Spaces:
Sleeping
Sleeping
File size: 8,323 Bytes
494c89b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
"""
Script Collector - collects all JS scripts from pages during registration.
Usage:
from debugger.collectors.script_collector import ScriptCollector
collector = ScriptCollector()
collector.collect(page) # Call after each page load
collector.save() # Save at the end
"""
import json
import hashlib
import base64
from pathlib import Path
from datetime import datetime
from urllib.parse import urlparse
from typing import Optional
class ScriptCollector:
"""Collects all JS scripts from browser pages."""
_instance: Optional['ScriptCollector'] = None
def __init__(self, output_dir: Path = None):
if output_dir is None:
from core.paths import get_paths
paths = get_paths()
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
output_dir = paths.debug_sessions_dir / 'aws_scripts' / timestamp
self.output_dir = Path(output_dir)
self.output_dir.mkdir(parents=True, exist_ok=True)
self.collected = {} # url -> filepath
self.page_count = 0
self.enabled = True
print(f"[ScriptCollector] Output: {self.output_dir}")
@classmethod
def get_instance(cls) -> 'ScriptCollector':
"""Get singleton instance."""
if cls._instance is None:
cls._instance = cls()
return cls._instance
@classmethod
def reset(cls):
"""Reset singleton (for new registration session)."""
if cls._instance:
cls._instance.save()
cls._instance = None
def collect(self, page, page_name: str = None) -> int:
"""
Collect all JS scripts from current page.
Args:
page: DrissionPage ChromiumPage instance
page_name: Optional name for this page (auto-generated if not provided)
Returns:
Number of new scripts collected
"""
if not self.enabled:
return 0
self.page_count += 1
url = page.url
if not page_name:
parsed = urlparse(url)
page_name = f"{self.page_count:02d}_{parsed.netloc.replace('.', '_')}"
print(f"[ScriptCollector] Page {self.page_count}: {url[:60]}...")
# Get all script URLs from page
try:
js_urls = page.run_js('''
const urls = new Set();
// Script tags with src
document.querySelectorAll('script[src]').forEach(s => {
if (s.src) urls.add(s.src);
});
// Performance API - catches dynamically loaded scripts
performance.getEntriesByType('resource').forEach(r => {
if (r.name.includes('.js') || r.initiatorType === 'script') {
urls.add(r.name);
}
});
return Array.from(urls);
''') or []
except Exception as e:
print(f"[ScriptCollector] Error getting scripts: {e}")
js_urls = []
print(f"[ScriptCollector] Found {len(js_urls)} script URLs")
# Create page directory
page_dir = self.output_dir / page_name
page_dir.mkdir(exist_ok=True)
new_count = 0
for js_url in js_urls:
if js_url in self.collected:
continue
try:
# Use CDP to fetch script content (bypasses CORS)
result = page.run_cdp('Network.loadNetworkResource',
frameId=page.run_cdp('Page.getFrameTree')['frameTree']['frame']['id'],
url=js_url,
options={'disableCache': False, 'includeCredentials': False}
)
content = None
if result.get('resource', {}).get('success'):
# Content might be base64 encoded
stream = result['resource'].get('stream')
if stream:
# Read from stream
data = page.run_cdp('IO.read', handle=stream)
content = data.get('data', '')
if data.get('base64Encoded'):
content = base64.b64decode(content).decode('utf-8', errors='ignore')
page.run_cdp('IO.close', handle=stream)
else:
content = result['resource'].get('content', '')
if not content or len(content) < 50:
# Fallback: try regular fetch
content = page.run_js(f'''
return await fetch("{js_url}").then(r => r.text()).catch(() => null);
''')
if content and len(content) > 50:
# Generate safe filename
parsed = urlparse(js_url)
filename = parsed.path.split('/')[-1] or 'script.js'
filename = filename.split('?')[0]
if not filename.endswith('.js'):
filename += '.js'
# Add hash for uniqueness
url_hash = hashlib.md5(js_url.encode()).hexdigest()[:8]
filename = f"{url_hash}_{filename}"
# Save script
filepath = page_dir / filename
filepath.write_text(content, encoding='utf-8')
self.collected[js_url] = str(filepath)
new_count += 1
size_kb = len(content) / 1024
print(f"[ScriptCollector] ✓ {filename} ({size_kb:.1f}KB)")
except Exception as e:
# Try simple approach as last resort
try:
content = page.run_js(f'return await fetch("{js_url}").then(r=>r.text()).catch(()=>null)')
if content and len(content) > 50:
parsed = urlparse(js_url)
filename = parsed.path.split('/')[-1] or 'script.js'
filename = filename.split('?')[0]
if not filename.endswith('.js'):
filename += '.js'
url_hash = hashlib.md5(js_url.encode()).hexdigest()[:8]
filename = f"{url_hash}_{filename}"
filepath = page_dir / filename
filepath.write_text(content, encoding='utf-8')
self.collected[js_url] = str(filepath)
new_count += 1
print(f"[ScriptCollector] ✓ {filename} (fallback)")
except:
pass
print(f"[ScriptCollector] Downloaded {new_count} new scripts")
return new_count
def save(self) -> Path:
"""Save index of all collected scripts."""
index = {
'timestamp': datetime.now().isoformat(),
'pages': self.page_count,
'total_scripts': len(self.collected),
'scripts': self.collected
}
index_file = self.output_dir / 'index.json'
with open(index_file, 'w', encoding='utf-8') as f:
json.dump(index, f, indent=2, ensure_ascii=False)
print(f"[ScriptCollector] Saved index: {index_file}")
print(f"[ScriptCollector] Total: {len(self.collected)} scripts from {self.page_count} pages")
return index_file
def disable(self):
"""Disable collection."""
self.enabled = False
def enable(self):
"""Enable collection."""
self.enabled = True
# Global function for easy access
def collect_scripts(page, page_name: str = None) -> int:
"""Collect scripts from page using singleton collector."""
return ScriptCollector.get_instance().collect(page, page_name)
def save_collected_scripts() -> Path:
"""Save all collected scripts."""
return ScriptCollector.get_instance().save()
|