Ross
adc21f5795
- Added `capture_passive_playwright.py` for synchronous passive capture of XHR/fetch responses. - Added `capture_passive_playwright_async.py` for asynchronous passive capture using Playwright's async API. - Introduced `save_page_snapshots.py` to save full page HTML snapshots with deduplication. - Removed obsolete CSRF token capture JSON file.
280 lines
9.8 KiB
Python
280 lines
9.8 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Save full page HTML snapshots after page loads and periodically while you browse.
|
|
|
|
This script launches a persistent Playwright profile (so you can log in),
|
|
optionally attempts automatic login, then either performs a one-shot snapshot
|
|
or continues saving snapshots as you browse. Snapshots are de-duplicated by
|
|
content hash to avoid writing identical files repeatedly.
|
|
|
|
Usage examples:
|
|
# manual login, one-shot snapshot after reload
|
|
python scrapers/save_page_snapshots.py --url https://app.statdx.com/ --output-dir xhr_captured
|
|
|
|
# auto-login and continuous snapshots while you browse
|
|
python scrapers/save_page_snapshots.py --continuous --username you --password secret --output-dir xhr_captured
|
|
|
|
"""
|
|
from pathlib import Path
|
|
import argparse
|
|
import time
|
|
import hashlib
|
|
import json
|
|
import mimetypes
|
|
import os
|
|
from datetime import datetime, timezone
|
|
|
|
try:
|
|
from loguru import logger
|
|
except Exception:
|
|
import logging
|
|
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
|
|
logger = logging.getLogger("save_page_snapshots")
|
|
|
|
from playwright.sync_api import sync_playwright
|
|
from dotenv import load_dotenv
|
|
|
|
# load .env
|
|
load_dotenv()
|
|
|
|
|
|
def sanitize_filename(s: str) -> str:
|
|
safe = []
|
|
for ch in s:
|
|
if ch.isalnum() or ch in ('-', '_', '.'):
|
|
safe.append(ch)
|
|
else:
|
|
safe.append('-')
|
|
name = ''.join(safe)
|
|
if len(name) > 180:
|
|
h = hashlib.sha1(s.encode('utf-8')).hexdigest()[:8]
|
|
name = name[:120] + '-' + h
|
|
return name
|
|
|
|
|
|
def write_text(path: Path, text: str):
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
with open(path, 'w', encoding='utf-8') as f:
|
|
f.write(text)
|
|
|
|
|
|
def write_json(path: Path, obj):
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
with open(path, 'w', encoding='utf-8') as f:
|
|
json.dump(obj, f, ensure_ascii=False, indent=2)
|
|
|
|
|
|
def now_ts():
|
|
return datetime.now(timezone.utc).strftime('%Y%m%dT%H%M%SZ')
|
|
|
|
|
|
def snapshot_page(page, out_dir: Path, index_path: Path, last_hashes: dict, min_interval: float = 3.0):
|
|
"""Capture page content and write HTML + meta if content changed or enough time passed."""
|
|
try:
|
|
url = page.url
|
|
except Exception:
|
|
url = 'unknown'
|
|
|
|
try:
|
|
content = page.content()
|
|
except Exception as e:
|
|
logger.exception('Failed to get page.content(): {}', e)
|
|
return None
|
|
|
|
h = hashlib.sha1(content.encode('utf-8')).hexdigest()
|
|
prev = last_hashes.get(url)
|
|
ts = now_ts()
|
|
|
|
# If unchanged and we saved recently, skip
|
|
if prev and prev.get('hash') == h and (time.time() - prev.get('ts', 0)) < min_interval:
|
|
logger.debug('Snapshot skipped (no change) for {}', url)
|
|
return None
|
|
|
|
# prepare filenames
|
|
name = sanitize_filename(url.replace('https://', '').replace('http://', ''))
|
|
short = h[:8]
|
|
html_name = f"{name}_{short}_{ts}.html"
|
|
meta_name = f"{name}_{short}_{ts}.json"
|
|
|
|
html_path = out_dir / html_name
|
|
meta_path = out_dir / meta_name
|
|
|
|
try:
|
|
write_text(html_path, content)
|
|
except Exception as e:
|
|
logger.exception('Failed to write HTML snapshot: {}', e)
|
|
return None
|
|
|
|
meta = {
|
|
'url': url,
|
|
'timestamp': ts,
|
|
'file': str(html_path),
|
|
'sha1': h,
|
|
'title': (page.title() if page else None),
|
|
}
|
|
try:
|
|
write_json(meta_path, meta)
|
|
except Exception:
|
|
logger.exception('Failed to write meta file')
|
|
|
|
# append to index
|
|
try:
|
|
entry = {'url': url, 'timestamp': ts, 'html_file': str(html_path), 'meta_file': str(meta_path), 'sha1': h}
|
|
with open(index_path, 'a', encoding='utf-8') as idx:
|
|
idx.write(json.dumps(entry, ensure_ascii=False) + '\n')
|
|
except Exception:
|
|
logger.exception('Failed to append to index')
|
|
|
|
last_hashes[url] = {'hash': h, 'ts': time.time()}
|
|
logger.info('Saved snapshot: {} ({} bytes)', html_path.name, len(content))
|
|
return html_path
|
|
|
|
|
|
def attempt_autologin(page, username: str, password: str, post_login_selector: str, wait_after: float = 3.0):
|
|
if not username or not password:
|
|
return False
|
|
logger.info('Attempting automatic login')
|
|
# Common selectors for STATdx and similar pages
|
|
user_selectors = ['input[name="username"]', 'input.usernameSelector', 'input[type="email"]', 'input[name*="email" i]', 'input[name*="user" i]', 'input[type="text"]']
|
|
pass_selectors = ['input[type="password"]', 'input[name="password"]', 'input.passwordSelector']
|
|
|
|
user_sel = None
|
|
for sel in user_selectors:
|
|
try:
|
|
if page.query_selector(sel):
|
|
user_sel = sel
|
|
break
|
|
except Exception:
|
|
continue
|
|
|
|
pass_sel = None
|
|
for sel in pass_selectors:
|
|
try:
|
|
if page.query_selector(sel):
|
|
pass_sel = sel
|
|
break
|
|
except Exception:
|
|
continue
|
|
|
|
if not user_sel or not pass_sel:
|
|
logger.warning('Could not find username/password fields for auto-login')
|
|
return False
|
|
|
|
try:
|
|
page.fill(user_sel, username)
|
|
time.sleep(0.1)
|
|
page.fill(pass_sel, password)
|
|
time.sleep(0.1)
|
|
# try submit
|
|
submit_selectors = ['button[type=submit]', 'input[type=submit]', 'button:has-text("Sign in")', 'button:has-text("Sign In")', 'button:has-text("Log in")']
|
|
clicked = False
|
|
for s in submit_selectors:
|
|
try:
|
|
btn = page.query_selector(s)
|
|
if btn:
|
|
btn.click()
|
|
clicked = True
|
|
logger.info('Clicked submit button using selector: {}', s)
|
|
break
|
|
except Exception:
|
|
continue
|
|
if not clicked:
|
|
page.press(pass_sel, 'Enter')
|
|
|
|
# wait for post-login selector
|
|
try:
|
|
if post_login_selector:
|
|
page.wait_for_selector(post_login_selector, timeout=10000)
|
|
except Exception:
|
|
logger.info('Post-login selector not found within timeout')
|
|
time.sleep(wait_after)
|
|
return True
|
|
except Exception:
|
|
logger.exception('Auto-login failed')
|
|
return False
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--url', '-u', default='https://app.statdx.com/')
|
|
parser.add_argument('--profile', '-p', default='playwright_profile')
|
|
parser.add_argument('--output-dir', '-o', default='xhr_captured')
|
|
parser.add_argument('--headless', action='store_true')
|
|
parser.add_argument('--continuous', action='store_true', help='Keep capturing while you browse until interrupted')
|
|
parser.add_argument('--capture-wait', type=float, default=6.0, help='Seconds to wait before initial snapshot')
|
|
parser.add_argument('--poll-interval', type=float, default=5.0, help='Periodic snapshot interval when continuous')
|
|
parser.add_argument('--min-interval', type=float, default=3.0, help='Minimum seconds between snapshots for same URL')
|
|
parser.add_argument('--username', help='STATdx username (or use STATDX_USERNAME env var)')
|
|
parser.add_argument('--password', help='STATdx password (or use STATDX_PASSWORD env var)')
|
|
parser.add_argument('--post-login-selector', default='#ds-app')
|
|
parser.add_argument('--no-prompt', action='store_true')
|
|
args = parser.parse_args()
|
|
|
|
out_dir = Path(args.output_dir)
|
|
out_dir.mkdir(parents=True, exist_ok=True)
|
|
index_path = out_dir / 'snapshot_index.jsonl'
|
|
|
|
username = args.username or os.getenv('STATDX_USERNAME')
|
|
password = args.password or os.getenv('STATDX_PASSWORD')
|
|
|
|
last_hashes = {}
|
|
|
|
with sync_playwright() as p:
|
|
try:
|
|
context = p.chromium.launch_persistent_context(user_data_dir=args.profile, headless=args.headless, channel='chrome')
|
|
except Exception:
|
|
context = p.chromium.launch_persistent_context(user_data_dir=args.profile, headless=args.headless)
|
|
|
|
page = context.new_page()
|
|
logger.info('Opening %s', args.url)
|
|
page.goto(args.url)
|
|
|
|
# attempt auto-login
|
|
if username and password:
|
|
attempt_autologin(page, username, password, args.post_login_selector)
|
|
|
|
# wait before initial snapshot to let in-flight XHRs populate DOM
|
|
logger.info('Waiting %.1f sec before initial snapshot', args.capture_wait)
|
|
time.sleep(args.capture_wait)
|
|
|
|
# initial snapshot
|
|
snapshot_page(page, out_dir, index_path, last_hashes, min_interval=args.min_interval)
|
|
|
|
if args.continuous:
|
|
logger.info('Continuous snapshot mode: saving on navigation and every %.1f sec', args.poll_interval)
|
|
|
|
# on navigation events, take a snapshot (debounced by min_interval)
|
|
def on_load():
|
|
try:
|
|
snapshot_page(page, out_dir, index_path, last_hashes, min_interval=args.min_interval)
|
|
except Exception:
|
|
logger.exception('Error during on_load snapshot')
|
|
|
|
page.on('load', lambda: on_load())
|
|
page.on('domcontentloaded', lambda: on_load())
|
|
page.on('framenavigated', lambda frame: on_load())
|
|
|
|
try:
|
|
# periodic polling snapshot
|
|
while True:
|
|
time.sleep(args.poll_interval)
|
|
snapshot_page(page, out_dir, index_path, last_hashes, min_interval=args.min_interval)
|
|
except KeyboardInterrupt:
|
|
logger.info('Interrupted by user, closing')
|
|
else:
|
|
# one-shot: save a final snapshot after a short delay to capture dynamic updates
|
|
try:
|
|
time.sleep(1.0)
|
|
snapshot_page(page, out_dir, index_path, last_hashes, min_interval=args.min_interval)
|
|
except Exception:
|
|
logger.exception('Error taking final snapshot')
|
|
|
|
try:
|
|
context.close()
|
|
except Exception:
|
|
pass
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|