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 +1,74 @@
+from playwright.sync_api import sync_playwright
+import json
+
+# ── CONFIG ──────────────────────────────────────────────────────────────────
+BASE_URL = "https://janssen.4gclinical.com"
+STUDY    = "42847922MDD3003"
+
+EMAIL    = "vbuzalka@its.jnj.com"
+PASSWORD = "Vlado123++-"   # doplň heslo
+# ────────────────────────────────────────────────────────────────────────────
+
+
+def list_reports():
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=False)
+        page = browser.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 — klikni na dropdown, vyber studii, klikni SELECT
+        page.get_by_label("Study *").click()
+        page.get_by_role("option", name=STUDY).click()
+        page.get_by_role("button", name="SELECT").click()
+        page.wait_for_load_state("networkidle")
+
+        # Přejdi na seznam reportů
+        page.goto(f"{BASE_URL}/reports")
+        page.wait_for_load_state("networkidle")
+        page.wait_for_selector('[role="gridcell"] a', timeout=15000)
+
+        # Získej názvy reportů
+        names = page.evaluate("""
+            () => Array.from(document.querySelectorAll('[role="gridcell"] a'))
+                .map(a => a.innerText.trim())
+                .filter(n => n)
+        """)
+        print(f"\nNalezeno {len(names)} reportů, zjišťuji URL...\n")
+
+        # Pro každý report klikni, zaznamenej URL a vrať se zpět
+        reports = []
+        for name in names:
+            with page.expect_navigation(timeout=15000):
+                page.locator('[role="gridcell"] a').filter(has_text=name).click()
+            page.wait_for_load_state("networkidle")
+            page.wait_for_timeout(2000)
+            path = page.url.replace(BASE_URL, "")
+            reports.append({"name": name, "href": path})
+            print(f"  {name:50s}  {path}")
+            # Průběžné uložení po každém reportu
+            with open("reports.json", "w", encoding="utf-8") as f:
+                json.dump(reports, f, ensure_ascii=False, indent=2)
+            if page.url != f"{BASE_URL}/reports":
+                page.goto(f"{BASE_URL}/reports")
+            page.wait_for_load_state("networkidle")
+            page.wait_for_timeout(2000)
+            page.wait_for_selector('[role="gridcell"] a', timeout=30000)
+
+        browser.close()
+
+        with open("reports.json", "w", encoding="utf-8") as f:
+            json.dump(reports, f, ensure_ascii=False, indent=2)
+        print(f"\nUloženo do reports.json")
+
+        return reports
+
+
+list_reports()