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>
2026-04-08 14:57:17 +02:00
commit aa194daf91
6 changed files with 434 additions and 0 deletions
@@ -0,0 +1,76 @@
+from playwright.sync_api import sync_playwright
+import os
+
+# ── CONFIG ──────────────────────────────────────────────────────────────────
+BASE_URL = "https://janssen.4gclinical.com"
+
+EMAIL    = "vbuzalka@its.jnj.com"
+PASSWORD = "Vlado123++-"
+
+SITES = [
+    "S10-CZ10002",
+    "S10-CZ10004",
+    "S10-CZ10005",
+    "S10-CZ10008",
+    "S10-CZ10011",
+    "S10-CZ10012",
+]
+
+OUTPUT_DIR = "xls_reports"
+# ────────────────────────────────────────────────────────────────────────────
+
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+
+def download_reports():
+    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 stránku
+        page.goto(f"{BASE_URL}/report/onsite_inventory_detail")
+        page.wait_for_load_state("networkidle", timeout=15000)
+
+        for site_id in SITES:
+            print(f"[{site_id}] Stahuji...")
+
+            # Otevři dropdown a vyber site
+            page.locator('input[placeholder="search"], input[type="text"]').first.click()
+            page.get_by_role("option", name=site_id).click()
+
+            # Počkej na dokončení načítání dat (síť se uklidní)
+            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
+            filename = os.path.join(OUTPUT_DIR, f"onsite_inventory_detail_{site_id}.xlsx")
+            download.save_as(filename)
+            print(f"[{site_id}] Uloženo → {filename}")
+
+            # Zruš výběr site pro další iteraci
+            page.get_by_role("button", name="Clear").click()
+            page.wait_for_load_state("networkidle", timeout=15000)
+
+        browser.close()
+        print("\nHotovo! Všechny reporty staženy.")
+
+
+download_reports()