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>

.gitignore

@@ -0,0 +1,8 @@
+xls_reports/
+xls_ip_destruction/
+accountability_combined.xlsx
+accountability_formatted.xlsx
+__pycache__/
+*.pyc
+.idea/
+.claude/

create_accountability_report.py

@@ -0,0 +1,172 @@
+import pandas as pd
+from pathlib import Path
+from openpyxl import load_workbook
+from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
+from openpyxl.utils import get_column_letter
+
+INVENTORY_DIR  = Path("xls_reports")
+DESTRUCTION_DIR = Path("xls_ip_destruction")
+OUTPUT_FILE    = "accountability_combined.xlsx"
+SHEET_NAME     = "CountryMedicationOverview"
+
+COLUMN_RENAMES = {
+    "Site":                                                  "Site",
+    "Medication ID":                                         "Med ID",
+    "Packaged Lot number":                                   "Lot No.",
+    "Original Expiration Date when Packaged Lot was Added":  "Orig Exp Date",
+    "Expiration date":                                       "Exp Date",
+    "Received Date":                                         "Rcv Date",
+    "Shipment Receipt User":                                 "Rcpt User",
+    "Subject Identifier":                                    "Subject ID",
+    "Quantity Assigned":                                     "Qty Asgn",
+    "IRT Transaction":                                       "IRT Tx",
+    "Date Assigned":                                         "Date Asgn",
+    "Assignment User":                                       "Asgn User",
+    "Dispensation Status":                                   "Disp Status",
+    "Dispensing Date":                                       "Disp Date",
+    "Quantity Dispensed":                                    "Qty Disp",
+    "Dispensing User":                                       "Disp User",
+    "Quantity Returned":                                     "Qty Ret",
+    "Date Returned":                                         "Date Ret",
+    "Return User":                                           "Ret User",
+    "DestroyedOn":                                           "Destroyed",
+    "Basket number":                                         "Basket No.",
+}
+
+DATE_COLUMNS = {
+    "Orig Exp Date", "Exp Date", "Rcv Date",
+    "Date Asgn", "Disp Date", "Date Ret", "Destroyed",
+}
+
+COLUMN_WIDTHS = {
+    "Site":          14,
+    "Med ID":        10,
+    "Lot No.":       12,
+    "Orig Exp Date": 16,
+    "Exp Date":      14,
+    "Rcv Date":      14,
+    "Rcpt User":     22,
+    "Subject ID":    14,
+    "Qty Asgn":       9,
+    "IRT Tx":         8,
+    "Date Asgn":     14,
+    "Asgn User":     20,
+    "Disp Status":   16,
+    "Disp Date":     14,
+    "Qty Disp":       9,
+    "Disp User":     20,
+    "Qty Ret":       10,
+    "Date Ret":      14,
+    "Ret User":      18,
+    "Destroyed":     14,
+    "Basket No.":    12,
+}
+
+
+def read_inventory(path):
+    df = pd.read_excel(path, header=None)
+    header_row = df[df[0] == "Medication ID"].index[0]
+    data = pd.read_excel(path, header=header_row)
+    meta = {}
+    for i in range(header_row):
+        val = str(df.iloc[i, 0]) if pd.notna(df.iloc[i, 0]) else ""
+        if val.startswith("Site:"):
+            meta["site"] = val.replace("Site:", "").strip()
+    return data, meta
+
+
+def read_destruction_lookup():
+    lookup = {}
+    for path in DESTRUCTION_DIR.glob("*.xlsx"):
+        df = pd.read_excel(path, header=None)
+        basket_id = None
+        destroyed_on = None
+        for i in range(15):
+            val = str(df.iloc[i, 0]) if pd.notna(df.iloc[i, 0]) else ""
+            if val.startswith("Basket ID:"):
+                basket_id = val.replace("Basket ID:", "").strip()
+            if val.startswith("Drug Destruction Created Date:"):
+                destroyed_on = val.replace("Drug Destruction Created Date:", "").strip()
+        header_row = df[df[0] == "Medication ID Description"].index[0]
+        data = pd.read_excel(path, header=header_row)
+        for med_id in data["Medication ID"].dropna():
+            lookup[int(med_id)] = (basket_id, destroyed_on)
+    return lookup
+
+
+def main():
+    lookup = read_destruction_lookup()
+    print(f"Loaded {len(lookup)} kits from destruction reports")
+
+    all_rows = []
+    for path in sorted(INVENTORY_DIR.glob("onsite_inventory_detail_*.xlsx")):
+        df, meta = read_inventory(path)
+        df["DestroyedOn"] = df["Medication ID"].apply(
+            lambda x: lookup.get(int(x), (None, None))[1] if pd.notna(x) else None
+        )
+        df["Basket number"] = df["Medication ID"].apply(
+            lambda x: lookup.get(int(x), (None, None))[0] if pd.notna(x) else None
+        )
+        df.insert(0, "Site", meta.get("site", path.stem))
+        all_rows.append(df)
+        print(f"  {path.name}: {len(df)} kits")
+
+    combined = pd.concat(all_rows, ignore_index=True)
+
+    # Rename columns
+    combined.rename(columns=COLUMN_RENAMES, inplace=True)
+
+    # Convert date columns
+    for col in DATE_COLUMNS:
+        if col in combined.columns:
+            combined[col] = pd.to_datetime(combined[col], dayfirst=True, errors="coerce")
+
+    # Sort
+    combined.sort_values(["Site", "Rcv Date", "Med ID"], inplace=True, ignore_index=True)
+
+    combined.to_excel(OUTPUT_FILE, index=False, sheet_name=SHEET_NAME)
+
+    # ── Formatting ────────────────────────────────────────────────────────────
+    wb = load_workbook(OUTPUT_FILE)
+    ws = wb[SHEET_NAME]
+
+    header_fill = PatternFill("solid", start_color="1F4E79")
+    header_font = Font(bold=True, color="FFFFFF", name="Arial", size=10)
+    new_col_fill = PatternFill("solid", start_color="E2EFDA")
+    row_font     = Font(name="Arial", size=10)
+
+    thin   = Side(style="thin", color="000000")
+    border = Border(left=thin, right=thin, top=thin, bottom=thin)
+
+    headers  = [cell.value for cell in ws[1]]
+    new_cols = {"Destroyed", "Basket No."}
+
+    for cell in ws[1]:
+        cell.fill      = header_fill
+        cell.font      = header_font
+        cell.alignment = Alignment(horizontal="center", vertical="center", wrap_text=False)
+        cell.border    = border
+
+    for row in ws.iter_rows(min_row=2, max_row=ws.max_row):
+        for cell in row:
+            col_name = headers[cell.column - 1] if cell.column <= len(headers) else None
+            cell.font      = row_font
+            cell.border    = border
+            cell.alignment = Alignment(horizontal="center")
+            if col_name in DATE_COLUMNS:
+                cell.number_format = "DD-MMM-YYYY"
+            if col_name in new_cols:
+                cell.fill = new_col_fill
+
+    for cell in ws[1]:
+        width = COLUMN_WIDTHS.get(cell.value, 14)
+        ws.column_dimensions[get_column_letter(cell.column)].width = width
+
+    ws.auto_filter.ref = ws.dimensions
+    ws.freeze_panes    = "A2"
+
+    wb.save(OUTPUT_FILE)
+    print(f"\nSaved: {OUTPUT_FILE} ({len(combined)} rows, sheet '{SHEET_NAME}')")
+
+
+main()

download_ip_destruction.py

@@ -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()

download_reports.py

@@ -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()

list_reports.py

@@ -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()

reports.json

@@ -0,0 +1,23 @@
+[
+  {"name": "Drug Accountability Form - Multiple Subjects", "href": "/report/drug_accountability_form_multiple_subjects"},
+  {"name": "Drug Accountability Form - Single Subject", "href": "/report/drug_accountability_form_single_subject"},
+  {"name": "Janssen Pharmaceuticals IP Destruction Form", "href": "/report/ip_destruction_form"},
+  {"name": "On-Site Drug Inventory and Accountability Details Form", "href": "/report/onsite_inventory_detail"},
+  {"name": "On-Site Drug Inventory Form", "href": "/report/onsite_drug_inventory_form"},
+  {"name": "Location Summary Report", "href": "/report/country_summary_report"},
+  {"name": "Site Detail Report", "href": "/report/site_detail_report"},
+  {"name": "Study Sites Report", "href": "/report/study_sites_report"},
+  {"name": "Site Inventory Detail Report", "href": "/report/site_inventory_detail"},
+  {"name": "Site Inventory Summary Report", "href": "/report/site_inventory_summary"},
+  {"name": "Subject Data Changes Report", "href": "/report/patient_data_changes_report"},
+  {"name": "Subject Detail Report", "href": "/report/patient_detail_report"},
+  {"name": "Subject Summary Report", "href": "/report/patient_summary_report"},
+  {"name": "Subject Visit Summary Report", "href": "/report/patient_visit_summary"},
+  {"name": "Shipment Details Report", "href": "/report/shipment_details_report"},
+  {"name": "Shipments Report", "href": "/report/shipments_report"},
+  {"name": "Cohort History Report", "href": "/report/cohort_history_report"},
+  {"name": "Cohort Summary Report", "href": "/report/cohort_summary_report"},
+  {"name": "Site Activations Report", "href": "/report/site_activation_pivot"},
+  {"name": "User Login History", "href": "/report/user_logins"},
+  {"name": "Users List", "href": "/report/users"}
+]