Files
legal-ai/mcp-server/src/legal_mcp/court_fetch_service/camofox_client.py
Chaim e186183527 fix(X13): harden court-fetch against browser leaks + reaper for task-master-mcp leak
שלוש שכבות-הגנה נגד דליפת-זיכרון מדפדפנים יתומים, + טיפול בדליפה הגדולה
בפועל בשרת (task-master-mcp).

- camofox_client.py:
  - asyncio.wait_for קשיח סביב כל ה-fetch (COURT_FETCH_HARD_TIMEOUT_S=180ש')
    — hang → ביטול → async-with tear-down → reap.
  - _reap_orphan_browsers(): הורג camoufox-bin יתומים (ppid=1) לפני ואחרי כל
    fetch. סדרתיות (INV-CF4) → כל ppid=1 הוא שארית בטוחה.
- scripts/reap_orphan_procs.py: reaper כללי ל-task-master-mcp (~3GB יתומים)
  + camoufox-bin. רק ppid=1; /proc טהור. --dry-run / --loop N.
- scripts/legal-reaper.config.cjs: דמון pm2 (loop 180s, max_memory_restart 100M).
- X13 spec + SCRIPTS.md: תיעוד שכבות-ההגנה.

max_memory_restart בשירות (1.5G) כבר נותן רשת-ביטחון ברמת-התהליך.
Invariants: מקיים INV-CF4 (politeness/serial) — ללא שינוי חוזה.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-07 19:43:53 +00:00

315 lines
13 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Camoufox driver for נט המשפט — calibrated, proven flow (X13, Tier 1).
Open-source, zero-API-cost: drives a **Camoufox** stealth browser (a Firefox
fork with C++ fingerprint spoofing) via its official Python package
(``camoufox.async_api``) — in-process, no separate Node server. The full flow
was reverse-engineered and validated end-to-end against עת"מ 46111-12-22
(2026-06-07): a 34-page verdict PDF retrieved with **no smart-card and no
CAPTCHA-solving**.
The proven path:
1. homepage → DOM-click ``btnExternalSearchCases`` ("תיקים לפי מס' תיק מקור").
2. Fill the visible header case-locator: ``BamaCaseNumberTextBoxH`` = case
number, ``BamaMonthYearTextBoxHT`` = "MM-YY"; click ``SearchHeaderCaseButton``.
→ lands on ``FolderCaseDetails/CaseDetails.aspx`` for the case.
3. Click the "פסקי דין" sidebar tab → ``Decisions/DecisionList.aspx``.
4. Click the document → popup ``Viewer/NGCSViewerPage.aspx?DocumentNumber=…``.
5. The viewer renders pages as PNG images via the ``GetImages`` PageMethod —
**served without reCAPTCHA** (the reCAPTCHA on the viewer only gates the
explicit save/print, which we don't use). Capture the internal
``documentNumber`` from the viewer's first ``GetImages`` call, then pull
every 4-page batch via ``fetch`` **with header ``X-Requested-With:
XMLHttpRequest``** (required — the F5 WAF blocks AJAX calls without it).
6. Decode the base64 PNGs → assemble a PDF (Pillow). The existing ingest
pipeline OCRs it (Google Vision) → text → corpus.
Operational requirements (see scripts/legal-court-fetch-service.config.cjs):
* a virtual display — Camoufox/Firefox crashes headless on this server
without one. Set ``DISPLAY`` to a running Xvfb (e.g. ``:99``).
* RAM — a Firefox content process loading the heavy ASP.NET pages needs
~0.51 GB; keep the box from swapping.
reCAPTCHA note: ``recaptcha_audio`` (local Whisper) remains as a fallback for
the explicit-PDF-download path, but the primary image-API path needs no
solving, so it is normally unused.
"""
from __future__ import annotations
import asyncio
import base64
import io
import json
import logging
import os
import re
logger = logging.getLogger(__name__)
NGCS_HOME = "https://www.court.gov.il/ngcs.web.site/homepage.aspx"
# Headless Camoufox needs a virtual display on this server.
_DISPLAY = os.environ.get("DISPLAY", "")
_NAV_TIMEOUT_MS = int(float(os.environ.get("COURT_FETCH_BROWSER_TIMEOUT_S", "60")) * 1000)
_PAGE_BATCH = 4 # the viewer's GetImages batch size
_MAX_PAGES = 400 # hard cap on a single document
# Hard wall-clock cap on a single fetch so a hung browser can't pin a Firefox
# process forever (anti-leak; INV-CF4 politeness). The async-with cleanup runs
# on the resulting CancelledError, tearing the browser down.
_FETCH_HARD_TIMEOUT_S = float(os.environ.get("COURT_FETCH_HARD_TIMEOUT_S", "180"))
def _reap_orphan_browsers() -> int:
"""Kill any ``camoufox-bin`` orphaned to ``ppid=1`` before we launch.
Fetching is serial (INV-CF4), so any browser not owned by a live parent is
a leftover from a prior crashed/killed fetch. Pure /proc, best-effort —
never raises into the fetch path.
"""
killed = 0
try:
for pid in os.listdir("/proc"):
if not pid.isdigit():
continue
try:
with open(f"/proc/{pid}/status", "rb") as f:
status = f.read().decode("utf-8", "replace")
with open(f"/proc/{pid}/cmdline", "rb") as f:
cmd = f.read().decode("utf-8", "replace")
except OSError:
continue
if "camoufox-bin" not in cmd:
continue
ppid = 0
for line in status.splitlines():
if line.startswith("PPid:"):
try: ppid = int(line.split()[1])
except (IndexError, ValueError): pass
break
if ppid == 1:
try:
os.kill(int(pid), 9)
killed += 1
except OSError:
pass
except OSError:
pass
if killed:
logger.warning("reaped %d orphaned camoufox-bin before fetch", killed)
return killed
class CamofoxUnavailable(RuntimeError):
"""Camoufox (or its virtual display) isn't available."""
class NgcsFlowError(RuntimeError):
"""A step in the נט-המשפט flow failed (navigation / not found / blocked)."""
def is_enabled() -> bool:
"""True if the Camoufox package imports (browser binary present)."""
try:
import camoufox.async_api # noqa: F401
return True
except Exception:
return False
async def health() -> dict:
return {"camoufox_import": is_enabled(), "display": _DISPLAY or "(none)"}
async def _fill_visible(page, id_substr: str, value: str) -> bool:
for el in await page.locator(f"input[id*='{id_substr}']").all():
try:
if await el.is_visible() and await el.is_editable():
await el.fill(value)
return True
except Exception:
continue
return False
async def _reach_viewer(page, *, case_number: str, month_year: str):
"""Drive home → search → case → פסקי דין → viewer popup. Returns the popup page."""
await page.goto(NGCS_HOME, wait_until="domcontentloaded", timeout=_NAV_TIMEOUT_MS)
await page.wait_for_timeout(2500)
await page.eval_on_selector(
"#Header1_UpperMenu1_btnExternalSearchCases", "el => el.click()"
)
try:
await page.wait_for_load_state("domcontentloaded", timeout=_NAV_TIMEOUT_MS)
except Exception:
pass
await page.wait_for_timeout(4500)
if not await _fill_visible(page, "BamaCaseNumberTextBoxH", case_number):
raise NgcsFlowError("שדה מספר-תיק לא נמצא בעמוד החיפוש")
my_filled = False
for el in await page.locator("input[id*='BamaMonthYearTextBoxHT']").all():
if await el.is_visible():
await el.click()
await page.keyboard.type(month_year, delay=60)
my_filled = True
break
if not my_filled:
raise NgcsFlowError("שדה חודש-שנה לא נמצא")
clicked = False
for b in await page.locator("[id*='SearchHeaderCaseButton']").all():
if await b.is_visible():
await b.click()
clicked = True
break
if not clicked:
raise NgcsFlowError("כפתור החיפוש לא נמצא")
await page.wait_for_timeout(6000)
if "CaseDetails" not in page.url:
raise NgcsFlowError(
f"לא הגענו לעמוד-התיק (URL={page.url[:80]}) — ייתכן שהתיק לא נמצא/לא פתוח לעיון"
)
# פסקי דין tab → DecisionList
psak = page.locator("a:has-text('פסקי דין')")
opened = False
for i in range(await psak.count()):
el = psak.nth(i)
if await el.is_visible():
await el.click()
opened = True
break
if not opened:
raise NgcsFlowError("לשונית 'פסקי דין' לא נמצאה בעמוד-התיק")
await page.wait_for_timeout(6000)
# open the verdict document viewer (popup)
viewers = page.locator(
"a[href*='Viewer'],[onclick*='Viewer'],a[href*='Document'],a:has-text('צפייה')"
)
async with page.context.expect_page(timeout=15000) as pop:
clicked = False
for i in range(await viewers.count()):
el = viewers.nth(i)
if await el.is_visible():
await el.click()
clicked = True
break
if not clicked:
raise NgcsFlowError("לא נמצא מסמך פסק-דין לצפייה")
return await pop.value
async def fetch_admin_verdict(
*, file_number: str, month: str, year: str, case_number: str, court: str
) -> dict:
"""Fetch an admin/district court verdict as a PDF. Returns
``{content: bytes, filename, source_url, court}``; raises on failure.
``file_number``/``month``/``year`` are the נט-המשפט triple (e.g. 46111/12/22).
"""
try:
from camoufox.async_api import AsyncCamoufox
except Exception as e:
raise CamofoxUnavailable(
"חבילת camoufox אינה מותקנת/זמינה. הרץ `pip install camoufox` ו-"
"`python -m camoufox fetch`. ראה docs/spec/X13-court-fetch.md."
) from e
if not _DISPLAY:
# Headless Firefox crashes here without a virtual display.
raise CamofoxUnavailable(
"אין DISPLAY — Camoufox דורש Xvfb על שרת ללא מסך. הפעל Xvfb (למשל :99) "
"והגדר DISPLAY (ראה pm2 config)."
)
month_year = f"{int(month):02d}-{year[-2:]}"
# Belt-and-suspenders against browser leaks: kill any orphaned browser from
# a prior crashed fetch before we launch a new one (serial → safe).
_reap_orphan_browsers()
async def _run() -> dict:
doc_num = {"v": None}
async def on_resp(resp):
if "GetImages" in resp.url and not doc_num["v"]:
try:
doc_num["v"] = json.loads(resp.request.post_data).get("documentNumber")
except Exception:
pass
async with AsyncCamoufox(
headless=True, geoip=False, humanize=True, locale="he-IL"
) as browser:
page = await browser.new_page()
page.context.on("response", lambda r: asyncio.create_task(on_resp(r)))
vp = await _reach_viewer(page, case_number=file_number, month_year=month_year)
source_url = vp.url
await vp.wait_for_timeout(9000)
if not doc_num["v"]:
raise NgcsFlowError("לא נלכד documentNumber מהצופה (ייתכן שהמסמך לא נטען)")
# Pull every page batch through fetch() with X-Requested-With (WAF-safe).
imgs = await vp.evaluate(
"""async (args) => {
const [dn, maxPages, batch] = args;
const url = window.location.href.split('?')[0] + '/GetImages';
const out = {};
for (let f = 0; f < maxPages; f += batch) {
let d;
try {
const r = await fetch(url, {method:'POST', credentials:'include',
headers:{'Content-Type':'application/json; charset=utf-8',
'X-Requested-With':'XMLHttpRequest'},
body: JSON.stringify({documentNumber:dn, fromIndex:f, toIndex:f+batch-1})});
if (!r.ok) break;
const j = await r.json(); d = (j.d !== undefined) ? j.d : j;
} catch (e) { break; }
if (!Array.isArray(d) || d.length === 0) break;
d.forEach((html, k) => { if (html) out[f+k] = html; });
if (d.length < batch) break;
await new Promise(r => setTimeout(r, 350));
}
return out;
}""",
[doc_num["v"], _MAX_PAGES, _PAGE_BATCH],
)
if not imgs:
raise NgcsFlowError("לא התקבלו עמודי-מסמך מ-GetImages")
from PIL import Image
pages = []
for idx in sorted(imgs, key=lambda x: int(x)):
m = re.search(r"base64,([A-Za-z0-9+/=]+)", imgs[idx] or "")
if not m:
continue
pages.append(Image.open(io.BytesIO(base64.b64decode(m.group(1)))).convert("RGB"))
if not pages:
raise NgcsFlowError("עמודי-המסמך לא ניתנים לפענוח (base64)")
buf = io.BytesIO()
pages[0].save(buf, format="PDF", save_all=True, append_images=pages[1:])
content = buf.getvalue()
logger.info("נט המשפט: fetched %s%d pages, %d bytes",
case_number, len(pages), len(content))
return {
"content": content,
"filename": f"{case_number}.pdf",
"source_url": source_url,
"court": court or "בית משפט מחוזי",
"pages": len(pages),
}
# Hard wall-clock cap: on a hung browser, the timeout cancels _run(); the
# async-with __aexit__ tears the browser down, and the reap below sweeps any
# process that outlived the cancellation.
try:
return await asyncio.wait_for(_run(), _FETCH_HARD_TIMEOUT_S)
except asyncio.TimeoutError:
_reap_orphan_browsers()
raise NgcsFlowError(
f"אחזור עבר את מגבלת-הזמן ({_FETCH_HARD_TIMEOUT_S:.0f}ש') ובוטל"
)
finally:
_reap_orphan_browsers()