Initial commit — clean history (removed large test files, browser profiles, Medidata/Clario downloads)

2026-06-01 15:36:31 +02:00
commit bb604e593e
1304 changed files with 116480 additions and 0 deletions
@@ -0,0 +1,143 @@
+# =============================================================================
+# Název:   download_samples_report_v1.1.py
+# Verze:   1.1
+# Datum:   2026-05-29
+# Popis:   Automatické stažení CSV reportu All Samples ze xsp.labcorp.com pro
+#          studie 77242113UCO3001 (study 36940) a 42847922MDD3003 (study 35472).
+#          Aplikuje country filtr CZ, date range od FROM_DATE, čeká na zmizení
+#          "Fetching Data" před exportem. Výstup do Source/ každé studie.
+# =============================================================================
+from playwright.sync_api import sync_playwright
+from datetime import datetime
+import os
+
+EMAIL       = "vbuzalka@its.jnj.com"
+PASSWORD    = "%zT3Wqfc9)cWua5"
+LOGIN_URL   = "https://xsp.covance.com/"
+HOME_URL    = "https://xsp.labcorp.com/sampletracking/home"
+FROM_DATE   = "01-Jan-2025"
+PROFILE_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "browser_profile")
+
+# (protocol, covance study ID, výstupní adresář)
+STUDIES = [
+    ("77242113UCO3001", "36940", r"U:\PythonProject\Janssen\Covance_UCO3001\Source"),
+    ("42847922MDD3003", "35472", r"U:\PythonProject\Janssen\Covance_MDD3003\Source"),
+]
+
+TILE_LABEL  = "All Samples"
+TILE_SUFFIX = "allSamples"
+
+
+def login(page):
+    page.goto(LOGIN_URL)
+    page.wait_for_load_state("networkidle", timeout=120000)
+    if not page.get_by_label("Email").is_visible():
+        print(f"Session aktivni, prihlasen: {page.url}")
+        return
+    page.get_by_label("Email").fill(EMAIL)
+    page.get_by_role("button", name="Next").click()
+    page.wait_for_load_state("networkidle", timeout=120000)
+    page.get_by_label("Password").fill(PASSWORD)
+    page.get_by_role("button", name="Verify").click()
+    page.wait_for_timeout(15000)
+    page.wait_for_load_state("networkidle", timeout=120000)
+    print(f"Prihlaseni OK: {page.url}")
+
+
+def select_protocol(page, protocol):
+    page.goto(HOME_URL)
+    page.wait_for_load_state("networkidle", timeout=120000)
+    page.wait_for_timeout(3000)
+    page.locator("span").filter(has_text=protocol).first.click()
+    page.wait_for_load_state("networkidle", timeout=120000)
+    page.wait_for_timeout(3000)
+    print(f"Protokol vybran: {protocol} ({page.url})")
+
+
+def apply_country_filter(page):
+    page.get_by_text("keyboard_arrow_down").nth(3).click()
+    page.wait_for_timeout(2000)
+    page.get_by_role("checkbox", name="Czech Republic").check()
+    page.wait_for_timeout(2000)
+    page.mouse.move(0, -50, steps=5)
+    page.wait_for_load_state("networkidle", timeout=120000)
+    page.wait_for_timeout(3000)
+    print("Country filter CZ aplikovan.")
+
+
+def export_tile(page, tile_label, file_suffix, timestamp, study_id, out_dir):
+    # Klikni na View Samples u správné dlaždice
+    page.locator("div.study-group-card").filter(
+        has=page.locator("span.label", has_text=tile_label)
+    ).locator("button.view-sample").click()
+    page.wait_for_load_state("networkidle", timeout=120000)
+    page.wait_for_timeout(3000)
+    print(f"  Otevreno: {tile_label} ({page.url})")
+
+    # Date picker
+    page.get_by_role("button", name="DD/MM - DD/MM").click()
+    page.wait_for_timeout(2000)
+    page.get_by_role("textbox", name="Date input field").first.click()
+    page.get_by_role("textbox", name="Date input field").first.press("End")
+    page.get_by_role("textbox", name="Date input field").first.press("Shift+Home")
+    page.get_by_role("textbox", name="Date input field").first.fill(FROM_DATE)
+    page.wait_for_timeout(500)
+    page.get_by_role("button", name="Apply").click()
+    page.wait_for_load_state("networkidle", timeout=120000)
+    page.wait_for_timeout(3000)
+
+    # Čekej až zmizí "Fetching Data": po filtru 5s, pak opakuj kontrolu každých 5s
+    page.wait_for_timeout(5000)
+    for _ in range(24):  # max 2 minuty
+        if not page.get_by_text("Fetching Data").is_visible():
+            break
+        print("  Fetching Data... cekam 5s")
+        page.wait_for_timeout(5000)
+    page.wait_for_timeout(5000)  # extra buffer po zmizení
+
+    if page.locator("div.table-row.no-data").is_visible():
+        print(f"  Record Count: 0 — preskakuji.")
+        return
+
+    count_str = page.locator("div.grid-count span").first.inner_text().strip().replace(",", "")
+    count = int(count_str) if count_str.isdigit() else -1
+    print(f"  Record Count: {count}")
+    with page.expect_download(timeout=120000) as dl:
+        page.get_by_role("button", name="Export arrow_drop_down").click()
+        page.wait_for_timeout(1000)
+        page.get_by_text("Export As CSV").click()
+    dest = os.path.join(out_dir, f"{timestamp} sponsor-study-{study_id}-samples-{file_suffix}.csv")
+    dl.value.save_as(dest)
+    print(f"  Stazeno: {dest}")
+
+
+def download(page):
+    timestamp = datetime.now().strftime("%Y-%m-%d_%H%M%S")
+    for protocol, study_id, out_dir in STUDIES:
+        print(f"\n--- Studie: {protocol} ---")
+        select_protocol(page, protocol)
+        apply_country_filter(page)
+        export_tile(page, TILE_LABEL, TILE_SUFFIX, timestamp, study_id, out_dir)
+    print("\nHotovo.")
+
+
+if __name__ == "__main__":
+    with sync_playwright() as p:
+        context = p.chromium.launch_persistent_context(
+            user_data_dir=PROFILE_DIR,
+            headless=False,
+            args=[
+                "--disable-blink-features=AutomationControlled",
+                "--start-maximized",
+                "--disable-restore-session-state",
+                "--disable-session-crashed-bubble",
+            ],
+            user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36",
+            accept_downloads=True,
+            no_viewport=True,
+        )
+        context.add_init_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
+        page = context.new_page()
+        login(page)
+        download(page)
+        context.close()