88 lines
3.3 KiB
Python
88 lines
3.3 KiB
Python
# Název: download_equeries_report_v1.2.py
|
|
# Verze: 1.2
|
|
# Datum: 2026-06-09
|
|
# Popis: Stahuje eQuery reporty ze Covance/Labcorp XSP pro obě studie (36940 + 35472).
|
|
# Pro každou studii stahuje 1 soubor: všechny eQueries.
|
|
# Výstup: timestampované CSV soubory do adresáře Source/.
|
|
# Prohlížeč spouštěn maximalizovaný.
|
|
|
|
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/"
|
|
|
|
# Seznam studií, které se mají stáhnout. Každá má vlastní sady sites.
|
|
STUDIES = [
|
|
{
|
|
"study": "36940",
|
|
"sites": "%5B%22930551%22,%22930556%22,%22930525%22,%22930549%22,%22930543%22,%22930547%22,%22930555%22,%22930557%22,%22930539%22,%22930536%22,%22930553%22,%22930531%22%5D",
|
|
},
|
|
{
|
|
"study": "35472",
|
|
"sites": "%5B%22898744%22,%22898739%22,%22898733%22,%22898745%22,%22898727%22%5D",
|
|
},
|
|
]
|
|
|
|
OUT_DIR = r"U:\PythonProject\Janssen\Covance\Source"
|
|
PROFILE_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "browser_profile")
|
|
|
|
|
|
def login(page):
|
|
page.goto(LOGIN_URL)
|
|
page.wait_for_load_state("networkidle")
|
|
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")
|
|
page.get_by_label("Password").fill(PASSWORD)
|
|
page.get_by_role("button", name="Verify").click()
|
|
page.wait_for_url(lambda url: "code=" not in url, timeout=60000)
|
|
page.wait_for_load_state("networkidle", timeout=60000)
|
|
page.wait_for_timeout(2000)
|
|
print(f"Prihlaseni OK: {page.url}")
|
|
|
|
|
|
def export_csv(page, url, filename):
|
|
page.goto(url)
|
|
page.wait_for_load_state("networkidle", timeout=60000)
|
|
print(f"Report nacteny: {page.url}")
|
|
page.locator("ag-export").get_by_role("button", name="more_horiz").click()
|
|
with page.expect_download(timeout=60000) as dl:
|
|
page.get_by_text("Export to CSV").click()
|
|
dest = os.path.join(OUT_DIR, filename)
|
|
dl.value.save_as(dest)
|
|
print(f"Stazeno: {dest}")
|
|
|
|
|
|
def download(page):
|
|
timestamp = datetime.now().strftime("%Y-%m-%d_%H%M%S")
|
|
for s in STUDIES:
|
|
study = s["study"]
|
|
sites = s["sites"]
|
|
base_url = f"https://xsp.labcorp.com/sponsor/study/{study}/activity-reports/documents/equery?site={sites}"
|
|
print(f"=== Studie {study} ===")
|
|
export_csv(page, base_url,
|
|
f"{timestamp} sponsor-study-{study}-activity-reports-documents-equery.csv")
|
|
|
|
|
|
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"],
|
|
no_viewport=True,
|
|
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,
|
|
)
|
|
context.add_init_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
|
|
page = context.new_page()
|
|
login(page)
|
|
download(page)
|
|
context.close()
|