exclude very long classes
if (classes.length > 0 && classes.length <= 3) {
const selector = classes.map(c => `.${CSS.escape(c)}`).join('');
try {
if (context.querySelectorAll(selector).length === 1) {
return selector;
}
} catch (e) {
// Invalid selector, continue
}
}
// Use nth-child with simple parent tag
const parent = element.parentElement;
if (parent && parent !== context) {
const siblings = Array.from(parent.children);
const index = siblings.indexOf(element) + 1;
// Just use parent tag name to avoid recursion
const parentTag = parent.tagName.toLowerCase();
return `${parentTag} > ${tagName}:nth-child(${index})`;
}
// Final fallback
return tagName;
}
updateToolbar() {
document.getElementById('c4ai-mode').textContent =
this.mode === 'container' ? 'Select Container' : 'Select Fields';
document.getElementById('c4ai-container').textContent =
this.container ? `${this.container.tagName}` : 'Not selected';
// Update fields list
const fieldsList = document.getElementById('c4ai-fields-list');
const fieldsItems = document.getElementById('c4ai-fields-items');
if (this.fields.length > 0) {
fieldsList.style.display = 'block';
fieldsItems.innerHTML = this.fields.map(field => `
<li class="c4ai-field-item">
<span class="c4ai-field-name">${field.name}</span>
<span class="c4ai-field-value">${field.value.substring(0, 30)}${field.value.length > 30 ? '...' : ''}</span>
</li>
`).join('');
} else {
fieldsList.style.display = 'none';
}
const hint = document.getElementById('c4ai-hint');
if (this.mode === 'container') {
hint.textContent = 'Click on a container element (e.g., product card, article, etc.)';
} else if (this.fields.length === 0) {
hint.textContent = 'Click on fields inside the container to extract (title, price, etc.)';
} else {
hint.innerHTML = `Continue selecting fields or click <strong>Stop & Generate</strong> to finish.`;
}
}
updateStats() {
chrome.runtime.sendMessage({
action: 'updateStats',
stats: {
container: !!this.container,
fields: this.fields.length
}
});
}
removeAllHighlights() {
document.querySelectorAll('.c4ai-selected-container').forEach(el => {
el.classList.remove('c4ai-selected-container');
});
document.querySelectorAll('.c4ai-selected-field').forEach(el => {
el.classList.remove('c4ai-selected-field');
});
}
generateCode() {
const fieldDescriptions = this.fields.map(f =>
`- ${f.name} (example: "${f.value.substring(0, 50)}...")`
).join('\n');
return `#!/usr/bin/env python3
"""
Generated by Crawl4AI Chrome Extension
URL: ${window.location.href}
Generated: ${new Date().toISOString()}
"""
import asyncio
import json
from pathlib import Path
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
# HTML snippet of the selected container element
HTML_SNIPPET = """
${this.container.html}
"""
# Extraction query based on your field selections
EXTRACTION_QUERY = """
Create a JSON CSS extraction schema to extract the following fields:
${fieldDescriptions}
The schema should handle multiple ${this.container.tagName} elements on the page.
Each item should be extracted as a separate object in the results array.
"""
async def generate_schema():
"""Generate extraction schema using LLM"""
print("🔧 Generating extraction schema...")
try:
# Generate the schema using Crawl4AI's built-in LLM integration
schema = JsonCssExtractionStrategy.generate_schema(
html=HTML_SNIPPET,
query=EXTRACTION_QUERY,
)
# Save the schema for reuse
schema_path = Path('generated_schema.json')
with open(schema_path, 'w') as f:
json.dump(schema, f, indent=2)
print("✅ Schema generated successfully!")
print(f"📄 Schema saved to: {schema_path}")
print("\\nGenerated schema:")
print(json.dumps(schema, indent=2))
return schema
except Exception as e:
print(f"❌ Error generating schema: {e}")
return None
async def test_extraction(url: str = "${window.location.href}"):
"""Test the generated schema on the actual webpage"""
print("\\n🧪 Testing extraction on live webpage...")
# Load the generated schema
try:
with open('generated_schema.json', 'r') as f:
schema = json.load(f)
except FileNotFoundError:
print("❌ Schema file not found. Run generate_schema() first.")
return
# Configure browser
browser_config = BrowserConfig(
headless=True,
verbose=False
)
# Configure extraction
crawler_config = CrawlerRunConfig(
extraction_strategy=JsonCssExtractionStrategy(schema=schema)
)
async with AsyncWebCrawler(config=browser_config) as crawler:
result = await crawler.arun(
url=url,
config=crawler_config
)
if result.success and result.extracted_content:
data = json.loads(result.extracted_content)
print(f"\\n✅ Successfully extracted {len(data)} items!")
# Save results
with open('extracted_data.json', 'w') as f:
json.dump(data, f, indent=2)
# Show sample results
print("\\n📊 Sample results (first 2 items):")
for i, item in enumerate(data[:2], 1):
print(f"\\nItem {i}:")
for key, value in item.items():
print(f" {key}: {value}")
else:
print("❌ Extraction failed:", result.error_message)
if __name__ == "__main__":
# Step 1: Generate the schema from HTML snippet
asyncio.run(generate_schema())
# Step 2: Test extraction on the live webpage
# Uncomment the line below to test extraction:
# asyncio.run(test_extraction())
print("\\n🎯 Next steps:")
print("1. Review the generated schema in 'generated_schema.json'")
print("2. Uncomment the test_extraction() line to test on the live site")
print("3. Use the schema in your Crawl4AI projects!")
`;
return code;
}
showCodeModal(code) {
// Create modal
this.codeModal = document.createElement('div');
this.codeModal.className = 'c4ai-code-modal';
this.codeModal.innerHTML = `
<div class="c4ai-code-modal-content">
<div class="c4ai-code-modal-header">
<h2>Generated Python Code</h2>
<button class="c4ai-close-modal" id="c4ai-close-modal">✕</button>
</div>
<div class="c4ai-code-modal-body">
<pre class="c4ai-code-block"><code class="language-python">${this.escapeHtml(code)}</code></pre>
</div>
<div class="c4ai-code-modal-footer">
<button class="c4ai-action-btn c4ai-cloud-btn" id="c4ai-run-cloud" disabled>
<span>☁️</span> Run on C4AI Cloud (Coming Soon)
</button>
<button class="c4ai-action-btn c4ai-download-btn" id="c4ai-download-code">
<span>⬇</span> Download Code
</button>
<button class="c4ai-action-btn c4ai-copy-btn" id="c4ai-copy-code">
<span>📋</span> Copy to Clipboard
</button>
</div>
</div>
`;
document.body.appendChild(this.codeModal);
// Add event listeners
document.getElementById('c4ai-close-modal').addEventListener('click', () => {
this.codeModal.remove();
this.codeModal = null;
// Don't stop the capture session
});
document.getElementById('c4ai-download-code').addEventListener('click', () => {
chrome.runtime.sendMessage({
action: 'downloadCode',
code: code,
filename: `crawl4ai_schema_${Date.now()}.py`
}, (response) => {
if (response && response.success) {
const btn = document.getElementById('c4ai-download-code');
const originalHTML = btn.innerHTML;
btn.innerHTML = '<span>✓</span> Downloaded!';
setTimeout(() => {
btn.innerHTML = originalHTML;
}, 2000);
} else {
console.error('Download failed:', response?.error);
alert('Download failed. Please check your browser settings.');
}
});
});
document.getElementById('c4ai-copy-code').addEventListener('click', () => {
navigator.clipboard.writeText(code).then(() => {
const btn = document.getElementById('c4ai-copy-code');
btn.innerHTML = '<span>✓</span> Copied!';
setTimeout(() => {
btn.innerHTML = '<span>📋</span> Copy to Clipboard';
}, 2000);
});
});
// Apply syntax highlighting if possible
this.applySyntaxHighlighting();
}
escapeHtml(text) {
const div = document.createElement('div');
div.textContent = text;
return div.innerHTML;
}
applySyntaxHighlighting() {
// Simple Python syntax highlighting - using a different approach
const codeElement = this.codeModal.querySelector('.language-python');
const code = codeElement.textContent;
// Split by lines to handle line-by-line
const lines = code.split('\n');
const highlightedLines = lines.map(line => {
let highlightedLine = this.escapeHtml(line);
// Skip if line is empty
if (!highlightedLine.trim()) return highlightedLine;
// Comments (lines starting with #)
if (highlightedLine.trim().startsWith('#')) {
return `<span class="c4ai-comment">${highlightedLine}</span>`;
}
// Triple quoted strings
if (highlightedLine.includes('"""')) {
highlightedLine = highlightedLine.replace(/(""".*?""")/g, '<span class="c4ai-string">$1</span>');
}
// Regular strings - single and double quotes
highlightedLine = highlightedLine.replace(/(["'])([^"']*)\1/g, '<span class="c4ai-string">$1$2$1</span>');
// Keywords - only highlight if not inside a string
const keywords = ['import', 'from', 'async', 'def', 'await', 'try', 'except', 'with', 'as', 'for', 'if', 'else', 'elif', 'return', 'print', 'open', 'and', 'or', 'not', 'in', 'is', 'class', 'self', 'None', 'True', 'False', '__name__', '__main__'];
keywords.forEach(keyword => {
// Use word boundaries and lookahead/lookbehind to ensure we're not in a string
const regex = new RegExp(`\\b(${keyword})\\b(?![^<]*</span>)`, 'g');
highlightedLine = highlightedLine.replace(regex, '<span class="c4ai-keyword">$1</span>');
});
// Functions (word followed by parenthesis)
highlightedLine = highlightedLine.replace(/\b([a-zA-Z_]\w*)\s*\(/g, '<span class="c4ai-function">$1</span>(');
return highlightedLine;
});
codeElement.innerHTML = highlightedLines.join('\n');
}
}
// Initialize
let schemaBuilder = null;
// Listen for messages from popup
chrome.runtime.onMessage.addListener((message, sender, sendResponse) => {
switch (message.action) {
case 'startSchemaCapture':
if (!schemaBuilder) {
schemaBuilder = new SchemaBuilder();
}
schemaBuilder.start();
sendResponse({ success: true });
break;
case 'stopCapture':
if (schemaBuilder) {
schemaBuilder.stop();
schemaBuilder = null;
}
sendResponse({ success: true });
break;
case 'generateCode':
if (schemaBuilder) {
const code = schemaBuilder.generateCode();
schemaBuilder.showCodeModal(code);
}
sendResponse({ success: true });
break;
}
return true;
});

View File

@@ -0,0 +1,561 @@
/* Crawl4AI Assistant Overlay Styles */
/* Font Face Definitions */
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
font-display: swap;
}
:root {
--font-primary: 'Dank Mono', -apple-system, BlinkMacSystemFont, sans-serif;
--font-code: 'Dank Mono', 'Monaco', 'Menlo', 'Consolas', monospace;
}
/* Highlight box for hovering */
.c4ai-highlight-box {
position: absolute;
pointer-events: none;
z-index: 999999;
transition: all 0.1s ease;
display: none;
}
.c4ai-highlight-box.c4ai-container-mode {
border: 3px dashed #0fbbaa;
background: rgba(15, 187, 170, 0.1);
box-shadow: 0 0 0 2px rgba(15, 187, 170, 0.3);
}
.c4ai-highlight-box.c4ai-field-mode {
border: 2px dashed #f380f5;
background: rgba(243, 128, 245, 0.1);
box-shadow: 0 0 0 2px rgba(243, 128, 245, 0.3);
}
/* Selected elements */
.c4ai-selected-container {
outline: 3px solid #0fbbaa !important;
outline-offset: 2px;
background: rgba(15, 187, 170, 0.05) !important;
}
.c4ai-selected-field {
outline: 2px solid #f380f5 !important;
outline-offset: 1px;
background: rgba(243, 128, 245, 0.1) !important;
position: relative;
}
.c4ai-selected-field::after {
content: attr(data-c4ai-field);
position: absolute;
top: -24px;
left: 0;
background: #f380f5;
color: #000;
padding: 2px 8px;
border-radius: 4px;
font-size: 12px;
font-weight: bold;
font-family: var(--font-primary);
z-index: 999999;
white-space: nowrap;
}
/* Toolbar */
.c4ai-toolbar {
position: fixed;
top: 20px;
right: 20px;
background: #070708;
border: 1px solid #3f3f44;
border-radius: 8px;
z-index: 999999;
font-family: var(--font-primary);
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.8);
width: 320px;
color: #e8e9ed;
overflow: hidden;
}
.c4ai-toolbar * {
font-family: inherit;
box-sizing: border-box;
}
/* macOS-style titlebar */
.c4ai-toolbar-titlebar {
display: flex;
align-items: center;
padding: 12px;
background: #1a1a1a;
border-bottom: 1px solid #3f3f44;
cursor: grab;
user-select: none;
}
.c4ai-titlebar-dots {
display: flex;
gap: 8px;
flex-shrink: 0;
}
.c4ai-dot {
width: 12px;
height: 12px;
border-radius: 50%;
border: none;
cursor: pointer;
transition: opacity 0.2s ease;
padding: 0;
}
.c4ai-dot-close {
background: #ff5f57;
}
.c4ai-dot-close:hover {
background: #ff3030;
}
.c4ai-dot-minimize {
background: #ffbd2e;
}
.c4ai-dot-minimize:hover {
background: #ffaa00;
}
.c4ai-dot-maximize {
background: #28ca42;
}
.c4ai-dot-maximize:hover {
background: #1eb533;
}
.c4ai-titlebar-icon {
width: 16px;
height: 16px;
margin-left: 8px;
margin-right: 8px;
}
.c4ai-titlebar-title {
flex: 1;
text-align: left;
font-size: 13px;
font-weight: 600;
color: #e8e9ed;
}
.c4ai-toolbar-content {
padding: 16px;
}
.c4ai-toolbar-status {
display: flex;
flex-direction: column;
gap: 8px;
margin-bottom: 16px;
padding: 12px;
background: #3f3f44;
border-radius: 8px;
}
.c4ai-status-item {
display: flex;
justify-content: space-between;
align-items: center;
}
.c4ai-status-label {
font-size: 12px;
color: #a3abba;
text-transform: uppercase;
}
.c4ai-status-value {
font-size: 14px;
font-weight: 600;
color: #e8e9ed;
}
.c4ai-toolbar-hint {
margin-top: 16px;
font-size: 13px;
line-height: 1.4;
color: #d5cec0;
padding: 12px;
background: #3f3f44;
border-radius: 8px;
border-left: 3px solid #0fbbaa;
}
.c4ai-toolbar-hint strong {
color: #0fbbaa;
font-weight: 600;
}
/* Fields list */
.c4ai-fields-list {
margin-top: 16px;
padding: 12px;
background: #3f3f44;
border-radius: 8px;
border: 1px solid #3f3f44;
}
.c4ai-fields-header {
font-size: 12px;
text-transform: uppercase;
color: #a3abba;
margin-bottom: 8px;
font-weight: 600;
}
.c4ai-fields-items {
list-style: none;
margin: 0;
padding: 0;
}
.c4ai-field-item {
display: flex;
justify-content: space-between;
align-items: center;
padding: 6px 8px;
margin-bottom: 4px;
background: #070708;
border-radius: 4px;
font-size: 12px;
}
.c4ai-field-name {
font-weight: 600;
color: #f380f5;
margin-right: 8px;
}
.c4ai-field-value {
color: #a3abba;
font-size: 11px;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
flex: 1;
text-align: right;
}
/* Field naming dialog */
.c4ai-field-dialog {
position: absolute;
background: #070708;
border: 2px solid #f380f5;
border-radius: 12px;
padding: 16px;
z-index: 999999;
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.8);
font-family: -apple-system, BlinkMacSystemFont, sans-serif;
color: #e8e9ed;
min-width: 300px;
}
.c4ai-field-dialog h4 {
margin: 0 0 12px 0;
font-size: 14px;
color: #e8e9ed;
}
.c4ai-field-dialog input {
width: 100%;
padding: 8px 12px;
background: #3f3f44;
border: 1px solid #3f3f44;
border-radius: 6px;
color: #e8e9ed;
font-size: 14px;
margin-bottom: 12px;
outline: none;
}
.c4ai-field-dialog input:focus {
border-color: #f380f5;
box-shadow: 0 0 0 2px rgba(243, 128, 245, 0.2);
}
.c4ai-field-preview {
font-size: 12px;
color: #999;
margin-bottom: 12px;
padding: 8px;
background: #1a1a1a;
border-radius: 6px;
word-break: break-word;
}
.c4ai-field-preview strong {
color: #ccc;
}
.c4ai-field-actions {
display: flex;
gap: 8px;
justify-content: flex-end;
}
.c4ai-field-actions button {
padding: 6px 16px;
border: none;
border-radius: 6px;
font-size: 13px;
font-weight: 600;
cursor: pointer;
transition: all 0.2s ease;
}
#c4ai-field-save {
background: #f380f5;
color: #070708;
}
#c4ai-field-save:hover {
background: #e370e5;
transform: translateY(-1px);
}
#c4ai-field-cancel {
background: #3f3f44;
color: #e8e9ed;
}
#c4ai-field-cancel:hover {
background: #4f4f54;
}
/* Toolbar action buttons */
.c4ai-toolbar-actions {
display: flex;
gap: 8px;
margin-top: 16px;
padding-top: 16px;
border-top: 1px solid #2a2a2a;
}
.c4ai-action-btn {
flex: 1;
padding: 8px 16px;
background: #3f3f44;
border: 1px solid #3f3f44;
border-radius: 6px;
color: #e8e9ed;
font-size: 13px;
font-weight: 600;
cursor: pointer;
transition: all 0.2s ease;
display: flex;
align-items: center;
justify-content: center;
gap: 6px;
}
.c4ai-action-btn:hover {
background: #4f4f54;
border-color: #5f5f64;
transform: translateY(-1px);
}
.c4ai-pause-btn {
background: #09b5a5;
border-color: #09b5a5;
color: #070708;
}
.c4ai-pause-btn:hover {
background: #0ac5b5;
}
.c4ai-pause-btn.c4ai-paused {
background: #ff3c74;
border-color: #ff3c74;
}
.c4ai-generate-btn {
background: #0fbbaa;
border-color: #0fbbaa;
color: #070708;
}
.c4ai-generate-btn:hover {
background: #1fcbba;
}
/* Code modal */
.c4ai-code-modal {
position: fixed;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: rgba(0, 0, 0, 0.8);
z-index: 999999;
display: flex;
align-items: center;
justify-content: center;
padding: 20px;
}
.c4ai-code-modal-content {
background: #070708;
border: 2px solid #3f3f44;
border-radius: 16px;
width: 90%;
max-width: 900px;
max-height: 90vh;
display: flex;
flex-direction: column;
box-shadow: 0 16px 64px rgba(0, 0, 0, 0.9);
}
.c4ai-code-modal-header {
display: flex;
justify-content: space-between;
align-items: center;
padding: 20px 24px;
border-bottom: 1px solid #2a2a2a;
}
.c4ai-code-modal-header h2 {
margin: 0;
font-size: 20px;
color: #fff;
font-family: -apple-system, BlinkMacSystemFont, sans-serif;
}
.c4ai-close-modal {
background: none;
border: none;
color: #999;
font-size: 24px;
cursor: pointer;
padding: 0;
width: 32px;
height: 32px;
display: flex;
align-items: center;
justify-content: center;
border-radius: 4px;
transition: all 0.2s ease;
}
.c4ai-close-modal:hover {
background: #2a2a2a;
color: #fff;
}
.c4ai-code-modal-body {
flex: 1;
overflow: auto;
padding: 24px;
}
.c4ai-code-block {
background: #3f3f44;
border: 1px solid #3f3f44;
border-radius: 8px;
padding: 20px;
overflow-x: auto;
margin: 0;
}
.c4ai-code-block code {
font-family: var(--font-code);
font-size: 13px;
line-height: 1.6;
color: #e8e9ed;
white-space: pre;
display: block;
}
/* Syntax highlighting */
.c4ai-keyword {
color: #0fbbaa;
font-weight: bold;
}
.c4ai-string {
color: #f380f5;
}
.c4ai-comment {
color: #a3abba;
font-style: italic;
}
.c4ai-function {
color: #ff3c74;
}
.c4ai-code-modal-footer {
display: flex;
gap: 12px;
padding: 20px 24px;
border-top: 1px solid #2a2a2a;
justify-content: flex-end;
}
.c4ai-download-btn {
background: #0fbbaa;
color: #070708;
border: none;
}
.c4ai-download-btn:hover {
background: #1fcbba;
}
.c4ai-copy-btn {
background: #3f3f44;
border-color: #3f3f44;
}
.c4ai-copy-btn:hover {
background: #4f4f54;
border-color: #5f5f64;
}
.c4ai-cloud-btn {
background: #3f3f44;
border-color: #3f3f44;
opacity: 0.6;
cursor: not-allowed;
}
.c4ai-cloud-btn:disabled {
opacity: 0.6;
cursor: not-allowed;
}
.c4ai-cloud-btn:hover:disabled {
background: #3f3f44;
transform: none;
}

Binary file not shown.

After

Width:  |  Height:  |  Size: 3.4 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 KiB

View File

@@ -0,0 +1,328 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Crawl4AI Assistant - Chrome Extension for Visual Web Scraping</title>
<link rel="stylesheet" href="assistant.css">
</head>
<body>
<div class="terminal-container">
<div class="header">
<div class="header-content">
<div class="logo-section">
<img src="../../img/favicon-32x32.png" alt="Crawl4AI Logo" class="logo">
<div>
<h1>Crawl4AI Assistant</h1>
<p class="tagline">Chrome Extension for Visual Web Scraping</p>
</div>
</div>
<nav class="nav-links">
<a href="../../" class="nav-link">← Back to Docs</a>
<a href="../" class="nav-link">All Apps</a>
<a href="https://github.com/unclecode/crawl4ai" class="nav-link" target="_blank">GitHub</a>
</nav>
</div>
</div>
<div class="content">
<!-- Video Section -->
<section class="video-section">
<div class="video-wrapper">
<video autoplay loop muted playsinline class="demo-video">
<source src="demo.mp4" type="video/mp4">
Your browser does not support the video tag.
</video>
</div>
</section>
<!-- Introduction -->
<section class="intro-section">
<div class="terminal-window">
<div class="terminal-header">
<span class="terminal-title">About Crawl4AI Assistant</span>
</div>
<div class="terminal-content">
<p>Transform any website into structured data with just a few clicks! The Crawl4AI Assistant Chrome Extension lets you visually select elements on any webpage and automatically generates Python code for web scraping.</p>
<div class="features-grid">
<div class="feature-card">
<span class="feature-icon">🎯</span>
<h3>Visual Selection</h3>
<p>Click on any element to select it - no CSS selectors needed</p>
</div>
<div class="feature-card">
<span class="feature-icon">📊</span>
<h3>Schema Builder</h3>
<p>Build extraction schemas by clicking on container and field elements</p>
</div>
<div class="feature-card">
<span class="feature-icon">🐍</span>
<h3>Python Code</h3>
<p>Get production-ready Crawl4AI code with LLM extraction</p>
</div>
<div class="feature-card">
<span class="feature-icon">🎨</span>
<h3>Beautiful UI</h3>
<p>Draggable toolbar with macOS-style interface</p>
</div>
</div>
</div>
</div>
</section>
<!-- Quick Start -->
<section class="quickstart-section">
<h2>Quick Start</h2>
<div class="terminal-window">
<div class="terminal-header">
<span class="terminal-title">Installation</span>
</div>
<div class="terminal-content">
<div class="installation-steps">
<div class="step">
<span class="step-number">1</span>
<div class="step-content">
<h4>Download the Extension</h4>
<p>Get the latest release from GitHub or use the button below</p>
<a href="crawl4ai-assistant-v1.0.1.zip" class="download-button" download>
<span class="button-icon"></span>
Download Extension (v1.0.1)
</a>
</div>
</div>
<div class="step">
<span class="step-number">2</span>
<div class="step-content">
<h4>Load in Chrome</h4>
<p>Navigate to <code>chrome://extensions/</code> and enable Developer Mode</p>
</div>
</div>
<div class="step">
<span class="step-number">3</span>
<div class="step-content">
<h4>Load Unpacked</h4>
<p>Click "Load unpacked" and select the extracted extension folder</p>
</div>
</div>
</div>
</div>
</div>
</section>
<!-- Usage Guide -->
<section class="usage-section">
<h2>How to Use</h2>
<div class="terminal-window">
<div class="terminal-header">
<span class="terminal-title">Step-by-Step Guide</span>
</div>
<div class="terminal-content">
<div class="usage-flow">
<div class="usage-step">
<div class="usage-header">
<span class="usage-icon">1</span>
<h4>Start Schema Builder</h4>
</div>
<p>Click the extension icon and select "Schema Builder" to begin</p>
</div>
<div class="usage-step">
<div class="usage-header">
<span class="usage-icon">2</span>
<h4>Select Container</h4>
</div>
<p>Click on a container element (e.g., product card, article, listing)</p>
<div class="code-snippet">
<span class="comment"># Container will be highlighted in green</span>
</div>
</div>
<div class="usage-step">
<div class="usage-header">
<span class="usage-icon">3</span>
<h4>Select Fields</h4>
</div>
<p>Click on individual fields inside the container and name them</p>
<div class="code-snippet">
<span class="comment"># Fields will be highlighted in pink</span>
<span class="comment"># Examples: title, price, description, image</span>
</div>
</div>
<div class="usage-step">
<div class="usage-header">
<span class="usage-icon">4</span>
<h4>Generate Code</h4>
</div>
<p>Click "Stop & Generate" to create your Python extraction code</p>
</div>
</div>
</div>
</div>
</section>
<!-- Generated Code Example -->
<section class="code-section">
<h2>Generated Code Example</h2>
<div class="terminal-window">
<div class="terminal-header">
<span class="terminal-title">example_extraction.py</span>
</div>
<div class="terminal-content">
<pre><code><span class="keyword">import</span> asyncio
<span class="keyword">import</span> json
<span class="keyword">from</span> crawl4ai <span class="keyword">import</span> AsyncWebCrawler, CrawlerRunConfig
<span class="keyword">from</span> crawl4ai.extraction_strategy <span class="keyword">import</span> JsonCssExtractionStrategy
<span class="keyword">async</span> <span class="keyword">def</span> <span class="function">extract_products</span>():
<span class="comment"># Schema generated from your visual selection</span>
schema = {
<span class="string">"name"</span>: <span class="string">"Product Catalog"</span>,
<span class="string">"baseSelector"</span>: <span class="string">"div.product-card"</span>, <span class="comment"># Container you clicked</span>
<span class="string">"fields"</span>: [
{
<span class="string">"name"</span>: <span class="string">"title"</span>,
<span class="string">"selector"</span>: <span class="string">"h3.product-title"</span>,
<span class="string">"type"</span>: <span class="string">"text"</span>
},
{
<span class="string">"name"</span>: <span class="string">"price"</span>,
<span class="string">"selector"</span>: <span class="string">"span.price"</span>,
<span class="string">"type"</span>: <span class="string">"text"</span>
},
{
<span class="string">"name"</span>: <span class="string">"description"</span>,
<span class="string">"selector"</span>: <span class="string">"p.description"</span>,
<span class="string">"type"</span>: <span class="string">"text"</span>
},
{
<span class="string">"name"</span>: <span class="string">"image"</span>,
<span class="string">"selector"</span>: <span class="string">"img.product-image"</span>,
<span class="string">"type"</span>: <span class="string">"attribute"</span>,
<span class="string">"attribute"</span>: <span class="string">"src"</span>
}
]
}
<span class="comment"># Create extraction strategy</span>
extraction_strategy = JsonCssExtractionStrategy(schema, verbose=<span class="keyword">True</span>)
<span class="comment"># Configure the crawler</span>
config = CrawlerRunConfig(
extraction_strategy=extraction_strategy
)
<span class="keyword">async</span> <span class="keyword">with</span> AsyncWebCrawler() <span class="keyword">as</span> crawler:
result = <span class="keyword">await</span> crawler.arun(
url=<span class="string">"https://example.com/products"</span>,
config=config
)
<span class="comment"># Parse the extracted data</span>
products = json.loads(result.extracted_content)
<span class="keyword">print</span>(<span class="string">f"Extracted {len(products)} products"</span>)
<span class="comment"># Display first product</span>
<span class="keyword">if</span> products:
<span class="keyword">print</span>(json.dumps(products[0], indent=2))
<span class="keyword">return</span> products
<span class="comment"># Run the extraction</span>
<span class="keyword">if</span> __name__ == <span class="string">"__main__"</span>:
asyncio.run(extract_products())</code></pre>
</div>
</div>
</section>
<!-- Coming Soon Section -->
<section class="coming-soon-section">
<h2>Coming Soon: Even More Power</h2>
<div class="terminal-window">
<div class="terminal-header">
<span class="terminal-title">Future Features</span>
</div>
<div class="terminal-content">
<p class="intro-text">We're continuously expanding C4AI Assistant with powerful new features to make web scraping even easier:</p>
<div class="coming-features">
<div class="coming-feature">
<div class="feature-header">
<span class="feature-badge">Cloud</span>
<h3>Run on C4AI Cloud</h3>
</div>
<p>Execute your extraction directly in the cloud without setting up any local environment. Just click "Run on Cloud" and get your data instantly.</p>
<div class="feature-preview">
<code>☁️ Instant results • Auto-scaling</code>
</div>
</div>
<div class="coming-feature">
<div class="feature-header">
<span class="feature-badge">Direct</span>
<h3>Get CrawlResult Without Code</h3>
</div>
<p>Skip the code generation entirely! Get extracted data directly in the extension as a CrawlResult object, ready to download as JSON.</p>
<div class="feature-preview">
<code>📊 One-click extraction • No Python needed • Export to JSON/CSV</code>
</div>
</div>
<div class="coming-feature">
<div class="feature-header">
<span class="feature-badge">AI</span>
<h3>Smart Schema Suggestions</h3>
</div>
<p>AI-powered field detection that automatically suggests the most likely data fields on any page, making schema building even faster.</p>
<div class="feature-preview">
<code>🤖 Auto-detect fields • Smart naming • Pattern recognition</code>
</div>
</div>
<div class="coming-feature">
<div class="feature-header">
<span class="feature-badge">Script</span>
<h3>C4A Script Builder</h3>
</div>
<p>Visual automation script builder for complex interactions - fill forms, click buttons, handle pagination, all without writing code.</p>
<div class="feature-preview">
<code>🎯 Visual automation • Record & replay • Export as C4A script</code>
</div>
</div>
</div>
<div class="stay-tuned">
<p>🚀 Stay tuned for updates! Follow our <a href="https://github.com/unclecode/crawl4ai" target="_blank">GitHub</a> for the latest releases.</p>
</div>
</div>
</div>
</section>
<!-- Footer -->
<footer class="footer">
<div class="footer-content">
<div class="footer-section">
<h4>Resources</h4>
<ul>
<li><a href="https://github.com/unclecode/crawl4ai">GitHub Repository</a></li>
<li><a href="../../">Documentation</a></li>
<li><a href="https://discord.gg/jP8KfhDhyN">Discord Community</a></li>
</ul>
</div>
<div class="footer-section">
<h4>Connect</h4>
<ul>
<li><a href="https://twitter.com/unclecode">Twitter @unclecode</a></li>
<li><a href="https://github.com/unclecode">GitHub @unclecode</a></li>
</ul>
</div>
</div>
<div class="footer-bottom">
<p>Made with 🚀 by the Crawl4AI team</p>
</div>
</footer>
</div>
</div>
</body>
</html>

View File

@@ -0,0 +1,44 @@
{
"manifest_version": 3,
"name": "Crawl4AI Assistant",
"version": "1.0.1",
"description": "Visual schema and script builder for Crawl4AI - Build extraction schemas by clicking on elements",
"permissions": [
"activeTab",
"storage",
"downloads"
],
"host_permissions": [
"<all_urls>"
],
"action": {
"default_popup": "popup/popup.html",
"default_icon": {
"16": "icons/icon-16.png",
"48": "icons/icon-48.png",
"128": "icons/icon-128.png"
}
},
"content_scripts": [
{
"matches": ["<all_urls>"],
"js": ["content/content.js"],
"css": ["content/overlay.css"],
"run_at": "document_idle"
}
],
"background": {
"service_worker": "background/service-worker.js"
},
"icons": {
"16": "icons/icon-16.png",
"48": "icons/icon-48.png",
"128": "icons/icon-128.png"
},
"web_accessible_resources": [
{
"resources": ["icons/*", "assets/*"],
"matches": ["<all_urls>"]
}
]
}

Binary file not shown.

After

Width:  |  Height:  |  Size: 3.4 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.6 KiB

View File

@@ -0,0 +1,324 @@
/* Font Face Definitions */
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
font-display: swap;
}
:root {
--font-primary: 'Dank Mono', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, monospace;
}
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
width: 380px;
font-family: var(--font-primary);
background: #0a0a0a;
color: #e0e0e0;
}
.popup-container {
padding: 20px;
}
header {
display: flex;
align-items: center;
gap: 16px;
margin-bottom: 20px;
padding-bottom: 16px;
border-bottom: 1px solid #2a2a2a;
}
.logo {
width: 48px;
height: 48px;
flex-shrink: 0;
}
.header-content {
flex: 1;
}
header h1 {
font-size: 20px;
font-weight: 600;
color: #fff;
margin: 0 0 4px 0;
}
.header-stats {
display: flex;
align-items: center;
gap: 12px;
}
.github-stars {
display: flex;
align-items: center;
gap: 6px;
color: #999;
text-decoration: none;
font-size: 13px;
transition: color 0.2s ease;
}
.github-stars:hover {
color: #4a9eff;
}
.github-icon {
flex-shrink: 0;
}
.mode-selector {
display: flex;
flex-direction: column;
gap: 12px;
margin-bottom: 20px;
}
.mode-button {
display: flex;
align-items: center;
gap: 16px;
padding: 16px;
background: #1a1a1a;
border: 2px solid #2a2a2a;
border-radius: 12px;
cursor: pointer;
transition: all 0.2s ease;
width: 100%;
text-align: left;
}
.mode-button:hover:not(:disabled) {
background: #252525;
border-color: #4a9eff;
transform: translateY(-2px);
}
.mode-button:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.mode-button .icon {
font-size: 32px;
width: 48px;
height: 48px;
display: flex;
align-items: center;
justify-content: center;
background: #252525;
border-radius: 8px;
}
.mode-button.schema .icon {
background: #1e3a5f;
}
.mode-button.script .icon {
background: #3a1e5f;
}
.mode-info h3 {
font-size: 16px;
color: #fff;
margin-bottom: 4px;
}
.mode-info p {
font-size: 13px;
color: #999;
line-height: 1.4;
}
.active-session {
background: #1a1a1a;
border: 2px solid #4a9eff;
border-radius: 12px;
padding: 16px;
margin-bottom: 20px;
}
.active-session.hidden {
display: none;
}
.session-header {
display: flex;
align-items: center;
gap: 8px;
margin-bottom: 12px;
}
.status-dot {
width: 8px;
height: 8px;
background: #4a9eff;
border-radius: 50%;
animation: pulse 2s infinite;
}
@keyframes pulse {
0%, 100% { opacity: 1; }
50% { opacity: 0.5; }
}
.session-title {
font-size: 14px;
font-weight: 600;
color: #4a9eff;
}
.session-stats {
display: flex;
gap: 20px;
margin-bottom: 16px;
padding: 12px;
background: #0a0a0a;
border-radius: 8px;
}
.stat {
flex: 1;
}
.stat-label {
display: block;
font-size: 11px;
color: #666;
text-transform: uppercase;
margin-bottom: 4px;
}
.stat-value {
font-size: 14px;
color: #fff;
font-weight: 600;
}
.session-actions {
display: flex;
gap: 8px;
}
.action-button {
flex: 1;
padding: 10px 16px;
border: none;
border-radius: 8px;
font-size: 14px;
font-weight: 600;
cursor: pointer;
transition: all 0.2s ease;
}
.action-button.primary {
background: #4a9eff;
color: #000;
}
.action-button.primary:hover:not(:disabled) {
background: #3a8eef;
transform: translateY(-1px);
}
.action-button.primary:disabled {
background: #2a4a7f;
color: #666;
cursor: not-allowed;
}
.action-button.secondary {
background: #2a2a2a;
color: #fff;
}
.action-button.secondary:hover {
background: #3a3a3a;
}
.instructions {
background: #1a1a1a;
border-radius: 12px;
padding: 16px;
margin-bottom: 16px;
}
.instructions h4 {
font-size: 14px;
margin-bottom: 12px;
color: #fff;
}
.instructions ol {
padding-left: 20px;
}
.instructions li {
font-size: 13px;
line-height: 1.6;
color: #ccc;
margin-bottom: 6px;
}
footer {
padding-top: 16px;
border-top: 1px solid #2a2a2a;
}
.social-links {
display: flex;
justify-content: center;
gap: 16px;
}
.social-link {
display: flex;
align-items: center;
gap: 6px;
color: #999;
text-decoration: none;
font-size: 12px;
transition: all 0.2s ease;
padding: 6px 12px;
border-radius: 6px;
background: #1a1a1a;
}
.social-link:hover {
color: #0fbbaa;
background: #2a2a2a;
transform: translateY(-1px);
}
.social-link svg {
width: 16px;
height: 16px;
flex-shrink: 0;
}

View File

@@ -0,0 +1,103 @@
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<link rel="stylesheet" href="popup.css">
</head>
<body>
<div class="popup-container">
<header>
<img src="icons/icon-48.png" class="logo" alt="Crawl4AI">
<div class="header-content">
<h1>Crawl4AI Assistant</h1>
<div class="header-stats">
<a href="https://github.com/unclecode/crawl4ai" target="_blank" class="github-stars">
<svg class="github-icon" viewBox="0 0 16 16" width="16" height="16">
<path fill="currentColor" d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"></path>
</svg>
<span id="stars-count">Loading...</span>
</a>
</div>
</div>
</header>
<div class="mode-selector">
<button id="schema-mode" class="mode-button schema">
<div class="icon">📊</div>
<div class="mode-info">
<h3>Schema Builder</h3>
<p>Click elements to build extraction schemas</p>
</div>
</button>
<button id="script-mode" class="mode-button script" disabled>
<div class="icon">🎯</div>
<div class="mode-info">
<h3>Script Builder</h3>
<p>Coming soon - Build automation scripts</p>
</div>
</button>
</div>
<div id="active-session" class="active-session hidden">
<div class="session-header">
<span class="status-dot"></span>
<span class="session-title">Schema Capture Active</span>
</div>
<div class="session-stats">
<div class="stat">
<span class="stat-label">Container:</span>
<span id="container-status" class="stat-value">Not selected</span>
</div>
<div class="stat">
<span class="stat-label">Fields:</span>
<span id="fields-count" class="stat-value">0</span>
</div>
</div>
<div class="session-actions">
<button id="generate-code" class="action-button primary" disabled>
<span>Generate Code</span>
</button>
<button id="stop-capture" class="action-button secondary">
<span>Stop Capture</span>
</button>
</div>
</div>
<div class="instructions">
<h4>How to use:</h4>
<ol>
<li>Click "Schema Builder" to start</li>
<li>Click on a container element (e.g., product card)</li>
<li>Click individual fields inside and name them</li>
<li>Generate Python code when done</li>
</ol>
</div>
<footer>
<div class="social-links">
<a href="https://docs.crawl4ai.com" target="_blank" class="social-link">
<svg viewBox="0 0 24 24" width="16" height="16">
<path fill="currentColor" d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm-2 15l-5-5 1.41-1.41L10 14.17l7.59-7.59L19 8l-9 9z"/>
</svg>
<span>Docs</span>
</a>
<a href="https://twitter.com/unclecode" target="_blank" class="social-link">
<svg viewBox="0 0 24 24" width="16" height="16">
<path fill="currentColor" d="M18.244 2.25h3.308l-7.227 8.26 8.502 11.24H16.17l-5.214-6.817L4.99 21.75H1.68l7.73-8.835L1.254 2.25H8.08l4.713 6.231zm-1.161 17.52h1.833L7.084 4.126H5.117z"/>
</svg>
<span>@unclecode</span>
</a>
<a href="https://discord.gg/jP8KfhDhyN" target="_blank" class="social-link">
<svg viewBox="0 0 24 24" width="16" height="16">
<path fill="currentColor" d="M19.27 5.33C17.94 4.71 16.5 4.26 15 4a.09.09 0 00-.07.03c-.18.33-.39.76-.53 1.09a16.09 16.09 0 00-4.8 0c-.14-.34-.35-.76-.54-1.09-.01-.02-.04-.03-.07-.03-1.5.26-2.93.71-4.27 1.33-.01 0-.02.01-.03.02-2.72 4.07-3.47 8.03-3.1 11.95 0 .02.01.04.03.05 1.8 1.32 3.53 2.12 5.24 2.65.03.01.06 0 .07-.02.4-.55.76-1.13 1.07-1.74.02-.04 0-.08-.04-.09-.57-.22-1.11-.48-1.64-.78-.04-.02-.04-.08-.01-.11.11-.08.22-.17.33-.25.02-.02.05-.02.07-.01 3.44 1.57 7.15 1.57 10.55 0 .02-.01.05-.01.07.01.11.09.22.17.33.26.04.03.04.09-.01.11-.52.31-1.07.56-1.64.78-.04.01-.05.06-.04.09.32.61.68 1.19 1.07 1.74.03.01.06.02.09.01 1.72-.53 3.45-1.33 5.25-2.65.02-.01.03-.03.03-.05.44-4.53-.73-8.46-3.1-11.95-.01-.01-.02-.02-.04-.02zM8.52 14.91c-1.03 0-1.89-.95-1.89-2.12s.84-2.12 1.89-2.12c1.06 0 1.9.96 1.89 2.12 0 1.17-.84 2.12-1.89 2.12zm6.97 0c-1.03 0-1.89-.95-1.89-2.12s.84-2.12 1.89-2.12c1.06 0 1.9.96 1.89 2.12 0 1.17-.83 2.12-1.89 2.12z"/>
</svg>
<span>Discord</span>
</a>
</div>
</footer>
</div>
<script src="popup.js"></script>
</body>
</html>

View File

@@ -0,0 +1,112 @@
// Popup script for Crawl4AI Assistant
let activeMode = null;
document.addEventListener('DOMContentLoaded', () => {
// Fetch GitHub stars
fetchGitHubStars();
// Check current state
chrome.storage.local.get(['captureMode', 'captureStats'], (data) => {
if (data.captureMode) {
activeMode = data.captureMode;
showActiveSession(data.captureStats || {});
}
});
// Mode buttons
document.getElementById('schema-mode').addEventListener('click', () => {
startSchemaCapture();
});
// Session actions
document.getElementById('generate-code').addEventListener('click', () => {
generateCode();
});
document.getElementById('stop-capture').addEventListener('click', () => {
stopCapture();
});
});
async function fetchGitHubStars() {
try {
const response = await fetch('https://api.github.com/repos/unclecode/crawl4ai');
const data = await response.json();
const stars = data.stargazers_count;
// Format the number (e.g., 1.2k)
let formattedStars;
if (stars >= 1000) {
formattedStars = (stars / 1000).toFixed(1) + 'k';
} else {
formattedStars = stars.toString();
}
document.getElementById('stars-count').textContent = `${formattedStars}`;
} catch (error) {
console.error('Failed to fetch GitHub stars:', error);
document.getElementById('stars-count').textContent = '⭐ 2k+';
}
}
function startSchemaCapture() {
chrome.tabs.query({ active: true, currentWindow: true }, (tabs) => {
chrome.tabs.sendMessage(tabs[0].id, {
action: 'startSchemaCapture'
}, (response) => {
if (response && response.success) {
// Close the popup to let user interact with the page
window.close();
}
});
});
}
function showActiveSession(stats) {
document.querySelector('.mode-selector').style.display = 'none';
document.getElementById('active-session').classList.remove('hidden');
updateSessionStats(stats);
}
function updateSessionStats(stats) {
document.getElementById('container-status').textContent =
stats.container ? 'Selected ✓' : 'Not selected';
document.getElementById('fields-count').textContent = stats.fields || 0;
// Enable generate button if we have container and fields
document.getElementById('generate-code').disabled =
!stats.container || stats.fields === 0;
}
function generateCode() {
chrome.tabs.query({ active: true, currentWindow: true }, (tabs) => {
chrome.tabs.sendMessage(tabs[0].id, {
action: 'generateCode'
});
});
}
function stopCapture() {
chrome.tabs.query({ active: true, currentWindow: true }, (tabs) => {
chrome.tabs.sendMessage(tabs[0].id, {
action: 'stopCapture'
}, () => {
// Reset UI
document.querySelector('.mode-selector').style.display = 'flex';
document.getElementById('active-session').classList.add('hidden');
activeMode = null;
// Clear storage
chrome.storage.local.remove(['captureMode', 'captureStats']);
});
});
}
// Listen for stats updates from content script
chrome.runtime.onMessage.addListener((message, sender, sendResponse) => {
if (message.action === 'updateStats') {
updateSessionStats(message.stats);
chrome.storage.local.set({ captureStats: message.stats });
}
});

View File

@@ -186,19 +186,20 @@ Our apps are designed to make Crawl4AI more accessible and powerful. Whether you
</div>
<div class="app-card">
<span class="app-status status-coming-soon">Coming Soon</span>
<h3>🏗️ Schema Builder</h3>
<span class="app-status status-available">Available</span>
<h3>🔍 Crawl4AI Assistant (Chrome Extension)</h3>
<p class="app-description">
Visually design JSON extraction schemas by pointing and clicking on webpage elements. No more guessing CSS selectors!
Visual schema builder Chrome extension - click on webpage elements to generate extraction schemas and Python code!
</p>
<ul class="app-features">
<li>Point-and-click selector generation</li>
<li>Automatic schema inference</li>
<li>Live extraction preview</li>
<li>Export to multiple formats</li>
<li>Visual element selection</li>
<li>Container & field selection modes</li>
<li>Smart selector generation</li>
<li>Complete Python code generation</li>
<li>One-click installation</li>
</ul>
<div class="app-action">
<a href="#" class="app-btn disabled">Coming Soon</a>
<a href="crawl4ai-assistant/" class="app-btn">Install Extension →</a>
</div>
</div>

View File

@@ -7,10 +7,25 @@
<link rel="stylesheet" href="llmtxt.css">
</head>
<body>
<div class="container">
<header class="header">
<h1><span class="logo">🚀🤖</span> Crawl4AI LLM Context Builder</h1>
</header>
<div class="terminal-container">
<div class="header">
<div class="header-content">
<div class="logo-section">
<img src="../../img/favicon-32x32.png" alt="Crawl4AI Logo" class="logo">
<div>
<h1>Crawl4AI LLM Context Builder</h1>
<p class="tagline">Multi-Dimensional Context for AI Assistants</p>
</div>
</div>
<nav class="nav-links">
<a href="../../" class="nav-link">← Back to Docs</a>
<a href="../" class="nav-link">All Apps</a>
<a href="https://github.com/unclecode/crawl4ai" class="nav-link" target="_blank">GitHub</a>
</nav>
</div>
</div>
<div class="content">
<section class="intro">
<div class="intro-header">
@@ -135,6 +150,7 @@
</table>
</div>
</section>
</div>
</div>
<script src="llmtxt.js"></script>

View File

@@ -1,5 +1,30 @@
/* Terminal Theme CSS for LLM Context Builder */
/* Font Face Definitions */
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Regular.woff2') format('woff2');
font-weight: 400;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Bold.woff2') format('woff2');
font-weight: 700;
font-style: normal;
font-display: swap;
}
@font-face {
font-family: 'Dank Mono';
src: url('../assets/DankMono-Italic.woff2') format('woff2');
font-weight: 400;
font-style: italic;
font-display: swap;
}
:root {
--background-color: #070708;
--font-color: #e8e9ed;
@@ -13,6 +38,9 @@
--border-color: #3f3f44;
--hover-bg: #1a1a1c;
--success-color: #50ff50;
--bg-secondary: #1a1a1a;
--primary-green: #0fbbaa;
--font-primary: 'Dank Mono', dm, Monaco, Courier New, monospace;
}
* {
@@ -22,38 +50,88 @@
body {
margin: 0;
padding: 0;
font-family: dm, Monaco, Courier New, monospace;
font-family: var(--font-primary);
font-size: 14px;
line-height: 1.5;
background-color: var(--background-color);
color: var(--font-color);
}
.container {
/* Terminal Container */
.terminal-container {
min-height: 100vh;
display: flex;
flex-direction: column;
}
/* Header - matching assistant layout */
.header {
background: var(--bg-secondary);
border-bottom: 1px solid var(--border-color);
padding: 1.5rem 0;
position: sticky;
top: 0;
z-index: 100;
backdrop-filter: blur(10px);
background: rgba(26, 26, 26, 0.95);
}
.header-content {
max-width: 1200px;
margin: 0 auto;
padding: 20px;
padding: 0 2rem;
display: flex;
justify-content: space-between;
align-items: center;
}
/* Header */
.header {
text-align: center;
margin-bottom: 40px;
border-bottom: 1px dashed var(--tertiary-color);
padding-bottom: 20px;
}
.header h1 {
font-size: 24px;
color: var(--primary-color);
margin: 0;
text-transform: uppercase;
letter-spacing: 2px;
.logo-section {
display: flex;
align-items: center;
gap: 1rem;
}
.logo {
font-size: 28px;
vertical-align: middle;
width: 48px;
height: 48px;
}
.logo-section h1 {
font-size: 1.75rem;
font-weight: 700;
color: var(--font-color);
margin: 0;
}
.tagline {
font-size: 0.875rem;
color: var(--tertiary-color);
margin-top: 0.25rem;
}
.nav-links {
display: flex;
gap: 2rem;
}
.nav-link {
color: var(--tertiary-color);
text-decoration: none;
font-size: 0.875rem;
transition: color 0.2s ease;
}
.nav-link:hover {
color: var(--primary-green);
}
/* Content */
.content {
flex: 1;
max-width: 1200px;
margin: 0 auto;
padding: 2rem;
width: 100%;
}
/* Intro Section */
@@ -446,6 +524,15 @@ body {
/* Responsive Design */
@media (max-width: 768px) {
.header-content {
flex-direction: column;
gap: 1.5rem;
}
.nav-links {
gap: 1rem;
}
.preset-options {
flex-direction: column;
}
@@ -454,7 +541,7 @@ body {
grid-template-columns: 1fr;
}
.container {
padding: 10px;
.content {
padding: 1rem;
}
}

View File

@@ -28,7 +28,8 @@
--secondary-color: #d5cec0;
--tertiary-color: #a3abba;
--primary-dimmed-color: #09b5a5; /* Updated to the brand color */
--primary-color: #0fbbaa; /* Updated to the brand color */
/* --primary-color: #0fbbaa; */
--primary-color: #50ffff; /* Updated to the brand color */
--accent-color: rgb(243, 128, 245);
--error-color: #ff3c74;
--progress-bar-background: #3f3f44;

View File

@@ -1,4 +1,4 @@
<div class="llmtxt-container">
I<div class="llmtxt-container">
<iframe id="llmtxt-frame" src="../../llmtxt/index.html" width="100%" style="border:none; display: block;" title="Crawl4AI LLM Context Builder"></iframe>
</div>