notebookvb
This commit is contained in:
Vladimir Buzalka
@@ -1,7 +1,7 @@
|
||||
[
|
||||
{
|
||||
"name": "SID",
|
||||
"value": "df433a68180840ba413c8f9c68eae034",
|
||||
"value": "9ed44d48a017f8915cdfb566d2e2e952",
|
||||
"domain": ".portal.zpskoda.cz",
|
||||
"path": "/",
|
||||
"expires": -1,
|
||||
@@ -14,7 +14,7 @@
|
||||
"value": "CERT",
|
||||
"domain": ".portal.zpskoda.cz",
|
||||
"path": "/",
|
||||
"expires": 1808227911,
|
||||
"expires": 1808246438,
|
||||
"secure": true,
|
||||
"httpOnly": false,
|
||||
"sameSite": "Lax"
|
||||
|
||||
@@ -0,0 +1,69 @@
|
||||
"""
|
||||
Přihlášení na portál ZPMVČR (eforms.zpmvcr.cz) jménem a heslem.
|
||||
Odlišná platforma od portalzp.cz — přihlášení přes POST formulář s polem PIN a heslo.
|
||||
|
||||
Přihlašovací pole:
|
||||
pin — přihlašovací jméno (zobrazeno jako "PIN" na stránce)
|
||||
pin2 — druhá část PINu (obvykle prázdné)
|
||||
pwd — heslo
|
||||
|
||||
POUŽITÍ:
|
||||
pip install requests
|
||||
python 01_prihlaseni.py
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
import requests
|
||||
|
||||
# ── Přihlašovací údaje ────────────────────────────────────────────────────────
|
||||
PIN = "9023895287"
|
||||
PIN2 = "" # druhé pole PINu — obvykle prázdné
|
||||
HESLO = "Ax162q8+"
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
LOGIN_URL = "https://eforms.zpmvcr.cz/eforms/ekomunikace"
|
||||
COOKIES_FILE = os.path.abspath(os.path.join(os.path.dirname(__file__), "zpmvcr_cookies.json"))
|
||||
|
||||
|
||||
def main() -> None:
|
||||
session = requests.Session()
|
||||
session.headers["User-Agent"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
|
||||
|
||||
# 1. GET → session cookie
|
||||
r = session.get(LOGIN_URL, timeout=15)
|
||||
r.raise_for_status()
|
||||
|
||||
# 2. POST přihlášení
|
||||
r = session.post(LOGIN_URL, data={"pin": PIN, "pin2": PIN2, "pwd": HESLO}, timeout=15)
|
||||
r.raise_for_status()
|
||||
|
||||
# Úspěch = server přesměroval pryč z login stránky na redir nebo smluvni
|
||||
if "pin" in r.text and "Přihlásit" in r.text:
|
||||
print(f"Prihlaseni selhalo — zkontroluj PIN a HESLO. URL: {r.url}")
|
||||
sys.exit(1)
|
||||
|
||||
print(f"Prihlaseni uspesne — {r.url}")
|
||||
|
||||
cookies = [
|
||||
{
|
||||
"name": c.name,
|
||||
"value": c.value,
|
||||
"domain": c.domain if c.domain.startswith(".") else "." + c.domain,
|
||||
"path": c.path or "/",
|
||||
"expires": int(c.expires) if c.expires else -1,
|
||||
"secure": bool(c.secure),
|
||||
"httpOnly": False,
|
||||
"sameSite": "Lax",
|
||||
}
|
||||
for c in session.cookies
|
||||
]
|
||||
with open(COOKIES_FILE, "w", encoding="utf-8") as f:
|
||||
json.dump(cookies, f, indent=2, ensure_ascii=False)
|
||||
print(f"Ulozeno {len(cookies)} cookies -> {COOKIES_FILE}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,244 @@
|
||||
"""
|
||||
Stahování dokumentů ze ZPMVČR portálu (eforms.zpmvcr.cz).
|
||||
|
||||
Stahuje Zúčtovací zprávy a Avíza za celou dostupnou historii.
|
||||
|
||||
Použij po 01_prihlaseni.py (ten uloží zpmvcr_cookies.json).
|
||||
|
||||
JAK TO FUNGUJE:
|
||||
Portál používá POST formuláře. Stažení souboru:
|
||||
POST /eforms/.../zuctovaci_zprava
|
||||
data: bin=1, dl=1, historie=1, doc_id=<id>
|
||||
|
||||
POUŽITÍ:
|
||||
pip install playwright
|
||||
playwright install chrome
|
||||
python 02_stahuj_vse.py
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
from datetime import datetime
|
||||
|
||||
BASE_URL = "https://eforms.zpmvcr.cz"
|
||||
ZPRAVY_URL = f"{BASE_URL}/eforms/smluvni_zdravotnicke_zarizeni/dokumenty_ke_stazeni/zuctovaci_zprava"
|
||||
AVIZA_URL = f"{BASE_URL}/eforms/smluvni_zdravotnicke_zarizeni/dokumenty_ke_stazeni/aviza"
|
||||
|
||||
COOKIES_FILE = os.path.abspath(os.path.join(os.path.dirname(__file__), "zpmvcr_cookies.json"))
|
||||
DOWNLOAD_DIR = os.path.join(os.path.dirname(__file__), "Staženo")
|
||||
|
||||
# Konfigurace sekcí — sloupce se liší podle stránky:
|
||||
# Zúčtovací zprávy: IČ | VarSymb | IntČ | Typ | Velikost | Období | Pobočka | Staženo
|
||||
# Avíza: IČ | Dokument | Typ | Velikost | Období | Pobočka | Staženo
|
||||
SEKCE = [
|
||||
{
|
||||
"name": "Zúčtovací zprávy",
|
||||
"url": ZPRAVY_URL,
|
||||
"need_history": True, # je třeba kliknout "Zobrazit historii"
|
||||
"dl_historie": "1", # hodnota pole 'historie' při stahování souboru
|
||||
"ident_col": 1, # Variabilní symbol
|
||||
"typ_col": 3, # Typ (pdf)
|
||||
"obdobi_col": 5, # Období (01.02.2026)
|
||||
"ident_prefix": "VS-",
|
||||
},
|
||||
{
|
||||
"name": "Avíza",
|
||||
"url": AVIZA_URL,
|
||||
"need_history": False, # Avíza zobrazuje vše rovnou
|
||||
"dl_historie": "0", # Avíza nevyužívá history mode — musí být 0
|
||||
"ident_col": 1, # Název dokumentu
|
||||
"typ_col": 2, # Typ (pdf)
|
||||
"obdobi_col": 4, # Období (jen rok: 2024)
|
||||
"ident_prefix": "",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def parse_period(raw: str) -> str:
|
||||
"""01.02.2026 → 2026-02 | 2024 → 2024"""
|
||||
try:
|
||||
return datetime.strptime(raw.strip()[:10], "%d.%m.%Y").strftime("%Y-%m")
|
||||
except Exception:
|
||||
cleaned = raw.strip()[:7].replace(".", "-")
|
||||
return cleaned if cleaned else "0000"
|
||||
|
||||
|
||||
def safe_filename(name: str) -> str:
|
||||
return re.sub(r'[\\/:*?"<>|]', "_", name).strip()
|
||||
|
||||
|
||||
def make_js_extract(ident_col: int, typ_col: int, obdobi_col: int) -> str:
|
||||
return f"""() => {{
|
||||
const KNOWN_EXTS = new Set(['pdf', 'xml', 'txt', 'zip', 'doc', 'xls', 'csv']);
|
||||
const docs = [];
|
||||
for (const inp of document.querySelectorAll('input[name="doc_id"]')) {{
|
||||
const docId = inp.value;
|
||||
if (!docId) continue;
|
||||
const td = inp.closest('td');
|
||||
const tr = td ? td.closest('tr') : null;
|
||||
let ident = '', typ = 'pdf', obdobi = '';
|
||||
if (tr) {{
|
||||
const tds = Array.from(tr.querySelectorAll('td')).map(t => t.innerText.trim());
|
||||
ident = tds[{ident_col}] || '';
|
||||
const t = (tds[{typ_col}] || '').toLowerCase().trim();
|
||||
typ = KNOWN_EXTS.has(t) ? t : 'pdf';
|
||||
obdobi = tds[{obdobi_col}] || '';
|
||||
}}
|
||||
docs.push({{ docId, ident, typ, obdobi }});
|
||||
}}
|
||||
return docs;
|
||||
}}"""
|
||||
|
||||
|
||||
def click_next_page(page, page_num: int) -> bool:
|
||||
"""Klikne na stránkovací input[name='page'][value='N+1']. Vrátí True pokud existoval."""
|
||||
# Stránkovací prvky jsou input[type=submit] s name="page" a value=číslo stránky
|
||||
# Příklad: <input name="page" type="submit" value="2" title="2. Strana">
|
||||
next_val = str(page_num + 1)
|
||||
btn = page.locator(f"input[name='page'][value='{next_val}']")
|
||||
if btn.count() == 0:
|
||||
return False
|
||||
btn.first.click()
|
||||
page.wait_for_load_state("networkidle", timeout=20_000)
|
||||
return True
|
||||
|
||||
|
||||
def process_sekce(page, context, cfg: dict, already: set) -> tuple:
|
||||
name = cfg["name"]
|
||||
url = cfg["url"]
|
||||
ident_pfx = cfg["ident_prefix"]
|
||||
js_extract = make_js_extract(cfg["ident_col"], cfg["typ_col"], cfg["obdobi_col"])
|
||||
|
||||
downloaded = 0
|
||||
skipped = 0
|
||||
|
||||
print(f"\n=== {name} ===")
|
||||
page.goto(url, wait_until="domcontentloaded", timeout=30_000)
|
||||
page.wait_for_load_state("networkidle", timeout=15_000)
|
||||
|
||||
if cfg["need_history"]:
|
||||
hist = page.get_by_text("Zobrazit historii dokumentů za poslední 3 roky")
|
||||
if hist.count() > 0:
|
||||
hist.first.click()
|
||||
page.wait_for_load_state("networkidle", timeout=20_000)
|
||||
|
||||
page_num = 1
|
||||
seen_ids: set = set()
|
||||
|
||||
while True:
|
||||
print(f" Strana {page_num}...")
|
||||
docs = page.evaluate(js_extract)
|
||||
docs = [d for d in docs if d["docId"] not in seen_ids]
|
||||
|
||||
if not docs:
|
||||
print(f" Strana {page_num} — žádné nové dokumenty, konec sekce.")
|
||||
break
|
||||
|
||||
seen_ids.update(d["docId"] for d in docs)
|
||||
print(f" Nalezeno {len(docs)} dokumentů")
|
||||
|
||||
for doc in docs:
|
||||
period = parse_period(doc["obdobi"])
|
||||
ext = doc["typ"] or "pdf"
|
||||
ident = safe_filename(doc["ident"])
|
||||
label = safe_filename(name)
|
||||
prefix = ident_pfx + ident if ident else f"id-{doc['docId']}"
|
||||
filename = f"{period} {label} {prefix}.{ext}"
|
||||
target = os.path.join(DOWNLOAD_DIR, filename)
|
||||
|
||||
if filename in already or os.path.exists(target):
|
||||
skipped += 1
|
||||
continue
|
||||
|
||||
r = context.request.post(url, form={
|
||||
"bin": "1", "dl": "1", "historie": cfg["dl_historie"],
|
||||
"doc_id": doc["docId"], "save": "Stáhnout",
|
||||
}, timeout=60_000)
|
||||
|
||||
if not r.ok:
|
||||
print(f" HTTP {r.status} doc_id={doc['docId']}")
|
||||
time.sleep(1.0)
|
||||
continue
|
||||
|
||||
# Content-Disposition pro originální název
|
||||
cd = r.headers.get("content-disposition", "")
|
||||
m = re.search(r'filename=["\']?([^"\';\r\n]+)', cd)
|
||||
if m:
|
||||
orig = m.group(1).strip()
|
||||
stem, suf = os.path.splitext(orig)
|
||||
ext2 = suf.lstrip(".").lower() or ext
|
||||
filename = f"{period} {label} {prefix} ({safe_filename(stem)}).{ext2}"
|
||||
target = os.path.join(DOWNLOAD_DIR, filename)
|
||||
|
||||
with open(target, "wb") as f:
|
||||
f.write(r.body())
|
||||
print(f" OK: {filename}")
|
||||
already.add(filename)
|
||||
downloaded += 1
|
||||
time.sleep(1.0)
|
||||
|
||||
# Přejdi na další stránku
|
||||
if not click_next_page(page, page_num):
|
||||
break
|
||||
page_num += 1
|
||||
|
||||
return downloaded, skipped
|
||||
|
||||
|
||||
def main() -> None:
|
||||
try:
|
||||
from playwright.sync_api import sync_playwright
|
||||
except ImportError:
|
||||
print("Chybi playwright: pip install playwright && playwright install chrome")
|
||||
sys.exit(1)
|
||||
|
||||
os.makedirs(DOWNLOAD_DIR, exist_ok=True)
|
||||
|
||||
if not os.path.exists(COOKIES_FILE):
|
||||
print(f"Soubor {COOKIES_FILE} nenalezen — spust 01_prihlaseni.py")
|
||||
sys.exit(1)
|
||||
|
||||
with open(COOKIES_FILE, encoding="utf-8") as f:
|
||||
cookies = json.load(f)
|
||||
|
||||
with sync_playwright() as p:
|
||||
context = p.chromium.launch_persistent_context(
|
||||
user_data_dir=os.path.join(os.path.dirname(__file__), "chrome_profile"),
|
||||
channel="chrome",
|
||||
headless=False,
|
||||
slow_mo=100,
|
||||
ignore_https_errors=True,
|
||||
)
|
||||
try:
|
||||
context.add_cookies(cookies)
|
||||
page = context.new_page()
|
||||
|
||||
# Ověř přihlášení
|
||||
page.goto(ZPRAVY_URL, wait_until="domcontentloaded", timeout=30_000)
|
||||
page.wait_for_load_state("networkidle", timeout=15_000)
|
||||
if page.locator("input[name='pin']").count() > 0:
|
||||
print("Cookies expirovala — spust 01_prihlaseni.py")
|
||||
return
|
||||
print("Prihlaseni OK\n")
|
||||
|
||||
already = set(os.listdir(DOWNLOAD_DIR))
|
||||
print(f"V archivu: {len(already)} souboru.")
|
||||
|
||||
total_dl = total_skip = 0
|
||||
for cfg in SEKCE:
|
||||
dl, sk = process_sekce(page, context, cfg, already)
|
||||
print(f" {cfg['name']}: stazeno {dl}, preskoceno {sk}")
|
||||
total_dl += dl
|
||||
total_skip += sk
|
||||
|
||||
print(f"\nHotovo. Celkem stazeno: {total_dl}, preskoceno: {total_skip}")
|
||||
|
||||
finally:
|
||||
context.close()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,12 @@
|
||||
[
|
||||
{
|
||||
"name": "JSESSIONID",
|
||||
"value": "36137BBDC47B5AA6EBACEA28257BB821",
|
||||
"domain": ".eforms.zpmvcr.cz",
|
||||
"path": "/eforms",
|
||||
"expires": -1,
|
||||
"secure": false,
|
||||
"httpOnly": false,
|
||||
"sameSite": "Lax"
|
||||
}
|
||||
]
|
||||
Reference in New Issue
Block a user