Initial commit: Janssen 4G Clinical report automation

- download_reports.py: Playwright script for site inventory XLS downloads
- download_ip_destruction.py: Playwright script for IP destruction basket downloads
- create_accountability_report.py: combines both sources into formatted accountability Excel
- list_reports.py: discovers available reports on portal
- reports.json: 21 available report URLs
- .gitignore: excludes downloaded XLS files and output Excel

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-08 14:57:17 +02:00
commit aa194daf91
6 changed files with 434 additions and 0 deletions
+81
View File
@@ -0,0 +1,81 @@
from playwright.sync_api import sync_playwright
import os
# ── CONFIG ──────────────────────────────────────────────────────────────────
BASE_URL = "https://janssen.4gclinical.com"
EMAIL = "vbuzalka@its.jnj.com"
PASSWORD = "Vlado123++-"
OUTPUT_DIR = "xls_ip_destruction"
# ────────────────────────────────────────────────────────────────────────────
os.makedirs(OUTPUT_DIR, exist_ok=True)
def download_ip_destruction():
with sync_playwright() as p:
browser = p.chromium.launch(headless=False)
context = browser.new_context(accept_downloads=True)
page = context.new_page()
# Přihlášení
page.goto(BASE_URL)
page.wait_for_load_state("networkidle")
page.get_by_label("Email *").fill(EMAIL)
page.get_by_label("Password *").fill(PASSWORD)
page.locator('#login__submit').click()
page.wait_for_load_state("networkidle")
# Výběr studie
page.get_by_label("Study *").click()
page.get_by_role("option", name="42847922MDD3003").click()
page.get_by_role("button", name="SELECT").click()
page.wait_for_load_state("networkidle")
# Naviguj na report
page.goto(f"{BASE_URL}/report/ip_destruction_form")
page.wait_for_load_state("networkidle", timeout=15000)
# Přečti dostupné košíky
page.locator('input[placeholder="search"], input[type="text"]').first.click()
page.wait_for_timeout(1000)
baskets = [b.strip() for b in page.locator('mat-option').all_inner_texts()]
print(f"Nalezeno {len(baskets)} košíků: {baskets}")
page.keyboard.press("Escape")
page.wait_for_timeout(500)
for basket in baskets:
filename = os.path.join(OUTPUT_DIR, f"ip_destruction_basket_{basket}.xlsx")
if os.path.exists(filename):
print(f"[{basket}] Přeskakuji — soubor již existuje.")
continue
print(f"[{basket}] Stahuji...")
# Otevři dropdown a vyber košík přes dispatch_event
input_field = page.locator('input[placeholder="search"], input[type="text"]').first
input_field.click()
input_field.fill(basket)
page.wait_for_timeout(500)
page.locator('mat-option').first.dispatch_event('click')
# Počkej na načtení dat
page.wait_for_load_state("networkidle", timeout=30000)
# Stáhni XLS
with page.expect_download(timeout=30000) as dl:
page.get_by_role("button", name="Download XLS").click()
download = dl.value
download.save_as(filename)
print(f"[{basket}] Uloženo → {filename}")
# Reset pro další košík
page.get_by_role("button", name="Clear").click()
page.wait_for_load_state("networkidle", timeout=15000)
browser.close()
print("\nHotovo!")
download_ip_destruction()