notebookvb
This commit is contained in:
Vladimir Buzalka
@@ -0,0 +1,289 @@
|
||||
"""
|
||||
01 — Stáhni číselníky VZP z point.vzp.cz/Cms/Document (sekce „Číselníky").
|
||||
Soubory přejmenuje do formátu: YYYY-MM-DD NázevLinku (popis).zip
|
||||
Ověří co již existuje v cílovém adresáři a stáhne pouze chybějící soubory.
|
||||
Použití: python 01_stahni_ciselniky.py [--dry-run]
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
|
||||
# Windows konzole - povol UTF-8 výstup
|
||||
if sys.stdout.encoding != "utf-8":
|
||||
import io
|
||||
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "Knihovny"))
|
||||
from najdi_dropbox import get_dropbox_root
|
||||
|
||||
TARGET_DIR = os.path.join(
|
||||
get_dropbox_root(),
|
||||
"Ordinace", "Dokumentace_ke_zpracování", "Zúčtovací zprávy", "Číselníky"
|
||||
)
|
||||
|
||||
DRY_RUN = False # True = pouze zobraz co by se stáhlo, nic nestahuj
|
||||
|
||||
CHROME_PROFILE = os.path.join(os.path.dirname(__file__), "chrome_profile")
|
||||
COOKIES_FILE = os.path.join(os.path.dirname(__file__), "vzp_cookies.json")
|
||||
|
||||
# Issuer CN certifikátu v Windows store (CurrentUser\My)
|
||||
CERT_ISSUER_CN = "I.CA Public CA/RSA 06/2022"
|
||||
|
||||
|
||||
def _set_chrome_cert_policy() -> None:
|
||||
"""Nastaví Chrome politiku AutoSelectCertificateForUrls — Chrome vybere certifikát automaticky."""
|
||||
import winreg
|
||||
policy = json.dumps({
|
||||
"pattern": "https://[*.]vzp.cz",
|
||||
"filter": {"ISSUER": {"CN": CERT_ISSUER_CN}},
|
||||
})
|
||||
key_path = r"SOFTWARE\Policies\Google\Chrome\AutoSelectCertificateForUrls"
|
||||
try:
|
||||
key = winreg.CreateKey(winreg.HKEY_CURRENT_USER, key_path)
|
||||
winreg.SetValueEx(key, "1", 0, winreg.REG_SZ, policy)
|
||||
winreg.CloseKey(key)
|
||||
print(f" Chrome politika nastavena (issuer: {CERT_ISSUER_CN})")
|
||||
except Exception as e:
|
||||
print(f" Varování: nelze nastavit Chrome politiku: {e}")
|
||||
|
||||
|
||||
def load_cookies(context) -> int:
|
||||
if not os.path.exists(COOKIES_FILE):
|
||||
return 0
|
||||
try:
|
||||
with open(COOKIES_FILE, "r", encoding="utf-8") as f:
|
||||
cookies = json.load(f)
|
||||
context.add_cookies(cookies)
|
||||
return len(cookies)
|
||||
except Exception as e:
|
||||
print(f" Chyba při načítání cookies: {e}")
|
||||
return 0
|
||||
|
||||
|
||||
def save_cookies(context) -> int:
|
||||
try:
|
||||
vzp = [c for c in context.cookies() if "vzp.cz" in c.get("domain", "")]
|
||||
with open(COOKIES_FILE, "w", encoding="utf-8") as f:
|
||||
json.dump(vzp, f, indent=2, ensure_ascii=False)
|
||||
return len(vzp)
|
||||
except Exception as e:
|
||||
print(f" Chyba při ukládání cookies: {e}")
|
||||
return 0
|
||||
|
||||
|
||||
def sanitize_filename(name: str) -> str:
|
||||
"""Odstraní znaky nepovolené ve Windows názvech souborů."""
|
||||
return re.sub(r'[\\/:*?"<>|]', '_', name).strip()
|
||||
|
||||
|
||||
# True = přidat popis v závorce do názvu souboru
|
||||
SECTIONS = {
|
||||
"Číselníky": True,
|
||||
"Soubor platných IČP": False,
|
||||
}
|
||||
|
||||
|
||||
def extract_entries(page) -> list[dict]:
|
||||
"""
|
||||
Projde tabulky sekcí definovaných v SECTIONS a vrátí seznam slovníků:
|
||||
orig_fname — původní název souboru z atributu download
|
||||
new_fname — nový název: YYYY-MM-DD Název [(popis)].zip
|
||||
link — Playwright Locator pro kliknutí
|
||||
"""
|
||||
entries = []
|
||||
for section, include_description in SECTIONS.items():
|
||||
rows = page.locator(f"h3:has-text('{section}') + table tbody tr").all()
|
||||
entries.extend(_extract_rows(rows, include_description=include_description))
|
||||
return entries
|
||||
|
||||
|
||||
def _extract_rows(rows: list, include_description: bool = True) -> list[dict]:
|
||||
entries = []
|
||||
i = 0
|
||||
while i < len(rows):
|
||||
row = rows[i]
|
||||
dl_links = row.locator("a[download]").all()
|
||||
|
||||
if not dl_links:
|
||||
i += 1
|
||||
continue
|
||||
|
||||
# Datum platnosti z <time datetime="YYYY-MM-DD">
|
||||
time_el = row.locator("time[datetime]")
|
||||
date_iso = time_el.get_attribute("datetime") if time_el.count() > 0 else ""
|
||||
|
||||
# Zobrazený název — přímý link nebo dropdown toggle
|
||||
span = row.locator("a[download] span[title='Stáhnout']")
|
||||
if span.count() > 0:
|
||||
display_name = span.first.inner_text().strip()
|
||||
else:
|
||||
toggle = row.locator(".dropdown-toggle span[title='Stáhnout']")
|
||||
display_name = toggle.first.inner_text().strip() if toggle.count() > 0 else ""
|
||||
|
||||
# Popis z následující řádky (má colspan="5" a div.text-gray)
|
||||
description = ""
|
||||
if i + 1 < len(rows):
|
||||
desc_div = rows[i + 1].locator(".text-gray")
|
||||
if desc_div.count() > 0:
|
||||
description = desc_div.first.inner_text().strip()
|
||||
|
||||
is_multi = len(dl_links) > 1
|
||||
for link in dl_links:
|
||||
orig_fname = link.get_attribute("download") or ""
|
||||
ext = os.path.splitext(orig_fname)[1] or ".zip"
|
||||
|
||||
if is_multi:
|
||||
# Pro více variant (např. LEKY má "leky" a "lekyp") přidej základ
|
||||
# původního názvu jako rozlišení: odstraní timestamp prefix (12 číslic-)
|
||||
base = re.sub(r'^\d{12}-', '', orig_fname)
|
||||
base = os.path.splitext(base)[0]
|
||||
name = f"{date_iso} {display_name} {base} ({description}){ext}" if include_description else f"{date_iso} {display_name} {base}{ext}"
|
||||
else:
|
||||
name = f"{date_iso} {display_name} ({description}){ext}" if include_description else f"{date_iso} {display_name}{ext}"
|
||||
|
||||
entries.append({
|
||||
"orig_fname": orig_fname,
|
||||
"new_fname": sanitize_filename(name),
|
||||
"link": link,
|
||||
})
|
||||
|
||||
i += 1
|
||||
|
||||
return entries
|
||||
|
||||
|
||||
def get_existing_files() -> set[str]:
|
||||
if not os.path.isdir(TARGET_DIR):
|
||||
return set()
|
||||
return {f for f in os.listdir(TARGET_DIR) if f.lower().endswith(".zip")}
|
||||
|
||||
|
||||
def ensure_logged_in(page, context):
|
||||
"""
|
||||
Pokud jsme přesměrováni na login, provede přihlášení certifikátem
|
||||
a vrátí stránku po přesměrování zpět na point.vzp.cz. Jinak vrátí původní page.
|
||||
Při selhání vrátí None.
|
||||
"""
|
||||
if not page.url.startswith("https://auth.vzp.cz/signin"):
|
||||
return page
|
||||
|
||||
print("[stahování] Přihlašovací stránka — klikám na certifikát...")
|
||||
cert_btn = page.locator("a, button").filter(has_text=re.compile(r"certifikát", re.I)).first
|
||||
cert_btn.wait_for(state="visible", timeout=10_000)
|
||||
cert_btn.click(no_wait_after=True)
|
||||
|
||||
print("[stahování] Čekám na přesměrování (max 60 s)...")
|
||||
try:
|
||||
page.wait_for_url("https://point.vzp.cz/**", timeout=60_000)
|
||||
except Exception:
|
||||
print(f"[stahování] Timeout čekání na přesměrování. URL: {page.url}")
|
||||
|
||||
if not page.url.startswith("https://point.vzp.cz"):
|
||||
print(f"[stahování] Auth selhala, URL: {page.url}")
|
||||
return None
|
||||
|
||||
print("[stahování] Přihlášení úspěšné.")
|
||||
return page
|
||||
|
||||
|
||||
def download_ciselniky(dry_run: bool = False) -> None:
|
||||
try:
|
||||
from playwright.sync_api import sync_playwright
|
||||
except ImportError:
|
||||
print("[chyba] pip install playwright && playwright install chromium")
|
||||
return
|
||||
|
||||
os.makedirs(TARGET_DIR, exist_ok=True)
|
||||
existing = get_existing_files()
|
||||
print(f"Cílový adresář: {TARGET_DIR}")
|
||||
print(f"Již staženo: {len(existing)} souborů")
|
||||
|
||||
_set_chrome_cert_policy()
|
||||
|
||||
with sync_playwright() as p:
|
||||
context = p.chromium.launch_persistent_context(
|
||||
user_data_dir=CHROME_PROFILE,
|
||||
channel="chrome",
|
||||
headless=False,
|
||||
slow_mo=200,
|
||||
ignore_https_errors=True,
|
||||
accept_downloads=True,
|
||||
)
|
||||
try:
|
||||
loaded = load_cookies(context)
|
||||
print(f"Cookies načtené z JSON: {loaded}")
|
||||
|
||||
page = context.new_page()
|
||||
|
||||
print("[stahování] Naviguji na VZP Point...")
|
||||
try:
|
||||
page.goto("https://point.vzp.cz/Cms/Document", wait_until="domcontentloaded", timeout=30_000)
|
||||
except Exception as e:
|
||||
print(f"[stahování] Navigace: {e}")
|
||||
|
||||
page = ensure_logged_in(page, context)
|
||||
if page is None:
|
||||
return
|
||||
|
||||
page.wait_for_load_state("networkidle", timeout=30_000)
|
||||
|
||||
entries = extract_entries(page)
|
||||
print(f"[stahování] Nalezeno {len(entries)} souborů v sekci Číselníky.")
|
||||
print()
|
||||
|
||||
downloaded = 0
|
||||
skipped = 0
|
||||
|
||||
for entry in entries:
|
||||
new_fname = entry["new_fname"]
|
||||
orig_fname = entry["orig_fname"]
|
||||
|
||||
if new_fname in existing:
|
||||
print(f" ✓ {new_fname}")
|
||||
skipped += 1
|
||||
continue
|
||||
|
||||
if dry_run:
|
||||
print(f" → {new_fname}")
|
||||
print(f" orig: {orig_fname}")
|
||||
downloaded += 1
|
||||
continue
|
||||
|
||||
dest = os.path.join(TARGET_DIR, new_fname)
|
||||
try:
|
||||
with page.expect_download(timeout=60_000) as dl_info:
|
||||
entry["link"].dispatch_event("click")
|
||||
dl = dl_info.value
|
||||
dl.save_as(dest)
|
||||
size = os.path.getsize(dest)
|
||||
print(f" ↓ {new_fname} ({size:,} B)")
|
||||
downloaded += 1
|
||||
except Exception as e:
|
||||
print(f" ! {orig_fname} CHYBA: {e}")
|
||||
|
||||
finally:
|
||||
saved = save_cookies(context)
|
||||
print(f"Uloženo {saved} VZP cookies.")
|
||||
try:
|
||||
context.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
print()
|
||||
if dry_run:
|
||||
print(f"[dry-run] Ke stažení: {downloaded}, přeskočeno: {skipped}")
|
||||
else:
|
||||
print(f"Staženo: {downloaded}, přeskočeno (již existovalo): {skipped}")
|
||||
|
||||
|
||||
def main():
|
||||
dry_run = DRY_RUN or "--dry-run" in sys.argv
|
||||
if dry_run:
|
||||
print("[dry-run] Pouze zobrazuji co by se stáhlo, nic nestahuju.\n")
|
||||
download_ciselniky(dry_run=dry_run)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user