feat: add progressive exploration to layout extraction script

Enhanced extract-layout-structure.js with intelligent selector discovery:
- Auto-detects missing main containers when <3 found
- Scans large visible containers (≥500×300px)
- Extracts class patterns (main/content/wrapper/container/page/layout/app)
- Suggests new selectors to add to script
- Returns exploration data with recommendations

Added commonClassSelectors strategy:
- .main, .content, .main-content, .page-content
- .container.main, .wrapper > .main
- div[class*="main-wrapper"], div[class*="content-wrapper"]

Updated layout-extract.md with progressive exploration documentation.

Version: 2.1.0 → 2.2.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-10-16 16:27:46 +08:00
parent 3066680f16
commit 872fb4995e
2 changed files with 244 additions and 19 deletions

View File

@@ -137,15 +137,50 @@ ELSE:
**Usage**: Read the script file and use content directly in `mcp__chrome-devtools__evaluate_script()`
**Script returns**:
- `metadata`: Extraction timestamp, URL, method
- `metadata`: Extraction timestamp, URL, method, version
- `patterns`: Layout pattern statistics (flexColumn, flexRow, grid counts)
- `structure`: Hierarchical DOM tree with layout properties
- `exploration`: (Optional) Progressive exploration results when standard selectors fail
**Benefits**:
- ✅ Real flex/grid configuration (justifyContent, alignItems, gap, etc.)
- ✅ Accurate element bounds (x, y, width, height)
- ✅ Structural hierarchy with depth control
- ✅ Layout pattern identification (flex-row, flex-column, grid-NCol)
- ✅ Progressive exploration: Auto-discovers missing selectors
**Progressive Exploration Strategy** (v2.2.0+):
When script finds <3 main containers, it automatically:
1. **Scans** all large visible containers (≥500×300px)
2. **Extracts** class patterns matching: `main|content|wrapper|container|page|layout|app`
3. **Suggests** new selectors to add to script
4. **Returns** exploration data in `result.exploration`:
```json
{
"triggered": true,
"discoveredCandidates": [{classes, bounds, display}],
"suggestedSelectors": [".wrapper", ".page-index"],
"recommendation": ".wrapper, .page-index, .app-container"
}
```
**Using Exploration Results**:
```javascript
// After extraction, check for suggestions
IF result.exploration?.triggered:
REPORT: result.exploration.warning
REPORT: "Suggested selectors: " + result.exploration.recommendation
// Update script by adding to commonClassSelectors array
// Then re-run extraction for better coverage
```
**Selector Update Workflow**:
1. Run extraction on unfamiliar site
2. Check `result.exploration.suggestedSelectors`
3. Add relevant selectors to script's `commonClassSelectors`
4. Re-run extraction → improved container detection
### Step 3: Memory Check
```bash

View File

@@ -1,10 +1,27 @@
/**
* Extract Layout Structure from DOM
* Extract Layout Structure from DOM - Enhanced Version
*
* Extracts real layout information from DOM to provide accurate
* structural data for UI replication.
*
* Features:
* - Framework detection (Nuxt.js, Next.js, React, Vue, Angular)
* - Multi-strategy container detection (strict → relaxed → class-based → framework-specific)
* - Intelligent main content detection with common class names support
* - Supports modern SPA frameworks
* - Detects non-semantic main containers (.main, .content, etc.)
* - Progressive exploration: Auto-discovers missing selectors when standard patterns fail
* - Suggests new class names to add to script based on actual page structure
*
* Progressive Exploration:
* When fewer than 3 main containers are found, the script automatically:
* 1. Analyzes all large visible containers (≥500×300px)
* 2. Extracts class name patterns (main/content/wrapper/container/page/etc.)
* 3. Suggests new selectors to add to the script
* 4. Returns exploration data in result.exploration
*
* Usage: Execute via Chrome DevTools evaluate_script
* Version: 2.2.0
*/
(() => {
@@ -62,7 +79,7 @@
const identifyPattern = (props) => {
const { display, flexDirection, gridTemplateColumns } = props;
if (display === 'flex') {
if (display === 'flex' || display === 'inline-flex') {
if (flexDirection === 'column') return 'flex-column';
if (flexDirection === 'row') return 'flex-row';
return 'flex';
@@ -77,12 +94,23 @@
return 'grid';
}
if (display === 'inline-flex') return 'inline-flex';
if (display === 'block') return 'block';
return display;
};
/**
* Detect frontend framework
*/
const detectFramework = () => {
if (document.querySelector('#__nuxt')) return { name: 'Nuxt.js', version: 'unknown' };
if (document.querySelector('#__next')) return { name: 'Next.js', version: 'unknown' };
if (document.querySelector('[data-reactroot]')) return { name: 'React', version: 'unknown' };
if (document.querySelector('[ng-version]')) return { name: 'Angular', version: 'unknown' };
if (window.Vue) return { name: 'Vue.js', version: window.Vue.version || 'unknown' };
return { name: 'Unknown', version: 'unknown' };
};
/**
* Build layout tree recursively
*/
@@ -139,35 +167,165 @@
};
/**
* Find main layout containers
* Find main layout containers with multi-strategy approach
*/
const findMainContainers = () => {
const selectors = [
const containers = [];
const found = new Set();
// Strategy 1: Strict selectors (body direct children)
const strictSelectors = [
'body > header',
'body > nav',
'body > main',
'body > footer',
'body > footer'
];
// Strategy 2: Relaxed selectors (any level)
const relaxedSelectors = [
'header',
'nav',
'main',
'footer',
'[role="banner"]',
'[role="navigation"]',
'[role="main"]',
'[role="contentinfo"]'
];
const containers = [];
// Strategy 3: Common class-based main content selectors
const commonClassSelectors = [
'.main',
'.content',
'.main-content',
'.page-content',
'.container.main',
'.wrapper > .main',
'div[class*="main-wrapper"]',
'div[class*="content-wrapper"]'
];
selectors.forEach(selector => {
const element = document.querySelector(selector);
if (element) {
const tree = buildLayoutTree(element, 0, 3);
if (tree) {
containers.push(tree);
}
// Strategy 4: Framework-specific selectors
const frameworkSelectors = [
'#__nuxt header', '#__nuxt .main', '#__nuxt main', '#__nuxt footer',
'#__next header', '#__next .main', '#__next main', '#__next footer',
'#app header', '#app .main', '#app main', '#app footer',
'[data-app] header', '[data-app] .main', '[data-app] main', '[data-app] footer'
];
// Try all strategies
const allSelectors = [...strictSelectors, ...relaxedSelectors, ...commonClassSelectors, ...frameworkSelectors];
allSelectors.forEach(selector => {
try {
const elements = document.querySelectorAll(selector);
elements.forEach(element => {
// Avoid duplicates and invisible elements
if (!found.has(element) && element.offsetParent !== null) {
found.add(element);
const tree = buildLayoutTree(element, 0, 3);
if (tree && tree.bounds.width > 0 && tree.bounds.height > 0) {
containers.push(tree);
}
}
});
} catch (e) {
console.warn(`Selector failed: ${selector}`, e);
}
});
// Fallback: If no containers found, use body's direct children
if (containers.length === 0) {
Array.from(document.body.children).forEach(child => {
if (child.offsetParent !== null && !found.has(child)) {
const tree = buildLayoutTree(child, 0, 2);
if (tree && tree.bounds.width > 100 && tree.bounds.height > 100) {
containers.push(tree);
}
}
});
}
return containers;
};
/**
* Progressive exploration: Discover main containers when standard selectors fail
* Analyzes large visible containers and suggests class name patterns
*/
const exploreMainContainers = () => {
const candidates = [];
const minWidth = 500;
const minHeight = 300;
// Find all large visible divs
const allDivs = document.querySelectorAll('div');
allDivs.forEach(div => {
const rect = div.getBoundingClientRect();
const style = window.getComputedStyle(div);
// Filter: large size, visible, not header/footer
if (rect.width >= minWidth &&
rect.height >= minHeight &&
div.offsetParent !== null &&
!div.closest('header') &&
!div.closest('footer')) {
const classes = Array.from(div.classList);
const area = rect.width * rect.height;
candidates.push({
element: div,
classes: classes,
area: area,
bounds: {
width: Math.round(rect.width),
height: Math.round(rect.height)
},
display: style.display,
depth: getElementDepth(div)
});
}
});
// Sort by area (largest first) and take top candidates
candidates.sort((a, b) => b.area - a.area);
// Extract unique class patterns from top candidates
const classPatterns = new Set();
candidates.slice(0, 20).forEach(c => {
c.classes.forEach(cls => {
// Identify potential main content class patterns
if (cls.match(/main|content|container|wrapper|page|body|layout|app/i)) {
classPatterns.add(cls);
}
});
});
return {
candidates: candidates.slice(0, 10).map(c => ({
classes: c.classes,
bounds: c.bounds,
display: c.display,
depth: c.depth
})),
suggestedSelectors: Array.from(classPatterns).map(cls => `.${cls}`)
};
};
/**
* Get element depth in DOM tree
*/
const getElementDepth = (element) => {
let depth = 0;
let current = element;
while (current.parentElement) {
depth++;
current = current.parentElement;
}
return depth;
};
/**
* Analyze layout patterns
*/
@@ -199,21 +357,53 @@
};
/**
* Main extraction function
* Main extraction function with progressive exploration
*/
const extractLayout = () => {
const framework = detectFramework();
const containers = findMainContainers();
const patterns = analyzePatterns(containers);
return {
// Progressive exploration: if too few containers found, explore and suggest
let exploration = null;
const minExpectedContainers = 3; // At least header, main, footer
if (containers.length < minExpectedContainers) {
exploration = exploreMainContainers();
// Add warning message
exploration.warning = `Only ${containers.length} containers found. Consider adding these selectors to the script:`;
exploration.recommendation = exploration.suggestedSelectors.join(', ');
}
const result = {
metadata: {
extractedAt: new Date().toISOString(),
url: window.location.href,
method: 'layout-structure'
framework: framework,
method: 'layout-structure-enhanced',
version: '2.2.0'
},
statistics: {
totalContainers: containers.length,
patterns: patterns
},
patterns: patterns,
structure: containers
};
// Add exploration results if triggered
if (exploration) {
result.exploration = {
triggered: true,
reason: 'Insufficient containers found with standard selectors',
discoveredCandidates: exploration.candidates,
suggestedSelectors: exploration.suggestedSelectors,
warning: exploration.warning,
recommendation: exploration.recommendation
};
}
return result;
};
// Execute and return results