z230

2026-06-10 09:25:49 +02:00
parent bc9b874f3b
commit 30f045e350
26 changed files with 1 additions and 1 deletions
@@ -0,0 +1,90 @@
+"""
+Stažení reportů z IWRS portálu — vše do jednoho adresáře `Incoming/`.
+
+  1. Subject Summary Report (per studie)
+  2. Subject Detail Reports + notifikace (per subjekt)
+
+Import se spouští samostatně skriptem `import_all.py`.
+"""
+
+import os
+import datetime
+
+from playwright.sync_api import sync_playwright
+
+import download_subject_details as dsd
+
+# ── CONFIG ───────────────────────────────────────────────────────────────────
+BASE_URL = "https://janssen.4gclinical.com"
+EMAIL    = "vbuzalka@its.jnj.com"
+PASSWORD = "Vlado123++-+"
+
+STUDIES = ["77242113UCO3001", "42847922MDD3003"]
+
+BASE_DIR     = os.path.dirname(os.path.abspath(__file__))
+INCOMING_DIR = os.path.join(BASE_DIR, "Incoming")
+
+
+def unique_path(directory, stem, ext=".xlsx"):
+    path = os.path.join(directory, f"{stem}{ext}")
+    if not os.path.exists(path):
+        return path
+    time_tag = datetime.datetime.now().strftime("%H%M")
+    return os.path.join(directory, f"{stem} {time_tag}{ext}")
+
+
+def login(page, study):
+    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")
+    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")
+
+
+def download_summary(page, study, today):
+    print(f"  [{study}] Stahuji Subject Summary Report...")
+    page.goto(f"{BASE_URL}/report/patient_summary_report")
+    page.wait_for_load_state("networkidle", timeout=120000)
+    filename = unique_path(INCOMING_DIR, f"{today} {study} Subject Summary Report")
+    with page.expect_download(timeout=120000) as dl:
+        page.get_by_role("button", name="Download XLS").click()
+    dl.value.save_as(filename)
+    print(f"  [{study}] Summary OK -> {os.path.basename(filename)}")
+    return filename
+
+
+def main():
+    today = datetime.date.today().strftime("%Y-%m-%d")
+    os.makedirs(INCOMING_DIR, exist_ok=True)
+
+    with sync_playwright() as p:
+        for study in STUDIES:
+            print("\n" + "=" * 60)
+            print(f"[{study}] Stažení reportů")
+            print("=" * 60)
+            browser = p.chromium.launch(headless=False)
+            context = browser.new_context(accept_downloads=True)
+            page = context.new_page()
+            try:
+                login(page, study)
+                download_summary(page, study, today)
+                # detail XLSX + notifikace přímo do Incoming/
+                dsd.run(page, study, out_dir=INCOMING_DIR, subjects_source_dir=INCOMING_DIR)
+            except Exception as e:
+                print(f"  [{study}] CHYBA: {e}")
+            finally:
+                browser.close()
+
+    print("\n" + "=" * 60)
+    print(f"Stahování hotovo. Soubory v: {INCOMING_DIR}")
+    print("Pro import spusť: python import_all.py")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,107 @@
+"""
+Import všech čekajících reportů z `Incoming/` do MongoDB.
+
+Pořadí zpracování per typ + studie: nejstarší soubor podle mtime první
+(důležité pro chronologickou správnost snapshotů).
+
+Po úspěšném importu se soubor přesune do `Incoming/Zpracováno/`.
+Při chybě zůstane soubor v `Incoming/`.
+"""
+
+import os
+import sys
+import glob
+import shutil
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from common.mongo_writer import ensure_indexes
+
+import import_to_mongo
+import import_notifications_to_mongo
+
+BASE_DIR     = os.path.dirname(os.path.abspath(__file__))
+INCOMING_DIR = os.path.join(BASE_DIR, "Incoming")
+DONE_DIR     = os.path.join(INCOMING_DIR, "Zpracováno")
+
+STUDIES = ["77242113UCO3001", "42847922MDD3003"]
+
+
+def _move_done(path):
+    os.makedirs(DONE_DIR, exist_ok=True)
+    dst = os.path.join(DONE_DIR, os.path.basename(path))
+    # kolize → přepiš (Mongo už má aktuální data, soubor je jen archiv)
+    if os.path.exists(dst):
+        os.remove(dst)
+    shutil.move(path, dst)
+
+
+def _sorted_by_mtime(paths):
+    """Nejstarší první."""
+    return sorted(
+        (p for p in paths if not os.path.basename(p).startswith("~$")),
+        key=os.path.getmtime,
+    )
+
+
+def import_summaries(study):
+    pattern = os.path.join(INCOMING_DIR, f"* {study} Subject Summary Report*.xlsx")
+    files = _sorted_by_mtime(glob.glob(pattern))
+    if not files:
+        print(f"  [{study}] summary: nic ke zpracování")
+        return
+    print(f"  [{study}] summary: {len(files)} soubor(ů) (oldest first)")
+    for path in files:
+        try:
+            import_to_mongo.import_subject_summary(study, path)
+            _move_done(path)
+        except Exception as e:
+            print(f"  [{study}] CHYBA summary {os.path.basename(path)}: {e}")
+
+
+def import_details(study):
+    pattern = os.path.join(INCOMING_DIR, f"* {study} * Subject Detail.xlsx")
+    files = _sorted_by_mtime(glob.glob(pattern))
+    if not files:
+        print(f"  [{study}] detail: nic ke zpracování")
+        return
+    print(f"  [{study}] detail: {len(files)} soubor(ů) (oldest first)")
+    for path in files:
+        parsed = import_to_mongo.parse_detail_filename(path)
+        if not parsed:
+            print(f"  [{study}] PŘESKAKUJI (nelze parsovat název): {os.path.basename(path)}")
+            continue
+        _, parsed_study, subject = parsed
+        if parsed_study != study:
+            continue  # patří jiné studii
+        try:
+            import_to_mongo.import_visits_single_file(study, subject, path)
+            _move_done(path)
+        except Exception as e:
+            print(f"  [{study}] CHYBA detail {os.path.basename(path)}: {e}")
+
+
+def main():
+    if not os.path.isdir(INCOMING_DIR):
+        print(f"Adresář neexistuje: {INCOMING_DIR}")
+        return
+    ensure_indexes()
+
+    print("=" * 60)
+    print("Import Subject Summary + Visits")
+    print("=" * 60)
+    for study in STUDIES:
+        import_summaries(study)
+        import_details(study)
+
+    print("\n" + "=" * 60)
+    print("Import notifikací")
+    print("=" * 60)
+    import_notifications_to_mongo.import_from_dir(INCOMING_DIR, DONE_DIR, STUDIES)
+
+    print("\n" + "=" * 60)
+    print(f"Hotovo. Zpracované soubory: {DONE_DIR}")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()