This commit is contained in:
2026-06-03 07:10:15 +02:00
parent 9ed9f97140
commit 681095d557
60 changed files with 215 additions and 2161 deletions
+11 -365
View File
@@ -4,7 +4,7 @@ Kompletní pipeline pro Drugs:
2. IP destruction (per košík, přeskočí již existující soubory)
3. Shipments report (jeden soubor na studii, přepisuje)
4. Shipment details (per zásilka CZ, vždy přepisuje)
5. Import do MySQL
5. Import do MongoDB (studie.iwrs_shipments / iwrs_shipment_items / iwrs_inventory / iwrs_destruction)
Spusť tento skript — zpracuje obě studie automaticky.
"""
@@ -14,12 +14,11 @@ import glob
import re
import datetime
import numpy as np
import sys
import pandas as pd
from playwright.sync_api import sync_playwright
import mysql.connector
import db_config
import import_to_mongo as drugs_mongo
BASE_URL = "https://janssen.4gclinical.com"
EMAIL = "vbuzalka@its.jnj.com"
@@ -42,357 +41,6 @@ SITES = {
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
# ── type converters ──────────────────────────────────────────────────────────
def _py(val):
if isinstance(val, np.generic):
return val.item()
return val
def to_date(val):
val = _py(val)
if val is None:
return None
if isinstance(val, float) and (val != val):
return None
try:
if pd.isna(val):
return None
except (TypeError, ValueError):
pass
if isinstance(val, pd.Timestamp):
return None if pd.isna(val) else val.date()
if isinstance(val, datetime.datetime):
return val.date()
if isinstance(val, datetime.date):
return val
s = str(val).strip()
if not s or s.lower() in ("nat", "nan", "none", ""):
return None
for fmt in ("%Y-%m-%d", "%d-%b-%Y", "%d-%m-%Y", "%Y-%m-%d %H:%M:%S"):
try:
return datetime.datetime.strptime(s, fmt).date()
except ValueError:
pass
return None
def to_int(val):
val = _py(val)
try:
v = float(val)
return None if (v != v) else int(v)
except (TypeError, ValueError):
return None
def to_str(val):
val = _py(val)
if val is None:
return None
if isinstance(val, float) and (val != val):
return None
s = str(val).strip()
return None if s.lower() in ("nan", "nat", "none", "") else s
# ── DB helpers ───────────────────────────────────────────────────────────────
def get_conn():
return mysql.connector.connect(
host=db_config.DB_HOST, port=db_config.DB_PORT,
user=db_config.DB_USER, password=db_config.DB_PASSWORD,
database=db_config.DB_NAME,
)
def insert_import(cursor, study, source_label):
cursor.execute(
"INSERT INTO iwrs_import (study, imported_at, source_file, report_type) VALUES (%s, %s, %s, %s)",
(study, datetime.datetime.now(), source_label, "drugs"),
)
return cursor.lastrowid
def basket_already_imported(cursor, study, basket_id):
cursor.execute(
"SELECT 1 FROM iwrs_destruction WHERE study=%s AND basket_id=%s LIMIT 1",
(study, str(basket_id)),
)
return cursor.fetchone() is not None
# ── parsery ──────────────────────────────────────────────────────────────────
def parse_shipments_report(study):
path = os.path.join(BASE_DIR, f"xls_shipments_{study}", f"shipments_report_{study}.xlsx")
if not os.path.exists(path):
print(f" CHYBÍ: {path}")
return []
raw = pd.read_excel(path, header=None)
header_row = None
for i, row in raw.iterrows():
if "Shipment ID" in [str(v).strip() for v in row]:
header_row = i
break
if header_row is None:
return []
df = pd.read_excel(path, header=header_row).dropna(how="all")
df = df[df["Location"].astype(str).str.contains("Czech", na=False, case=False)]
col = df.columns.tolist()
rows = []
for _, r in df.iterrows():
rows.append({
"shipment_id": to_str(r["Shipment ID"]),
"status": to_str(r["IRT Shipment Status"]),
"type": to_str(r["Type"]),
"ship_from": to_str(r["Shipment From"]),
"ship_to_site": to_str(r["Ship To:"]),
"location": to_str(r["Location"]),
"request_date": to_date(r["Request Date"]),
"shipped_date": to_date(r["Shipped Date"]),
"received_date": to_date(r["Received Date"]) if "Received Date" in col else None,
"received_by": to_str(r["Received by"]) if "Received by" in col else None,
"delivered_date_utc": to_date(r["Delivered Date [UTC]"]) if "Delivered Date [UTC]" in col else None,
"delivery_recipient": to_str(r["Delivery Recipient"]) if "Delivery Recipient" in col else None,
"delivery_details": to_str(r["Delivery Details"]) if "Delivery Details" in col else None,
"cancelled_date": to_date(r["Cancelled Date"]) if "Cancelled Date" in col else None,
"total_medication_ids": to_int(r["Total Medication IDs"]) if "Total Medication IDs" in col else None,
"tracking_no": to_str(r["Tracking #"]) if "Tracking #" in col else None,
"shipping_category": to_str(r["Shipping Category"]) if "Shipping Category" in col else None,
"expected_arrival": to_date(r["Expected Arrival"]) if "Expected Arrival" in col else None,
})
return rows
def parse_shipment_details(study):
detail_dir = os.path.join(BASE_DIR, f"xls_shipment_details_{study}")
files = sorted(glob.glob(os.path.join(detail_dir, "shipment_details_*.xlsx")))
rows = []
for path in files:
m = re.search(r"shipment_details_(.+)\.xlsx", os.path.basename(path))
shipment_id = m.group(1) if m else "UNKNOWN"
raw = pd.read_excel(path, header=None)
header_row = None
for i, row in raw.iterrows():
if "Medication ID" in [str(v).strip() for v in row]:
header_row = i
break
if header_row is None:
continue
df = pd.read_excel(path, header=header_row).dropna(how="all")
for _, r in df.iterrows():
med_desc = (to_str(r.get("Medication Description"))
or to_str(r.get("Medication ID Description")))
med_type = (to_str(r.get("Medication type"))
or to_str(r.get("Medication ID type")))
rows.append({
"shipment_id": shipment_id,
"destination_location": to_str(r.get("Destination Location")),
"shipment_status": to_str(r.get("IRT Shipment Status")),
"shipment_type": to_str(r.get("Type")),
"destination_site": to_str(r.get("Destination Site")),
"investigator": to_str(r.get("Investigator")),
"medication_description": med_desc,
"medication_type": med_type,
"medication_id": to_str(r.get("Medication ID")),
"packaged_lot_no": to_str(r.get("Packaged Lot number")),
"packaged_lot_description": to_str(r.get("Packaged Lot description")),
"container_id": to_str(r.get("Container ID")),
"quantity": to_int(r.get("Quantity of Medication IDs")),
"expiration_date": to_date(r.get("Expiration Date")),
"item_status": to_str(r.get("Status")),
})
return rows
def parse_inventory(study):
inv_dir = os.path.join(BASE_DIR, f"xls_reports_{study}")
files = sorted(glob.glob(os.path.join(inv_dir, "onsite_inventory_detail_*.xlsx")))
rows = []
for path in files:
raw = pd.read_excel(path, header=None)
site = investigator = location = None
header_row = None
for i, row in raw.iterrows():
first = str(row.iloc[0]).strip() if pd.notna(row.iloc[0]) else ""
if first.startswith("Site:"):
site = first.replace("Site:", "").strip()
elif first.startswith("Investigator:"):
investigator = first.replace("Investigator:", "").strip()
elif first.startswith("Location:"):
location = first.replace("Location:", "").strip()
if first in ("Medication", "Medication ID") and header_row is None:
header_row = i
if header_row is None:
continue
df = pd.read_excel(path, header=header_row).dropna(how="all")
df = df.rename(columns={df.columns[0]: "medication_id"})
for _, r in df.iterrows():
rows.append({
"site": site,
"investigator": investigator,
"location": location,
"medication_id": to_str(r["medication_id"]),
"packaged_lot_no": to_str(r.get("Packaged Lot number")),
"original_expiration_date": to_date(r.get("Original Expiration Date when Packaged Lot was Added")),
"expiration_date": to_date(r.get("Expiration date")),
"received_date": to_date(r.get("Received Date")),
"receipt_user": to_str(r.get("Shipment Receipt User")),
"subject_identifier": to_str(r.get("Subject Identifier")),
"quantity_assigned": to_int(r.get("Quantity Assigned")),
"irt_transaction": to_str(r.get("IRT Transaction")),
"date_assigned": to_date(r.get("Date Assigned")),
"assignment_user": to_str(r.get("Assignment User")),
"dispensation_status": to_str(r.get("Dispensation Status")),
"dispensing_date": to_date(r.get("Dispensing date") or r.get("Dispensing Date")),
"quantity_dispensed": to_int(r.get("Quantity Dispensed")),
"dispensing_user": to_str(r.get("Dispensing User")),
"quantity_returned": to_int(r.get("Quantity Returned")),
"date_returned": to_date(r.get("Date Returned")),
"return_user": to_str(r.get("Return User")),
})
return rows
def parse_destruction_files(study):
dest_dir = os.path.join(BASE_DIR, f"xls_ip_destruction_{study}")
files = sorted(glob.glob(os.path.join(dest_dir, "ip_destruction_basket_*.xlsx")))
baskets = []
for path in files:
raw = pd.read_excel(path, header=None)
meta = {}
header_row = None
for i, row in raw.iterrows():
first = str(row.iloc[0]).strip() if pd.notna(row.iloc[0]) else ""
for key, attr in [
("Investigator Name:", "investigator"),
("Site ID:", "site_id"),
("Location:", "location"),
("Basket ID:", "basket_id"),
("Drug Destruction Created Date:", "destruction_date"),
]:
if first.startswith(key):
meta[attr] = first.replace(key, "").strip()
if first == "Medication ID Description" and header_row is None:
header_row = i
if header_row is None:
continue
df = pd.read_excel(path, header=header_row).dropna(how="all")
items = []
for _, r in df.iterrows():
items.append({
"medication_description": to_str(r.get("Medication ID Description")),
"medication_id": to_str(r.get("Medication ID")),
"packaged_lot_description": to_str(r.get("Packaged Lot description")),
"comments": to_str(r.get("Comments")),
})
baskets.append({
"site_id": meta.get("site_id"),
"investigator": meta.get("investigator"),
"location": meta.get("location"),
"basket_id": meta.get("basket_id"),
"destruction_date": to_date(meta.get("destruction_date")),
"items": items,
})
return baskets
# ── insertery ────────────────────────────────────────────────────────────────
def insert_shipments(cursor, import_id, study, rows):
sql = """INSERT INTO iwrs_shipments
(import_id, study, shipment_id, status, type, ship_from, ship_to_site,
location, request_date, shipped_date, received_date, received_by,
delivered_date_utc, delivery_recipient, delivery_details, cancelled_date,
total_medication_ids, tracking_no, shipping_category, expected_arrival)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
for r in rows:
cursor.execute(sql, (
import_id, study, r["shipment_id"], r["status"], r["type"],
r["ship_from"], r["ship_to_site"], r["location"],
r["request_date"], r["shipped_date"], r["received_date"],
r["received_by"], r["delivered_date_utc"], r["delivery_recipient"],
r["delivery_details"], r["cancelled_date"], r["total_medication_ids"],
r["tracking_no"], r["shipping_category"], r["expected_arrival"],
))
def insert_shipment_items(cursor, import_id, study, rows):
sql = """INSERT INTO iwrs_shipment_items
(import_id, study, shipment_id, destination_location, shipment_status,
shipment_type, destination_site, investigator, medication_description,
medication_type, medication_id, packaged_lot_no, packaged_lot_description,
container_id, quantity, expiration_date, item_status)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
for r in rows:
cursor.execute(sql, (
import_id, study, r["shipment_id"], r["destination_location"],
r["shipment_status"], r["shipment_type"], r["destination_site"],
r["investigator"], r["medication_description"], r["medication_type"],
r["medication_id"], r["packaged_lot_no"], r["packaged_lot_description"],
r["container_id"], r["quantity"], r["expiration_date"], r["item_status"],
))
def insert_inventory(cursor, import_id, study, rows):
sql = """INSERT INTO iwrs_inventory
(import_id, study, site, investigator, location, medication_id,
packaged_lot_no, original_expiration_date, expiration_date, received_date,
receipt_user, subject_identifier, quantity_assigned, irt_transaction,
date_assigned, assignment_user, dispensation_status, dispensing_date,
quantity_dispensed, dispensing_user, quantity_returned, date_returned, return_user)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
for r in rows:
cursor.execute(sql, (
import_id, study, r["site"], r["investigator"], r["location"],
r["medication_id"], r["packaged_lot_no"], r["original_expiration_date"],
r["expiration_date"], r["received_date"], r["receipt_user"],
r["subject_identifier"], r["quantity_assigned"], r["irt_transaction"],
r["date_assigned"], r["assignment_user"], r["dispensation_status"],
r["dispensing_date"], r["quantity_dispensed"], r["dispensing_user"],
r["quantity_returned"], r["date_returned"], r["return_user"],
))
def insert_destruction(cursor, study, baskets):
sql = """INSERT IGNORE INTO iwrs_destruction
(study, site_id, investigator, location, basket_id, destruction_date,
medication_description, medication_id, packaged_lot_description, comments)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
skipped = imported = 0
for b in baskets:
if basket_already_imported(cursor, study, b["basket_id"]):
skipped += 1
continue
for item in b["items"]:
cursor.execute(sql, (
study, b["site_id"], b["investigator"], b["location"],
b["basket_id"], b["destruction_date"],
item["medication_description"], item["medication_id"],
item["packaged_lot_description"], item["comments"],
))
imported += 1
return imported, skipped
def import_study(study):
print(f"\n Parsování dat pro {study}...")
shipments = parse_shipments_report(study)
items = parse_shipment_details(study)
inventory = parse_inventory(study)
baskets = parse_destruction_files(study)
print(f" Zásilky: {len(shipments)} | Položky: {len(items)} | Sklad: {len(inventory)} | Destrukce: {len(baskets)} košíků")
conn = get_conn()
cursor = conn.cursor()
import_id = insert_import(cursor, study, f"drugs_{study}")
print(f" import_id = {import_id}")
insert_shipments(cursor, import_id, study, shipments)
insert_shipment_items(cursor, import_id, study, items)
insert_inventory(cursor, import_id, study, inventory)
dest_imported, dest_skipped = insert_destruction(cursor, study, baskets)
conn.commit()
cursor.close()
conn.close()
print(f" Destrukce: {dest_imported} nových | {dest_skipped} košíků přeskočeno")
# ── login ────────────────────────────────────────────────────────────────────
@@ -577,19 +225,17 @@ def main():
finally:
browser.close()
# ── Import do MySQL ───────────────────────────────────────────────────────
# ── Import do MongoDB ─────────────────────────────────────────────────────
print(f"\n{'='*60}")
print("IMPORT DO MySQL")
print("IMPORT DO MongoDB")
print(f"{'='*60}")
for study in STUDIES:
print(f"\n[{study}]")
try:
import_study(study)
except Exception as e:
import traceback
print(f" CHYBA při importu: {e}")
traceback.print_exc()
try:
drugs_mongo.run(STUDIES)
except Exception as e:
import traceback
print(f" CHYBA při importu: {e}")
traceback.print_exc()
print(f"\n{'='*60}")
print("Vše hotovo.")
+57 -28
View File
@@ -156,38 +156,62 @@ def run(page, study):
total_notif = 0
for subject in subjects:
filename = os.path.join(out_dir, f"{today} {study} {subject} Subject Detail.xlsx")
print(f" [{subject}] Stahuji...")
input_field = page.locator('input[placeholder="search"], input[type="text"]').first
input_field.click()
input_field.fill(subject)
page.wait_for_timeout(500)
# Zachytíme table_1 response při výběru subjektu
if api_base:
success = False
table1_data = None
for attempt in range(1, 4):
try:
with page.expect_response(
lambda r: "report_data" in r.url and "table_1" in r.url,
timeout=60000
) as resp_info:
print(f" [{subject}] Stahuji... (pokus {attempt}/3)")
input_field = page.locator('input[placeholder="search"], input[type="text"]').first
input_field.click()
input_field.fill(subject)
page.wait_for_timeout(500)
# Zachytíme table_1 response při výběru subjektu
if api_base:
try:
with page.expect_response(
lambda r: "report_data" in r.url and "table_1" in r.url,
timeout=60000
) as resp_info:
page.locator("mat-option").first.dispatch_event("click")
table1_data = resp_info.value.json()
except Exception as e:
print(f" [{subject}] CHYBA zachycení table_1: {e}")
page.locator("mat-option").first.dispatch_event("click")
page.wait_for_load_state("networkidle", timeout=120000)
table1_data = None
else:
page.locator("mat-option").first.dispatch_event("click")
table1_data = resp_info.value.json()
except Exception as e:
print(f" [{subject}] CHYBA zachycení table_1: {e}")
page.locator("mat-option").first.dispatch_event("click")
page.wait_for_load_state("networkidle", timeout=120000)
table1_data = None
page.wait_for_load_state("networkidle", timeout=120000)
table1_data = None
else:
page.locator("mat-option").first.dispatch_event("click")
page.wait_for_load_state("networkidle", timeout=120000)
table1_data = None
page.wait_for_timeout(2000)
page.wait_for_load_state("networkidle", timeout=120000)
page.wait_for_timeout(1000)
with page.expect_download(timeout=60000) as dl:
page.get_by_role("button", name="Download XLS").click()
dl.value.save_as(filename)
print(f" [{subject}] XLS OK")
success = True
break
except Exception as e:
print(f" [{subject}] pokus {attempt} selhal: {e}")
if attempt < 3:
try:
page.goto(f"{BASE_URL}/report/patient_detail_report")
page.wait_for_load_state("networkidle", timeout=120000)
except Exception as ge:
print(f" [{subject}] refresh selhal: {ge}")
with page.expect_download(timeout=120000) as dl:
page.get_by_role("button", name="Download XLS").click()
dl.value.save_as(filename)
print(f" [{subject}] XLS OK")
if not success:
print(f" [{subject}] PŘESKAKUJI po 3 neúspěšných pokusech")
try:
page.goto(f"{BASE_URL}/report/patient_detail_report")
page.wait_for_load_state("networkidle", timeout=120000)
except Exception:
pass
continue
# Stáhnout notifikace pro tohoto subjekta
if api_base and table1_data:
@@ -196,8 +220,13 @@ def run(page, study):
)
total_notif += n
page.get_by_role("button", name="Clear").click()
page.wait_for_load_state("networkidle", timeout=120000)
try:
page.get_by_role("button", name="Clear").click()
page.wait_for_load_state("networkidle", timeout=120000)
except Exception as e:
print(f" [{subject}] Clear selhal: {e} — refresh")
page.goto(f"{BASE_URL}/report/patient_detail_report")
page.wait_for_load_state("networkidle", timeout=120000)
print(f" [{study}] Subject details hotovo. Nových notifikací: {total_notif}")
+24 -292
View File
@@ -2,23 +2,21 @@
Kompletní pipeline:
1. Stažení Subject Summary Reportů (obě studie)
2. Stažení Subject Detail Reportů + notifikací (obě studie)
3. Import do MySQL (summary, visits, notifikace)
3. Import do MongoDB (subject_summary + visits + notifications)
Spusť tento skript místo samostatných skriptů.
"""
import os
import sys
import datetime
import glob
import re
from playwright.sync_api import sync_playwright
import numpy as np
import pandas as pd
import db_config
import mysql.connector
import download_subject_details as dsd
import import_to_mongo
import import_notifications_to_mongo
# ── CONFIG ───────────────────────────────────────────────────────────────────
BASE_URL = "https://janssen.4gclinical.com"
@@ -72,6 +70,7 @@ def download_summary(page, study, today):
# ── KROK 2: Subject Details ───────────────────────────────────────────────────
def get_subjects_from_summary(summary_path):
import pandas as pd
raw = pd.read_excel(summary_path, header=None)
header_row = None
for i, row in raw.iterrows():
@@ -112,277 +111,7 @@ def download_details(page, study, summary_path, today):
page.wait_for_load_state("networkidle", timeout=120000)
# ── KROK 3: Import do MySQL ───────────────────────────────────────────────────
def get_conn():
return mysql.connector.connect(
host=db_config.DB_HOST,
port=db_config.DB_PORT,
user=db_config.DB_USER,
password=db_config.DB_PASSWORD,
database=db_config.DB_NAME,
)
def _py(val):
"""Převede numpy skalár na Python nativní typ."""
if isinstance(val, np.generic):
return val.item()
return val
def to_date(val):
val = _py(val)
if val is None or (isinstance(val, float) and (val != val)):
return None
try:
if pd.isna(val):
return None
except (TypeError, ValueError):
pass
if isinstance(val, pd.Timestamp):
return None if pd.isna(val) else val.date()
if isinstance(val, datetime.datetime):
return val.date()
if isinstance(val, datetime.date):
return val
s = str(val).strip()
if not s or s.lower() in ("nat", "nan", "none", ""):
return None
for fmt in ("%Y-%m-%d", "%d-%b-%Y", "%d-%m-%Y", "%Y-%m-%d %H:%M:%S"):
try:
return datetime.datetime.strptime(s, fmt).date()
except ValueError:
pass
return None
def to_int(val):
val = _py(val)
try:
v = float(val)
return None if (v != v) else int(v)
except (TypeError, ValueError):
return None
def to_float(val):
val = _py(val)
try:
v = float(val)
return None if (v != v) else float(v)
except (TypeError, ValueError):
return None
def to_str(val):
val = _py(val)
if val is None:
return None
if isinstance(val, float) and (val != val):
return None
s = str(val).strip()
return None if s.lower() in ("nan", "nat", "none", "") else s
def read_summary_df(path):
raw = pd.read_excel(path, header=None)
header_row = None
for i, row in raw.iterrows():
if "Subject" in [str(v).strip() for v in row]:
header_row = i
break
if header_row is None:
raise ValueError(f"Hlavičkový řádek nenalezen v {path}")
return pd.read_excel(path, header=header_row).dropna(how="all")
def parse_detail_visits(path):
df = pd.read_excel(path, sheet_name="patient_detail_report", header=None)
header_row = None
for i, row in df.iterrows():
if "Visit Type" in [str(v).strip() for v in row]:
header_row = i
break
if header_row is None:
return []
visits_df = df.iloc[header_row + 1:].copy()
visits_df.columns = range(visits_df.shape[1])
rows = []
for _, r in visits_df.iterrows():
visit_type = to_str(r.get(0))
if visit_type not in ("Past", "Upcoming"):
continue
rows.append({
"visit_type": visit_type,
"scheduled_date": to_date(r.get(1)),
"window_days": to_str(r.get(2)),
"actual_date": to_date(r.get(3)),
"irt_transaction_no": to_int(r.get(4)),
"irt_transaction_description": to_str(r.get(5)),
"medication_assignment": to_str(r.get(6)),
"quantity_assigned": to_int(r.get(7)),
"medication_id": to_str(r.get(8)),
})
return rows
def insert_import(cursor, study, source_file):
cursor.execute(
"INSERT INTO iwrs_import (study, imported_at, source_file) VALUES (%s, %s, %s)",
(study, datetime.datetime.now(), os.path.basename(source_file)),
)
return cursor.lastrowid
def insert_uco3001_summary(cursor, import_id, df):
sql = """INSERT INTO iwrs_uco3001_subject_summary (
import_id, subject, prior_subject_identifier, site, investigator, location,
cohort_per_irt, informed_consent_date, adolescent_assent_date, age, weight,
rescreened_subject, adt_ir, three_or_more_advanced_therapies,
only_oral_5asa_compounds, ustekinumab, isolated_proctitis,
clinical_responder_status_i12_m0, irt_subject_status,
i0_rand_date_local, last_irt_transaction,
last_irt_transaction_date_local, last_irt_transaction_date_utc,
next_irt_transaction, next_irt_transaction_date_local,
most_recent_med_assignment_date, days_since_last_med_assignment,
patient_forecast_status, patient_forecast_status_changed_date
) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
col = df.columns.tolist()
for _, r in df.iterrows():
cursor.execute(sql, (
import_id,
to_str(r["Subject"]),
to_str(r["Prior Subject Identifier"]) if "Prior Subject Identifier" in col else None,
to_str(r["Site"]),
to_str(r["Investigator"]),
to_str(r["Location"]),
to_str(r["Cohort per IRT"]),
to_date(r["Informed Consent Date"]),
to_date(r["Adolescent Assent Date"]) if "Adolescent Assent Date" in col else None,
to_int(r["Subject's age collection"]),
to_float(r["Subject's weight collection"]) if "Subject's weight collection" in col else None,
to_str(r["Rescreened Subject"]) if "Rescreened Subject" in col else None,
to_str(r["ADT-IR"]) if "ADT-IR" in col else None,
to_str(r["3 or More Advanced Therapies"]) if "3 or More Advanced Therapies" in col else None,
to_str(r["Only Oral 5-ASA Compounds"]) if "Only Oral 5-ASA Compounds" in col else None,
to_str(r["Ustekinumab"]) if "Ustekinumab" in col else None,
to_str(r["Isolated Proctitis"]) if "Isolated Proctitis" in col else None,
to_str(r["Clinical Responder Status at I-12 / M-0"]) if "Clinical Responder Status at I-12 / M-0" in col else None,
to_str(r["IRT Subject Status"]),
to_date(r["I0_RAND_TIMESTAMP_LOCAL [Local]"]) if "I0_RAND_TIMESTAMP_LOCAL [Local]" in col else None,
to_str(r["Last Recorded IRT Transaction"]),
to_date(r["Last Recorded IRT Transaction Date [Local]"]),
to_date(r["Last Recorded IRT Transaction Date (UTC)"]),
to_str(r["Next Expected IRT Transaction"]),
to_date(r["Next Expected IRT Transaction Date [Local]"]),
to_date(r["Most Recent Medication Assignment Transaction [Local]"]) if "Most Recent Medication Assignment Transaction [Local]" in col else None,
to_int(r["Days Since Last Medication Assignment Transaction"]) if "Days Since Last Medication Assignment Transaction" in col else None,
to_str(r["Patient Forecast Status"]) if "Patient Forecast Status" in col else None,
to_date(r["Patient Forecast Status Changed Date (UTC)"]) if "Patient Forecast Status Changed Date (UTC)" in col else None,
))
def insert_mdd3003_summary(cursor, import_id, df):
sql = """INSERT INTO iwrs_mdd3003_subject_summary (
import_id, subject, prior_subject_identifier, site, investigator, location,
cohort_per_irt, madrs_criteria_integrated, informed_consent_date, age,
madrs_criteria_v15, madrs_criteria_v16, madrs_criteria_v17,
stratification_country, age_group, stable_remitters, irt_subject_status,
last_irt_transaction, last_irt_transaction_date_local,
last_irt_transaction_date_utc, next_irt_transaction,
next_irt_transaction_date_local, date_screened, date_screen_failed,
date_randomized_part1, date_early_withdraw_randomized_part1,
date_open_label_induction, date_early_withdraw_open_label_induction,
date_randomized_part2, date_early_withdraw_randomized_part2,
date_completed, date_unblinded
) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
col = df.columns.tolist()
for _, r in df.iterrows():
cursor.execute(sql, (
import_id,
to_str(r["Subject"]),
to_str(r["Prior Subject Identifier"]) if "Prior Subject Identifier" in col else None,
to_str(r["Site"]),
to_str(r["Investigator"]),
to_str(r["Location"]),
to_str(r["Cohort per IRT"]),
to_str(r["MADRS response criteria integrated or manually entered"]) if "MADRS response criteria integrated or manually entered" in col else None,
to_date(r["Informed Consent Date"]),
to_int(r["Subject's age collection"]),
to_str(r["MADRS response criteria v1.5 from RAVE"]) if "MADRS response criteria v1.5 from RAVE" in col else None,
to_str(r["MADRS response criteria v1.6 from RAVE"]) if "MADRS response criteria v1.6 from RAVE" in col else None,
to_str(r["MADRS response criteria v1.7 from RAVE"]) if "MADRS response criteria v1.7 from RAVE" in col else None,
to_str(r["Stratification Country"]) if "Stratification Country" in col else None,
to_str(r["Age Group"]) if "Age Group" in col else None,
to_str(r["Stable Remitters vs. Non Stable Remitters"]) if "Stable Remitters vs. Non Stable Remitters" in col else None,
to_str(r["IRT Subject Status"]),
to_str(r["Last Recorded IRT Transaction"]),
to_date(r["Last Recorded IRT Transaction Date [Local]"]),
to_date(r["Last Recorded IRT Transaction Date (UTC)"]),
to_str(r["Next Expected IRT Transaction"]),
to_date(r["Next Expected IRT Transaction Date [Local]"]),
to_date(r["Date Screened [Local]"]) if "Date Screened [Local]" in col else None,
to_date(r["Date Screen Failed [Local]"]) if "Date Screen Failed [Local]" in col else None,
to_date(r["Date Randomized Part 1 [Local]"]) if "Date Randomized Part 1 [Local]" in col else None,
to_date(r["Date Early Withdraw Randomized Part 1 [Local]"]) if "Date Early Withdraw Randomized Part 1 [Local]" in col else None,
to_date(r["Date Open Label Induction [Local]"]) if "Date Open Label Induction [Local]" in col else None,
to_date(r["Date Early Withdraw Open Label Induction [Local]"]) if "Date Early Withdraw Open Label Induction [Local]" in col else None,
to_date(r["Date Randomized Part 2 [Local]"]) if "Date Randomized Part 2 [Local]" in col else None,
to_date(r["Date Early Withdraw Randomized Part 2 [Local]"]) if "Date Early Withdraw Randomized Part 2 [Local]" in col else None,
to_date(r["Date Completed [Local]"]) if "Date Completed [Local]" in col else None,
to_date(r["Date Unblinded [Local]"]) if "Date Unblinded [Local]" in col else None,
))
def insert_visits(cursor, import_id, study, subject, visits):
if not visits:
return
sql = """INSERT INTO iwrs_subject_visits (
import_id, study, subject, visit_type, scheduled_date, window_days,
actual_date, irt_transaction_no, irt_transaction_description,
medication_assignment, quantity_assigned, medication_id
) VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"""
for v in visits:
cursor.execute(sql, (
import_id, study, subject,
v["visit_type"], v["scheduled_date"], v["window_days"],
v["actual_date"], v["irt_transaction_no"],
v["irt_transaction_description"], v["medication_assignment"],
v["quantity_assigned"], v["medication_id"],
))
def import_to_mysql(summary_path, detail_files, study):
print(f"\n [MySQL] Importuji {study}...")
df_summary = read_summary_df(summary_path)
conn = get_conn()
cursor = conn.cursor()
import_id = insert_import(cursor, study, summary_path)
if study == "77242113UCO3001":
insert_uco3001_summary(cursor, import_id, df_summary)
else:
insert_mdd3003_summary(cursor, import_id, df_summary)
total_visits = 0
for path in detail_files:
fname = os.path.basename(path)
m = re.search(r"\d{4}-\d{2}-\d{2} \S+ (\S+) Subject Detail\.xlsx", fname)
subject = m.group(1) if m else "UNKNOWN"
visits = parse_detail_visits(path)
insert_visits(cursor, import_id, study, subject, visits)
total_visits += len(visits)
conn.commit()
cursor.close()
conn.close()
print(f" [MySQL] import_id={import_id} | pacientů={len(df_summary)} | transakcí={total_visits}")
return import_id
# ── MAIN ─────────────────────────────────────────────────────────────────────
# ── KROK 3: Import do MongoDB ────────────────────────────────────────────────
def main():
today = datetime.date.today().strftime("%Y-%m-%d")
@@ -391,12 +120,12 @@ def main():
summary_paths = {}
# ── Krok 1 + 2: stahování (Playwright, každá studie zvlášť kvůli session) ──
# Krok 1 + 2: stahování (Playwright, každá studie zvlášť kvůli session)
with sync_playwright() as p:
for study in STUDIES:
print(f"\n{'='*60}")
print("\n" + "=" * 60)
print(f"[{study}] KROK 1: Subject Summary Report")
print(f"{'='*60}")
print("=" * 60)
browser = p.chromium.launch(headless=False)
context = browser.new_context(accept_downloads=True)
page = context.new_page()
@@ -415,10 +144,10 @@ def main():
finally:
browser.close()
# ── Krok 3: import do MySQL ──────────────────────────────────────────────
print(f"\n{'='*60}")
print("KROK 3: Import do MySQL")
print(f"{'='*60}")
# Krok 3: import do MongoDB
print("\n" + "=" * 60)
print("KROK 3: Import do MongoDB")
print("=" * 60)
for study in STUDIES:
summary_path = summary_paths.get(study)
@@ -426,18 +155,21 @@ def main():
print(f" [{study}] PŘESKOČENO — stahování selhalo")
continue
detail_files = sorted(glob.glob(
os.path.join(DETAILS_DIR, study, f"{today} {study} * Subject Detail.xlsx")
))
try:
import_to_mysql(summary_path, detail_files, study)
import_to_mongo.run(study, summary_path, DETAILS_DIR, today)
except Exception as e:
print(f" [{study}] CHYBA při importu: {e}")
print(f" [{study}] CHYBA při importu summary/visits: {e}")
print(f"\n{'='*60}")
# Notifikace: PDF/JSON z disku rovnou do Mongo iwrs_notifications
print("\n [notifikace] import PDF/JSON do Mongo...")
try:
import_notifications_to_mongo.main(STUDIES)
except Exception as e:
print(f" CHYBA při importu notifikací: {e}")
print("\n" + "=" * 60)
print("Vše hotovo.")
print(f"{'='*60}")
print("=" * 60)
main()
-449
View File
@@ -1,449 +0,0 @@
"""
download_attachments_v1.0.py
Nazev: download_attachments_v1.0.py
Verze: 1.0
Datum: 2026-06-02
Autor: vladimir.buzalka
Popis:
Stahuje skutecne prilohy (is_inline=False) vsech emailu z MongoDB kolekce
ordinace@buzalkova.cz primo pres Microsoft Graph API a uklada je do
adresare /mnt/Emails/ordinace@buzalkova.cz/Attachments/.
Deduplikace podle SHA256 hashe obsahu:
- stejny hash = soubor uz existuje -> preskoci
- prvni vyskytu souboru: ulozi pod puvodnimnazvem
- kolize nazvu (stejny nazev, jiny hash): faktura_2.pdf, faktura_3.pdf ...
Po ulozeni aktualizuje MongoDB:
- v email dokumentu: kazda priloha dostane file_hash + local_path
- kolekce emaily.attachments_index: _id=hash, filename, path, size_bytes,
mime_type, first_seen_at, ref_count (pocet emailu ktery ji obsahuje)
Bezpecne prerusit a opakovat:
- zpravy kde jsou vsechny prilohy uz stazene (maji file_hash) se preskoci
- --force-recheck znovu overi i uz stazene (pro pripad zmen na disku)
POZOR: Skript pouze CIST ze schranky — zadny zapis do schranky!
Spousteni:
python download_attachments_v1.0.py # stahni vse co chybi
python download_attachments_v1.0.py --limit 50 # test na prvnich 50 emailech
python download_attachments_v1.0.py --force-recheck # overi i uz stazene
Docker (po pridani mountu /mnt/user/Emails -> /mnt/Emails):
docker exec -it python-runner python /scripts/download_attachments_v1.0.py
Zavislosti:
msal, requests, pymongo, python-dateutil
Python 3.10+
Struktura na disku:
/mnt/Emails/
└── ordinace@buzalkova.cz/
└── Attachments/
├── faktura_2026.pdf
├── vysledky_lab.pdf
├── vysledky_lab_2.pdf <- kolize nazvu, jiny obsah
└── ...
Kolekce emaily.attachments_index:
_id SHA256 hash (hex)
filename nazev souboru na disku (prvni vyskytu)
local_path relativni cesta od Attachments/ (zatim = filename)
size_bytes velikost souboru
mime_type MIME typ
first_seen_at datetime UTC
ref_count v kolika emailech se tato priloha vyskytuje
Aktualizace v email dokumentu (kolekce ordinace@buzalkova.cz):
attachments[i].file_hash SHA256 hash
attachments[i].local_path cesta relativni od Attachments/
Historie verzi:
1.0 2026-06-02 Inicialni verze
"""
import sys
import hashlib
import logging
import argparse
from pathlib import Path
from datetime import datetime, timezone
from typing import Optional
import msal
import requests
from pymongo import MongoClient, UpdateOne
if hasattr(sys.stdout, "reconfigure"):
sys.stdout.reconfigure(encoding="utf-8", errors="replace")
# ─── KONFIGURACE ──────────────────────────────────────────────────────────────
GRAPH_TENANT_ID = "7d269944-37a4-43a1-8140-c7517dc426e9"
GRAPH_CLIENT_ID = "4b222bfd-78c9-4239-a53f-43006b3ed07f"
GRAPH_CLIENT_SECRET = "Txg8Q~MjhocuopxsJyJBhPmDfMxZ2r5WpTFj1dfk"
GRAPH_MAILBOX = "ordinace@buzalkova.cz"
GRAPH_URL = "https://graph.microsoft.com/v1.0"
MONGO_URI = "mongodb://192.168.1.76:27017"
MONGO_DB = "emaily"
MONGO_COL_EMAILS = "ordinace@buzalkova.cz"
MONGO_COL_INDEX = "attachments_index"
ATTACHMENTS_DIR = Path("/mnt/Emails/ordinace@buzalkova.cz/Attachments")
LOG_FILE = Path(__file__).parent / "parse_emails_errors.log"
SCRIPT_VERSION = "1.0"
BATCH_SIZE = 50
# ──────────────────────────────────────────────────────────────────────────────
logging.basicConfig(
filename=str(LOG_FILE),
level=logging.ERROR,
format="%(asctime)s | %(message)s",
datefmt="%Y-%m-%d %H:%M:%S",
encoding="utf-8",
)
_graph_token: Optional[str] = None
# ─── Graph API ────────────────────────────────────────────────────────────────
def get_token() -> str:
global _graph_token
app = msal.ConfidentialClientApplication(
GRAPH_CLIENT_ID,
authority=f"https://login.microsoftonline.com/{GRAPH_TENANT_ID}",
client_credential=GRAPH_CLIENT_SECRET,
)
result = app.acquire_token_for_client(scopes=["https://graph.microsoft.com/.default"])
if "access_token" not in result:
raise RuntimeError(f"Graph auth failed: {result}")
_graph_token = result["access_token"]
return _graph_token
def graph_get_bytes(url: str) -> bytes:
"""Stahne binarni obsah prilohy."""
global _graph_token
if not _graph_token:
get_token()
for attempt in range(2):
r = requests.get(url, headers={"Authorization": f"Bearer {_graph_token}"}, timeout=120, stream=True)
if r.status_code == 401:
get_token()
continue
r.raise_for_status()
return r.content
raise RuntimeError(f"Graph GET bytes failed: {url}")
def graph_get_json(url: str, params: dict = None) -> dict:
global _graph_token
if not _graph_token:
get_token()
for attempt in range(2):
r = requests.get(url, headers={"Authorization": f"Bearer {_graph_token}"}, params=params, timeout=30)
if r.status_code == 401:
get_token()
continue
r.raise_for_status()
return r.json()
raise RuntimeError(f"Graph GET json failed: {url}")
def fetch_attachment_content(graph_message_id: str, attachment_id: str) -> Optional[bytes]:
"""Stahne obsah prilohy pres Graph API."""
url = f"{GRAPH_URL}/users/{GRAPH_MAILBOX}/messages/{graph_message_id}/attachments/{attachment_id}/$value"
try:
return graph_get_bytes(url)
except Exception as e:
logging.error("fetch_attachment_content failed [msg=%s att=%s]: %s", graph_message_id, attachment_id, e)
return None
def fetch_message_attachments(graph_message_id: str) -> list[dict]:
"""Nacte seznam priloh zpravy z Graph API (metadata vcetne attachment ID)."""
url = f"{GRAPH_URL}/users/{GRAPH_MAILBOX}/messages/{graph_message_id}/attachments"
try:
data = graph_get_json(url, {"$select": "id,name,contentType,size,isInline,contentId"})
return data.get("value", [])
except Exception as e:
logging.error("fetch_message_attachments failed [%s]: %s", graph_message_id, e)
return []
# ─── Dedup + ukládání ─────────────────────────────────────────────────────────
def sha256(data: bytes) -> str:
return hashlib.sha256(data).hexdigest()
def resolve_filename(desired_name: str, att_dir: Path, hash_val: str, index_col) -> str:
"""
Vrati nazev souboru ktery pouzit pro ulozeni.
Pokud desired_name jiz existuje s jinym hashem, prida suffix _2, _3 ...
"""
# Zkontroluj jestli existujici soubor se stejnym nazvem ma stejny hash
existing = index_col.find_one({"filename": desired_name})
if existing:
if existing["_id"] == hash_val:
return desired_name # Stejny hash, stejne jmeno — dedup hit
# Jiny hash — hledej volny suffix
stem = Path(desired_name).stem
suffix = Path(desired_name).suffix
n = 2
while True:
candidate = f"{stem}_{n}{suffix}"
if not (att_dir / candidate).exists():
# Overi ze ani v indexu neni tento kandidat s jinym hashem
ex2 = index_col.find_one({"filename": candidate})
if not ex2 or ex2["_id"] == hash_val:
return candidate
n += 1
return desired_name
def save_attachment(content: bytes, original_name: str, att_dir: Path, index_col) -> tuple[str, str, bool]:
"""
Ulozi prilohu s deduplikaci.
Vraci (hash, local_path, was_new):
was_new=True -> soubor byl ulozen
was_new=False -> hash uz existoval, soubor preskocen
"""
hash_val = sha256(content)
# Zkontroluj index — pokud hash uz existuje, vrat existujici zaznam
existing = index_col.find_one({"_id": hash_val})
if existing:
# Zvys pocitadlo referenci
index_col.update_one({"_id": hash_val}, {"$inc": {"ref_count": 1}})
return hash_val, existing["local_path"], False
# Novy soubor — urcit nazev
safe_name = "".join(c if c.isalnum() or c in "._- " else "_" for c in original_name).strip()
if not safe_name:
safe_name = f"attachment_{hash_val[:8]}"
filename = resolve_filename(safe_name, att_dir, hash_val, index_col)
file_path = att_dir / filename
# Uloz soubor
file_path.write_bytes(content)
# Zaznamenej do indexu
index_col.insert_one({
"_id": hash_val,
"filename": filename,
"local_path": filename,
"size_bytes": len(content),
"mime_type": "",
"first_seen_at": datetime.now(timezone.utc).replace(tzinfo=None),
"ref_count": 1,
})
return hash_val, filename, True
# ─── MAIN ─────────────────────────────────────────────────────────────────────
def main():
ap = argparse.ArgumentParser(description=f"download_attachments v{SCRIPT_VERSION}")
ap.add_argument("--limit", type=int, default=0,
help="Zpracovat max N emailu (0 = vse)")
ap.add_argument("--force-recheck", action="store_true",
help="Znovu overi i emaily kde prilohy uz maji file_hash")
ap.add_argument("--no-indexes", action="store_true",
help="Nevytvorit indexy na konci")
args = ap.parse_args()
start = datetime.now()
print(f"=== download_attachments v{SCRIPT_VERSION} ===")
print(f"Start: {start.strftime('%Y-%m-%d %H:%M:%S')}")
print(f"Schránka: {GRAPH_MAILBOX}")
print(f"Cilovy adresar: {ATTACHMENTS_DIR}")
print(f"MongoDB: {MONGO_URI} -> {MONGO_DB}")
# Adresar
ATTACHMENTS_DIR.mkdir(parents=True, exist_ok=True)
print(f" Adresar OK")
# Graph
print("\nPřipojuji se k Graph API...")
try:
get_token()
print(" Graph API OK")
except Exception as e:
print(f" CHYBA: {e}")
sys.exit(1)
# MongoDB
client = MongoClient(MONGO_URI, serverSelectionTimeoutMS=5000)
try:
client.admin.command("ping")
print(" MongoDB OK")
except Exception as e:
print(f" CHYBA: MongoDB neni dostupna -- {e}")
sys.exit(1)
col_emails = client[MONGO_DB][MONGO_COL_EMAILS]
col_index = client[MONGO_DB][MONGO_COL_INDEX]
# Indexy na attachment index kolekci
if not args.no_indexes:
col_index.create_index("filename")
col_index.create_index("mime_type")
# Dotaz — emaily s prilohou ktere jeste nebyly zpracovany
if args.force_recheck:
query = {"has_attachments": True}
else:
query = {
"has_attachments": True,
"attachments": {
"$elemMatch": {
"is_inline": False,
"file_hash": {"$exists": False},
}
}
}
total = col_emails.count_documents(query)
print(f"\nEmailu ke zpracovani: {total}")
if total == 0:
print("Neni co stahnout.")
client.close()
return
cursor = col_emails.find(query, {"_id": 1, "graph_id": 1, "subject": 1, "attachments": 1})
if args.limit:
cursor = cursor.limit(args.limit)
ok_count = 0
new_count = 0
skip_count = 0
err_count = 0
email_i = 0
batch = []
def flush():
if not batch:
return
try:
col_emails.bulk_write(batch, ordered=False)
except Exception as e:
logging.error("bulk_write: %s", e)
print(f" CHYBA bulk_write: {e}")
batch.clear()
for email_doc in cursor:
email_i += 1
email_id = email_doc["_id"]
graph_id = email_doc.get("graph_id", "")
subject = (email_doc.get("subject") or "")[:60]
att_list = email_doc.get("attachments") or []
# Jen skutecne prilohy
real_atts = [a for a in att_list if not a.get("is_inline", False)]
if not real_atts:
continue
print(f"\n {email_i:>5}/{total} {subject}")
# Nacti attachment IDs z Graph API
graph_atts = fetch_message_attachments(graph_id)
graph_att_map = {a["name"]: a for a in graph_atts if not a.get("isInline", False)}
updated_atts = list(att_list)
email_ok = True
for i, att in enumerate(updated_atts):
if att.get("is_inline", False):
continue
if not args.force_recheck and att.get("file_hash"):
skip_count += 1
print(f" SKIP {att['filename']}")
continue
att_name = att.get("filename", "")
graph_att = graph_att_map.get(att_name)
if not graph_att:
# Zkus najit podle casti nazvu
for gname, ga in graph_att_map.items():
if att_name.lower() in gname.lower():
graph_att = ga
break
if not graph_att:
logging.error("attachment not found in Graph [email=%s att=%s]", email_id, att_name)
print(f" ERR {att_name} (nenalezeno v Graph)")
err_count += 1
email_ok = False
continue
# Stahni obsah
content = fetch_attachment_content(graph_id, graph_att["id"])
if content is None:
err_count += 1
email_ok = False
print(f" ERR {att_name} (stazeni selhalo)")
continue
# Uloz s dedupem
hash_val, local_path, was_new = save_attachment(content, att_name, ATTACHMENTS_DIR, col_index)
# Aktualizuj MIME typ v indexu
col_index.update_one(
{"_id": hash_val},
{"$set": {"mime_type": att.get("mime_type", graph_att.get("contentType", ""))}},
)
# Zaznamenej do emailu
updated_atts[i] = {**att, "file_hash": hash_val, "local_path": local_path}
if was_new:
new_count += 1
print(f" NEW {local_path} ({len(content):,} B)")
else:
skip_count += 1
print(f" DUP {att_name} -> {local_path}")
if email_ok:
ok_count += 1
# Uloz aktualizovane prilohy zpet do emailu
batch.append(UpdateOne(
{"_id": email_id},
{"$set": {"attachments": updated_atts}}
))
if len(batch) >= BATCH_SIZE:
flush()
if email_i % 100 == 0:
elapsed = (datetime.now() - start).total_seconds()
print(f" {''*60}")
print(f" Průběh: emaily={email_i}/{total} nove={new_count} dup={skip_count} err={err_count}")
print(f" {''*60}")
flush()
elapsed_total = (datetime.now() - start).total_seconds()
files_total = col_index.count_documents({})
size_total = sum(d.get("size_bytes", 0) for d in col_index.find({}, {"size_bytes": 1}))
print(f"\n{'='*52}")
print(f"Vysledek: emaily={ok_count} | nove soubory={new_count} | duplikaty={skip_count} | err={err_count}")
print(f"Souboru v indexu: {files_total} ({size_total/1024/1024:.1f} MB)")
print(f"Celkovy cas: {int(elapsed_total//3600)}h {int((elapsed_total%3600)//60)}m {int(elapsed_total%60)}s")
print(f"\nKonec: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
if err_count:
print(f"Chyby logovany do: {LOG_FILE}")
client.close()
if __name__ == "__main__":
main()
-428
View File
@@ -1,428 +0,0 @@
"""
download_attachments_v1.1.py
Nazev: download_attachments_v1.1.py
Verze: 1.1
Datum: 2026-06-02
Autor: vladimir.buzalka
Popis:
Stahuje skutecne prilohy (is_inline=False) vsech emailu z MongoDB
pres Microsoft Graph API a uklada je do adresare
/mnt/Emails/<schránka>/Attachments/.
Schránka se predava jako povinny parametr --mailbox.
Deduplikace podle SHA256 hashe obsahu:
- stejny hash = soubor uz existuje -> preskoci
- prvni vyskytu souboru: ulozi pod puvodnimnazvem
- kolize nazvu (stejny nazev, jiny hash): faktura_2.pdf, faktura_3.pdf ...
Po ulozeni aktualizuje MongoDB:
- v email dokumentu: kazda priloha dostane file_hash + local_path
- kolekce emaily.attachments_index: _id=hash, filename, path, size_bytes,
mime_type, mailbox, first_seen_at, ref_count
Bezpecne prerusit a opakovat — emaily kde vsechny prilohy maji file_hash
se preskoci. --force-recheck znovu overi i uz stazene.
POZOR: Skript pouze CIST ze schranky — zadny zapis do schranky!
Spousteni:
python download_attachments_v1.1.py --mailbox ordinace@buzalkova.cz
python download_attachments_v1.1.py --mailbox vladimir.buzalka@buzalka.cz --limit 50
python download_attachments_v1.1.py --mailbox ordinace@buzalkova.cz --force-recheck
Docker:
docker exec -it python-runner python /scripts/download_attachments_v1.1.py \\
--mailbox ordinace@buzalkova.cz
Zavislosti:
msal, requests, pymongo
Python 3.10+
Struktura na disku:
/mnt/Emails/
└── <mailbox>/
└── Attachments/
├── faktura_2026.pdf
├── vysledky_lab.pdf
├── vysledky_lab_2.pdf
└── ...
Kolekce emaily.attachments_index:
_id SHA256 hash (hex)
filename nazev souboru na disku
local_path relativni cesta od Attachments/
size_bytes velikost souboru
mime_type MIME typ
mailbox schránka ze ktere pochazi prvni vyskytu
first_seen_at datetime UTC
ref_count v kolika emailech se tato priloha vyskytuje
Historie verzi:
1.0 2026-06-02 Inicialni verze
1.1 2026-06-02 Schránka jako parametr --mailbox (univerzalni pouziti)
"""
import sys
import hashlib
import logging
import argparse
from pathlib import Path
from datetime import datetime, timezone
from typing import Optional
import msal
import requests
from pymongo import MongoClient, UpdateOne
if hasattr(sys.stdout, "reconfigure"):
sys.stdout.reconfigure(encoding="utf-8", errors="replace")
# ─── KONFIGURACE ──────────────────────────────────────────────────────────────
GRAPH_TENANT_ID = "7d269944-37a4-43a1-8140-c7517dc426e9"
GRAPH_CLIENT_ID = "4b222bfd-78c9-4239-a53f-43006b3ed07f"
GRAPH_CLIENT_SECRET = "Txg8Q~MjhocuopxsJyJBhPmDfMxZ2r5WpTFj1dfk"
GRAPH_URL = "https://graph.microsoft.com/v1.0"
MONGO_URI = "mongodb://192.168.1.76:27017"
MONGO_DB = "emaily"
MONGO_COL_INDEX = "attachments_index"
EMAILS_BASE_DIR = Path("/mnt/Emails")
LOG_FILE = Path(__file__).parent / "parse_emails_errors.log"
SCRIPT_VERSION = "1.1"
BATCH_SIZE = 50
# ──────────────────────────────────────────────────────────────────────────────
logging.basicConfig(
filename=str(LOG_FILE),
level=logging.ERROR,
format="%(asctime)s | %(message)s",
datefmt="%Y-%m-%d %H:%M:%S",
encoding="utf-8",
)
_graph_token: Optional[str] = None
# ─── Graph API ────────────────────────────────────────────────────────────────
def get_token() -> str:
global _graph_token
app = msal.ConfidentialClientApplication(
GRAPH_CLIENT_ID,
authority=f"https://login.microsoftonline.com/{GRAPH_TENANT_ID}",
client_credential=GRAPH_CLIENT_SECRET,
)
result = app.acquire_token_for_client(scopes=["https://graph.microsoft.com/.default"])
if "access_token" not in result:
raise RuntimeError(f"Graph auth failed: {result}")
_graph_token = result["access_token"]
return _graph_token
def graph_get_bytes(url: str) -> bytes:
global _graph_token
if not _graph_token:
get_token()
for attempt in range(2):
r = requests.get(url, headers={"Authorization": f"Bearer {_graph_token}"}, timeout=120, stream=True)
if r.status_code == 401:
get_token()
continue
r.raise_for_status()
return r.content
raise RuntimeError(f"Graph GET bytes failed: {url}")
def graph_get_json(url: str, params: dict = None) -> dict:
global _graph_token
if not _graph_token:
get_token()
for attempt in range(2):
r = requests.get(url, headers={"Authorization": f"Bearer {_graph_token}"}, params=params, timeout=30)
if r.status_code == 401:
get_token()
continue
r.raise_for_status()
return r.json()
raise RuntimeError(f"Graph GET json failed: {url}")
def fetch_message_attachments(mailbox: str, graph_message_id: str) -> list[dict]:
url = f"{GRAPH_URL}/users/{mailbox}/messages/{graph_message_id}/attachments"
try:
data = graph_get_json(url, {"$select": "id,name,contentType,size,isInline,contentId"})
return data.get("value", [])
except Exception as e:
logging.error("fetch_message_attachments failed [%s]: %s", graph_message_id, e)
return []
def fetch_attachment_content(mailbox: str, graph_message_id: str, attachment_id: str) -> Optional[bytes]:
url = f"{GRAPH_URL}/users/{mailbox}/messages/{graph_message_id}/attachments/{attachment_id}/$value"
try:
return graph_get_bytes(url)
except Exception as e:
logging.error("fetch_attachment_content failed [msg=%s att=%s]: %s", graph_message_id, attachment_id, e)
return None
# ─── Dedup + ukládání ─────────────────────────────────────────────────────────
def sha256(data: bytes) -> str:
return hashlib.sha256(data).hexdigest()
def safe_filename(name: str) -> str:
safe = "".join(c if c.isalnum() or c in "._- " else "_" for c in name).strip()
return safe or "attachment"
def resolve_filename(desired_name: str, att_dir: Path, hash_val: str, col_index) -> str:
"""Vrati nazev souboru pro ulozeni — resi kolize (stejny nazev, jiny hash)."""
existing = col_index.find_one({"filename": desired_name})
if existing:
if existing["_id"] == hash_val:
return desired_name # Dedup hit — stejny hash
# Kolize — hledej volny suffix
stem = Path(desired_name).stem
suffix = Path(desired_name).suffix
n = 2
while True:
candidate = f"{stem}_{n}{suffix}"
ex2 = col_index.find_one({"filename": candidate})
if not ex2 or ex2["_id"] == hash_val:
if not (att_dir / candidate).exists() or (ex2 and ex2["_id"] == hash_val):
return candidate
n += 1
return desired_name
def save_attachment(
content: bytes,
original_name: str,
mime_type: str,
mailbox: str,
att_dir: Path,
col_index,
) -> tuple[str, str, bool]:
"""
Ulozi prilohu s deduplikaci.
Vraci (hash, local_path, was_new).
"""
hash_val = sha256(content)
existing = col_index.find_one({"_id": hash_val})
if existing:
col_index.update_one({"_id": hash_val}, {"$inc": {"ref_count": 1}})
return hash_val, existing["local_path"], False
filename = resolve_filename(safe_filename(original_name), att_dir, hash_val, col_index)
file_path = att_dir / filename
file_path.write_bytes(content)
col_index.insert_one({
"_id": hash_val,
"filename": filename,
"local_path": filename,
"size_bytes": len(content),
"mime_type": mime_type,
"mailbox": mailbox,
"first_seen_at": datetime.now(timezone.utc).replace(tzinfo=None),
"ref_count": 1,
})
return hash_val, filename, True
# ─── MAIN ─────────────────────────────────────────────────────────────────────
def main():
ap = argparse.ArgumentParser(description=f"download_attachments v{SCRIPT_VERSION}")
ap.add_argument("--mailbox", required=True,
help="Emailova schranka (napr. ordinace@buzalkova.cz)")
ap.add_argument("--limit", type=int, default=0,
help="Zpracovat max N emailu (0 = vse)")
ap.add_argument("--force-recheck", action="store_true",
help="Znovu overi i emaily kde prilohy uz maji file_hash")
ap.add_argument("--no-indexes", action="store_true",
help="Nevytvorit indexy na attachments_index kolekci")
args = ap.parse_args()
mailbox = args.mailbox
att_dir = EMAILS_BASE_DIR / mailbox / "Attachments"
mongo_col = mailbox
start = datetime.now()
print(f"=== download_attachments v{SCRIPT_VERSION} ===")
print(f"Start: {start.strftime('%Y-%m-%d %H:%M:%S')}")
print(f"Schránka: {mailbox}")
print(f"Cilovy adresar: {att_dir}")
print(f"MongoDB: {MONGO_URI} -> {MONGO_DB}.{mongo_col}")
att_dir.mkdir(parents=True, exist_ok=True)
print(" Adresar OK")
print("\nPřipojuji se k Graph API...")
try:
get_token()
print(" Graph API OK")
except Exception as e:
print(f" CHYBA: {e}")
sys.exit(1)
client = MongoClient(MONGO_URI, serverSelectionTimeoutMS=5000)
try:
client.admin.command("ping")
print(" MongoDB OK")
except Exception as e:
print(f" CHYBA: MongoDB neni dostupna -- {e}")
sys.exit(1)
col_emails = client[MONGO_DB][mongo_col]
col_index = client[MONGO_DB][MONGO_COL_INDEX]
if not args.no_indexes:
col_index.create_index("filename")
col_index.create_index("mime_type")
col_index.create_index("mailbox")
# Dotaz
if args.force_recheck:
query = {"has_attachments": True}
else:
query = {
"has_attachments": True,
"attachments": {
"$elemMatch": {
"is_inline": False,
"file_hash": {"$exists": False},
}
}
}
total = col_emails.count_documents(query)
print(f"\nEmailu ke zpracovani: {total}")
if total == 0:
print("Neni co stahnout.")
client.close()
return
cursor = col_emails.find(query, {"_id": 1, "graph_id": 1, "subject": 1, "attachments": 1})
if args.limit:
cursor = cursor.limit(args.limit)
ok_count = 0
new_count = 0
dup_count = 0
err_count = 0
email_i = 0
batch = []
def flush():
if not batch:
return
try:
col_emails.bulk_write(batch, ordered=False)
except Exception as e:
logging.error("bulk_write: %s", e)
print(f" CHYBA bulk_write: {e}")
batch.clear()
for email_doc in cursor:
email_i += 1
email_id = email_doc["_id"]
graph_id = email_doc.get("graph_id", "")
subject = (email_doc.get("subject") or "")[:60]
att_list = email_doc.get("attachments") or []
real_atts = [a for a in att_list if not a.get("is_inline", False)]
if not real_atts:
continue
print(f"\n {email_i:>5}/{total} {subject}")
graph_atts = fetch_message_attachments(mailbox, graph_id)
graph_att_map = {a["name"]: a for a in graph_atts if not a.get("isInline", False)}
updated_atts = list(att_list)
email_ok = True
for i, att in enumerate(updated_atts):
if att.get("is_inline", False):
continue
if not args.force_recheck and att.get("file_hash"):
print(f" SKIP {att['filename']}")
continue
att_name = att.get("filename", "")
graph_att = graph_att_map.get(att_name)
if not graph_att:
for gname, ga in graph_att_map.items():
if att_name.lower() in gname.lower():
graph_att = ga
break
if not graph_att:
logging.error("attachment not found in Graph [email=%s att=%s]", email_id, att_name)
print(f" ERR {att_name} (nenalezeno v Graph)")
err_count += 1
email_ok = False
continue
content = fetch_attachment_content(mailbox, graph_id, graph_att["id"])
if content is None:
err_count += 1
email_ok = False
print(f" ERR {att_name} (stazeni selhalo)")
continue
mime_type = att.get("mime_type") or graph_att.get("contentType", "")
hash_val, local_path, was_new = save_attachment(
content, att_name, mime_type, mailbox, att_dir, col_index
)
updated_atts[i] = {**att, "file_hash": hash_val, "local_path": local_path}
if was_new:
new_count += 1
print(f" NEW {local_path} ({len(content):,} B)")
else:
dup_count += 1
print(f" DUP {att_name} -> {local_path}")
if email_ok:
ok_count += 1
batch.append(UpdateOne({"_id": email_id}, {"$set": {"attachments": updated_atts}}))
if len(batch) >= BATCH_SIZE:
flush()
if email_i % 100 == 0:
elapsed = (datetime.now() - start).total_seconds()
print(f" {''*60}")
print(f" Průběh: emaily={email_i}/{total} nove={new_count} dup={dup_count} err={err_count}")
print(f" {''*60}")
flush()
elapsed_total = (datetime.now() - start).total_seconds()
files_total = col_index.count_documents({})
size_total = sum(d.get("size_bytes", 0) for d in col_index.find({}, {"size_bytes": 1}))
print(f"\n{'='*52}")
print(f"Vysledek: emaily={ok_count} | nove={new_count} | dup={dup_count} | err={err_count}")
print(f"Souboru v indexu: {files_total} ({size_total / 1024 / 1024:.1f} MB)")
print(f"Celkovy cas: {int(elapsed_total//3600)}h {int((elapsed_total%3600)//60)}m {int(elapsed_total%60)}s")
print(f"\nKonec: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
if err_count:
print(f"Chyby logovany do: {LOG_FILE}")
client.close()
if __name__ == "__main__":
main()
-560
View File
@@ -1,560 +0,0 @@
"""
parse_emails_graph_v1.0.py
Nazev: parse_emails_graph_v1.0.py
Verze: 1.0
Datum: 2026-06-02
Autor: vladimir.buzalka
Popis:
Cte vsechny emaily ze schranky ordinace@buzalkova.cz primo pres
Microsoft Graph API a importuje je jako dokumenty do MongoDB.
Ze kazde zpravy extrahuje vsechny dostupne vlastnosti:
- predmet, odesilatel, prijemci (To/CC/BCC s typy)
- cas doruceni, odeslani, vytvoreni, modifikace (UTC)
- telo HTML (max 2 MB) + textovy preview
- prilohy (metadata: jmeno, velikost, MIME typ, inline flag)
- internet headers (SPF, DKIM, Received, X-*, ...)
- MAPI-ekvivalenty: dulezitost, priznak, konverzacni vlakno,
kategorie, In-Reply-To, References, ...
- navic: isRead, isDraft, folder_path, inferenceClassification
Prochazi VSECHNY slozky schranky rekurzivne (Inbox, Sent, Deleted,
archivni slozky, ...).
DB: emaily
Kolekce: ordinace@buzalkova.cz
_id: Internet Message-ID (nebo "graphid:<id>" jako fallback)
Bezpecne prerusit a opakovat:
- upsert podle _id — duplicity se automaticky prepisi
- --skip-existing nacte seznam hotovych _id z MongoDB a preskoci je
POZOR: Skript pouze CIST ze schranky — zadny zapis do schranky!
Spousteni:
python parse_emails_graph_v1.0.py # kompletni import
python parse_emails_graph_v1.0.py --limit 50 # test na prvnich 50
python parse_emails_graph_v1.0.py --skip-existing # pokracovani po preruseni
python parse_emails_graph_v1.0.py --folder Inbox # jen jedna slozka
python parse_emails_graph_v1.0.py --no-indexes # bez indexu na konci
Zavislosti:
msal, requests, pymongo, python-dateutil
Python 3.10+
Struktura dokumentu v MongoDB:
_id Internet Message-ID (nebo graphid: fallback)
graph_id Graph API message ID (pro pripadne dalsi operace)
subject predmet zpravy
normalized_subject predmet bez RE:/FW:/AW: prefixu
importance 0=nizka 1=normalni 2=vysoka
flag_status 0=bez priznaku 1=oznaceno 2=dokonceno
is_read bool — aktualni stav precteni ve schrance
is_draft bool
has_attachments bool
attachment_count int
inference_classification focused / other (Outlook AI trideni)
categories [str]
conversation_id Graph conversationId
conversation_index base64 conversationIndex
conversation_topic tema vlakna (z internet headers Thread-Topic)
in_reply_to Message-ID predchozi zpravy
internet_references [Message-ID] — cela historia vlakna
received_at datetime UTC
sent_at datetime UTC
created_at datetime UTC — cas vytvoreni zaznamu v M365
modified_at datetime UTC — cas posledni modifikace
folder_id Graph parentFolderId
folder_path cela cesta slozky (napr. Inbox/Subfolder)
sender.email emailova adresa odesilatele
sender.name zobrazovane jmeno odesilatele
to retezec To (joined)
cc retezec CC
bcc retezec BCC
recipients [{type, email, name}] — to/cc/bcc s typy
body_html HTML telo (max 2 MB)
body_preview textovy nahled (max 255 znaku z Graph)
attachments [{filename, size_bytes, mime_type,
content_id, is_inline}]
headers dict internet headers (lowercase_s_podtrzitky)
parsed_at datetime UTC — cas parsovani
Indexy:
received_at, sent_at, sender.email, graph_id (unique),
conversation_id, folder_path, has_attachments, categories,
importance, flag_status, is_read,
text_search (subject + body_preview + to + cc)
Historie verzi:
1.0 2026-06-02 Inicialni verze — Graph API jako zdroj
"""
import sys
import re
import logging
import argparse
import base64
from pathlib import Path
from datetime import datetime, timezone
from typing import Optional
import msal
import requests
from dateutil import parser as dtparser
from pymongo import MongoClient, UpdateOne, ASCENDING, TEXT
if hasattr(sys.stdout, "reconfigure"):
sys.stdout.reconfigure(encoding="utf-8", errors="replace")
# ─── KONFIGURACE ──────────────────────────────────────────────────────────────
GRAPH_TENANT_ID = "7d269944-37a4-43a1-8140-c7517dc426e9"
GRAPH_CLIENT_ID = "4b222bfd-78c9-4239-a53f-43006b3ed07f"
GRAPH_CLIENT_SECRET = "Txg8Q~MjhocuopxsJyJBhPmDfMxZ2r5WpTFj1dfk"
GRAPH_MAILBOX = "ordinace@buzalkova.cz"
GRAPH_URL = "https://graph.microsoft.com/v1.0"
MONGO_URI = "mongodb://192.168.1.76:27017"
MONGO_DB = "emaily"
MONGO_COL = "ordinace@buzalkova.cz"
BATCH_SIZE = 100
PAGE_SIZE = 50
LOG_FILE = Path(__file__).parent / "parse_emails_errors.log"
SCRIPT_VERSION = "1.0"
# ──────────────────────────────────────────────────────────────────────────────
logging.basicConfig(
filename=str(LOG_FILE),
level=logging.ERROR,
format="%(asctime)s | %(message)s",
datefmt="%Y-%m-%d %H:%M:%S",
encoding="utf-8",
)
IMPORTANCE_MAP = {"low": 0, "normal": 1, "high": 2}
FLAG_STATUS_MAP = {"notFlagged": 0, "flagged": 1, "complete": 2}
RE_SUBJECT = re.compile(r"^(RE|FW|AW|SV|VS|TR|WG|odpov[eě]d[ťt]|fwd?)[:\s]+", re.IGNORECASE)
MSG_SELECT = (
"id,internetMessageId,subject,bodyPreview,body,"
"importance,isRead,isDraft,hasAttachments,"
"receivedDateTime,sentDateTime,createdDateTime,lastModifiedDateTime,"
"sender,from,toRecipients,ccRecipients,bccRecipients,replyTo,"
"conversationId,conversationIndex,parentFolderId,"
"categories,flag,inferenceClassification,internetMessageHeaders"
)
# ─── Graph API helpers ────────────────────────────────────────────────────────
_graph_token: Optional[str] = None
def get_token() -> str:
global _graph_token
app = msal.ConfidentialClientApplication(
GRAPH_CLIENT_ID,
authority=f"https://login.microsoftonline.com/{GRAPH_TENANT_ID}",
client_credential=GRAPH_CLIENT_SECRET,
)
result = app.acquire_token_for_client(scopes=["https://graph.microsoft.com/.default"])
if "access_token" not in result:
raise RuntimeError(f"Graph auth failed: {result}")
_graph_token = result["access_token"]
return _graph_token
def graph_get(url: str, params: dict = None) -> dict:
global _graph_token
if not _graph_token:
get_token()
for attempt in range(2):
r = requests.get(url, headers={"Authorization": f"Bearer {_graph_token}"}, params=params, timeout=30)
if r.status_code == 401:
get_token()
continue
r.raise_for_status()
return r.json()
raise RuntimeError(f"Graph GET failed after retry: {url}")
def get_all_folders(parent_id: str = None, parent_path: str = "") -> list[dict]:
"""Rekurzivne nacte vsechny slozky schranky. Vraci [{id, path}]."""
if parent_id is None:
url = f"{GRAPH_URL}/users/{GRAPH_MAILBOX}/mailFolders"
else:
url = f"{GRAPH_URL}/users/{GRAPH_MAILBOX}/mailFolders/{parent_id}/childFolders"
folders = []
params = {"$top": 100, "$select": "id,displayName,childFolderCount"}
while url:
data = graph_get(url, params)
for f in data.get("value", []):
path = f"{parent_path}/{f['displayName']}".lstrip("/")
folders.append({"id": f["id"], "path": path})
if f.get("childFolderCount", 0) > 0:
folders.extend(get_all_folders(f["id"], path))
url = data.get("@odata.nextLink")
params = None
return folders
def iter_folder_messages(folder_id: str):
"""Generator: vraci zpravy ze slozky po strankach."""
url = f"{GRAPH_URL}/users/{GRAPH_MAILBOX}/mailFolders/{folder_id}/messages"
params = {"$top": PAGE_SIZE, "$select": MSG_SELECT, "$expand": "attachments"}
while url:
data = graph_get(url, params)
for msg in data.get("value", []):
yield msg
url = data.get("@odata.nextLink")
params = None
# ─── Pomocné funkce ───────────────────────────────────────────────────────────
def parse_date(raw) -> Optional[datetime]:
if raw is None:
return None
if isinstance(raw, datetime):
if raw.tzinfo:
return raw.astimezone(timezone.utc).replace(tzinfo=None)
return raw
try:
dt = dtparser.parse(str(raw))
if dt.tzinfo:
return dt.astimezone(timezone.utc).replace(tzinfo=None)
return dt
except Exception:
return None
def normalize_subject(subject: str) -> str:
s = subject.strip()
while True:
m = RE_SUBJECT.match(s)
if not m:
break
s = s[m.end():].strip()
return s
def parse_headers(raw_headers: list) -> dict:
result = {}
for h in raw_headers:
k = h["name"].lower().replace("-", "_")
v = h["value"]
if k in result:
existing = result[k]
if isinstance(existing, list):
existing.append(v)
else:
result[k] = [existing, v]
else:
result[k] = v
return result
def format_recipients(lst: list) -> str:
return "; ".join(
f'{r["emailAddress"].get("name", "")} <{r["emailAddress"].get("address", "")}>'.strip()
for r in lst
)
# ─── Hlavní extrakce ─────────────────────────────────────────────────────────
def extract_message(msg: dict, folder_path: str) -> Optional[dict]:
try:
# _id
mid = (msg.get("internetMessageId") or "").strip()
if not mid:
mid = f"graphid:{msg['id']}"
subject = msg.get("subject") or ""
norm_subject = normalize_subject(subject)
# tělo
body_html = None
body_preview = msg.get("bodyPreview") or ""
body = msg.get("body", {})
if body.get("contentType") == "html":
content = body.get("content") or ""
body_html = content if len(content) <= 2 * 1024 * 1024 else content[:2 * 1024 * 1024]
elif body.get("contentType") == "text":
body_preview = (body.get("content") or "")[:2000]
# odesílatel
sender_ea = (msg.get("from") or msg.get("sender") or {}).get("emailAddress", {})
sender_email = sender_ea.get("address", "")
sender_name = sender_ea.get("name", "")
# příjemci
to_list = msg.get("toRecipients", [])
cc_list = msg.get("ccRecipients", [])
bcc_list = msg.get("bccRecipients", [])
recipients = (
[{"type": "to", "email": r["emailAddress"].get("address",""), "name": r["emailAddress"].get("name","")} for r in to_list] +
[{"type": "cc", "email": r["emailAddress"].get("address",""), "name": r["emailAddress"].get("name","")} for r in cc_list] +
[{"type": "bcc", "email": r["emailAddress"].get("address",""), "name": r["emailAddress"].get("name","")} for r in bcc_list]
)
# příznaky
importance = IMPORTANCE_MAP.get(msg.get("importance", "normal"), 1)
flag_status = FLAG_STATUS_MAP.get((msg.get("flag") or {}).get("flagStatus", "notFlagged"), 0)
# internet headers
raw_headers = msg.get("internetMessageHeaders") or []
headers = parse_headers(raw_headers)
in_reply_to = headers.get("in_reply_to", "")
if isinstance(in_reply_to, list):
in_reply_to = in_reply_to[0]
refs_raw = headers.get("references", "")
if isinstance(refs_raw, list):
refs_raw = " ".join(refs_raw)
internet_refs = [r.strip() for r in refs_raw.split() if r.strip()] if refs_raw else []
conv_topic = headers.get("thread_topic", "")
if isinstance(conv_topic, list):
conv_topic = conv_topic[0]
# conversation index
conv_index = ""
ci_raw = msg.get("conversationIndex")
if ci_raw:
try:
conv_index = base64.b64encode(base64.b64decode(ci_raw)).decode()
except Exception:
conv_index = ci_raw
# přílohy (jen metadata, bez obsahu)
attachments = []
for att in msg.get("attachments") or []:
fname = att.get("name") or ""
if not fname:
continue
attachments.append({
"filename": fname,
"size_bytes": att.get("size", 0),
"mime_type": att.get("contentType", "application/octet-stream"),
"content_id": att.get("contentId"),
"is_inline": att.get("isInline", False),
})
return {
"_id": mid,
"graph_id": msg["id"],
"subject": subject,
"normalized_subject": norm_subject,
"importance": importance,
"flag_status": flag_status,
"is_read": msg.get("isRead", False),
"is_draft": msg.get("isDraft", False),
"has_attachments": msg.get("hasAttachments", False),
"attachment_count": len(attachments),
"inference_classification": msg.get("inferenceClassification", ""),
"categories": msg.get("categories") or [],
"conversation_id": msg.get("conversationId", ""),
"conversation_index": conv_index,
"conversation_topic": conv_topic,
"in_reply_to": in_reply_to,
"internet_references": internet_refs,
"received_at": parse_date(msg.get("receivedDateTime")),
"sent_at": parse_date(msg.get("sentDateTime")),
"created_at": parse_date(msg.get("createdDateTime")),
"modified_at": parse_date(msg.get("lastModifiedDateTime")),
"folder_id": msg.get("parentFolderId", ""),
"folder_path": folder_path,
"sender": {
"email": sender_email,
"name": sender_name,
},
"to": format_recipients(to_list),
"cc": format_recipients(cc_list),
"bcc": format_recipients(bcc_list),
"recipients": recipients,
"body_html": body_html,
"body_preview": body_preview,
"attachments": attachments,
"headers": headers,
"parsed_at": datetime.now(timezone.utc).replace(tzinfo=None),
}
except Exception as e:
logging.error("extract_message failed [%s]: %s", msg.get("id", "?"), e)
return None
# ─── MongoDB indexy ───────────────────────────────────────────────────────────
def create_indexes(col):
print(" Vytvarim indexy...")
col.create_index([("received_at", ASCENDING)])
col.create_index([("sent_at", ASCENDING)])
col.create_index([("sender.email", ASCENDING)])
col.create_index([("graph_id", ASCENDING)], unique=True, sparse=True)
col.create_index([("conversation_id", ASCENDING)])
col.create_index([("folder_path", ASCENDING)])
col.create_index([("has_attachments", ASCENDING)])
col.create_index([("categories", ASCENDING)])
col.create_index([("importance", ASCENDING)])
col.create_index([("flag_status", ASCENDING)])
col.create_index([("is_read", ASCENDING)])
col.create_index([
("subject", TEXT),
("body_preview", TEXT),
("to", TEXT),
("cc", TEXT),
], name="text_search", default_language="none")
print(" Indexy hotovy.")
# ─── MAIN ─────────────────────────────────────────────────────────────────────
def main():
ap = argparse.ArgumentParser(description=f"parse_emails_graph v{SCRIPT_VERSION}")
ap.add_argument("--limit", type=int, default=0,
help="Zpracovat max N zprav (0 = vse)")
ap.add_argument("--skip-existing", action="store_true",
help="Preskocit zpravy ktere jiz jsou v MongoDB")
ap.add_argument("--folder", default="",
help="Zpracovat jen slozku se zadanym nazvem (napr. Inbox)")
ap.add_argument("--no-indexes", action="store_true",
help="Nevytvorit indexy na konci")
args = ap.parse_args()
start = datetime.now()
print(f"=== parse_emails_graph v{SCRIPT_VERSION} ===")
print(f"Start: {start.strftime('%Y-%m-%d %H:%M:%S')}")
print(f"Schránka: {GRAPH_MAILBOX}")
print(f"MongoDB: {MONGO_URI} -> {MONGO_DB}.{MONGO_COL}")
# Graph token
print("\nPřipojuji se k Graph API...")
try:
get_token()
print(" Graph API OK")
except Exception as e:
print(f" CHYBA: {e}")
sys.exit(1)
# MongoDB
client = MongoClient(MONGO_URI, serverSelectionTimeoutMS=5000)
try:
client.admin.command("ping")
print(" MongoDB OK")
except Exception as e:
print(f" CHYBA: MongoDB neni dostupna -- {e}")
sys.exit(1)
col = client[MONGO_DB][MONGO_COL]
# Skip existing
existing: set = set()
if args.skip_existing:
print(" Nacitam existujici zaznamy z MongoDB...")
existing = set(col.distinct("_id"))
print(f" {len(existing)} jiz importovano")
# Slozky
print("\nNacitam seznam slozek...")
all_folders = get_all_folders()
if args.folder:
all_folders = [f for f in all_folders if args.folder.lower() in f["path"].lower()]
print(f" Slozek ke zpracovani: {len(all_folders)}")
for f in all_folders:
print(f" {f['path']}")
# Import
batch = []
ok_count = 0
err_count = 0
skip_count = 0
total_i = 0
def flush():
if not batch:
return
try:
col.bulk_write(batch, ordered=False)
except Exception as e:
logging.error("bulk_write: %s", e)
print(f" CHYBA bulk_write: {e}")
batch.clear()
print()
for folder in all_folders:
print(f"--- Složka: {folder['path']} ---")
folder_count = 0
for msg in iter_folder_messages(folder["id"]):
if args.limit and total_i >= args.limit:
break
mid = (msg.get("internetMessageId") or "").strip() or f"graphid:{msg['id']}"
if mid in existing:
skip_count += 1
total_i += 1
continue
doc = extract_message(msg, folder["path"])
total_i += 1
folder_count += 1
if doc is None:
err_count += 1
else:
batch.append(UpdateOne({"_id": doc["_id"]}, {"$set": doc}, upsert=True))
ok_count += 1
if len(batch) >= BATCH_SIZE:
flush()
status = "ERR " if doc is None else "OK "
subject_str = (doc.get("subject") or "")[:60] if doc else "?"
sender_str = (doc.get("sender", {}).get("email") or "")[:40] if doc else "?"
print(f" {total_i:>6} {status} {subject_str:<60} {sender_str}")
if total_i % 500 == 0:
elapsed = (datetime.now() - start).total_seconds()
rate = total_i / elapsed if elapsed > 0 else 0
print(f" {''*80}")
print(f" Průběh: ok={ok_count} skip={skip_count} err={err_count} {rate:.1f} msg/s")
print(f" {''*80}")
flush()
print(f"{folder_count} zprav ze slozky {folder['path']}")
if args.limit and total_i >= args.limit:
break
elapsed_total = (datetime.now() - start).total_seconds()
print(f"\n{'='*52}")
print(f"Vysledek: ok={ok_count} | skip={skip_count} | err={err_count}")
print(f"Celkovy cas: {int(elapsed_total//3600)}h {int((elapsed_total%3600)//60)}m {int(elapsed_total%60)}s")
print(f"Dokumentu v kolekci: {col.count_documents({})}")
if not args.no_indexes:
print()
create_indexes(col)
print(f"\nKonec: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
if err_count:
print(f"Chyby logovany do: {LOG_FILE}")
client.close()
if __name__ == "__main__":
main()
+121 -39
View File
@@ -39,53 +39,138 @@ c.close()
## Volume mounty
| Host (Unraid) | Kontejner | Popis |
|-----------------------|-------------------|------------------------------|
| `/mnt/user/Scripts` | `/scripts` | Skripty, logy — working dir |
| `/mnt/user/JNJEMAILS` | `/mnt/JNJEMAILS` | .msg soubory emailů (JNJ) |
| Host (Unraid) | Kontejner | Popis |
|-----------------------|-------------------|----------------------------------|
| `/mnt/user/Scripts` | `/scripts` | Skripty, logy — working dir |
| `/mnt/user/Emails` | `/mnt/Emails` | Stažené přílohy `<schránka>/Attachments/` |
---
## Spouštění skriptů
```bash
# Interaktivně (vidíš výstup):
docker exec -it python-runner python /scripts/parse_emails_tower_v1.1.py --limit 50 --no-indexes
# Na pozadí (log do souboru):
docker exec -d python-runner bash -c \
"python /scripts/parse_emails_tower_v1.1.py > /scripts/parse_emails.log 2>&1"
# Pokračování po přerušení (skip hotových):
docker exec -d python-runner bash -c \
"python /scripts/parse_emails_tower_v1.1.py --skip-existing > /scripts/parse_emails.log 2>&1"
# Sledování průběhu:
docker exec -it python-runner tail -f /scripts/parse_emails.log
```
> Skripty čtou emaily **přímo přes Microsoft Graph API** — lokální `.msg` soubory už nejsou potřeba.
---
## Aktuální skripty v /scripts
| Soubor | Popis |
|-------------------------------|------------------------------------------------|
| `parse_emails_tower_v1.1.py` | Import .msg → MongoDB (db: emaily, kolekce: vbuzalka@its.jnj.com) |
| `parse_emails_tower_v1.1.md` | Dokumentace ke skriptu |
| `parse_emails.log` | Log průběhu importu |
| `parse_emails_errors.log` | Log chyb (soubory které selhaly) |
| Soubor | Popis |
|---------------------------------|--------------------------------------------------------------|
| `parse_emails_graph_v1.3.py` | Import emailů ze schránky přes Graph API → MongoDB |
| `download_attachments_v1.3.py` | Stažení skutečných příloh emailů (Graph API) → `/mnt/Emails` |
| `python_runner.md` | Tato dokumentace |
| `parse_emails_errors.log` | Log chyb (soubory/zprávy které selhaly) |
Lokální protějšek: `EmailsImport/parse_emails_v1.0.py` — identický kód, liší se jen cestou
(`\\tower\JNJEMAILS` SMB vs. `/mnt/JNJEMAILS` lokální mount) a verzí hlavičky.
> **POZOR:** oba skripty pouze **čtou** ze schránky — žádný zápis do schránky.
---
## Microsoft Graph API — konfigurace (v obou skriptech)
| Parametr | Hodnota |
|-----------------|----------------------------------------|
| Graph URL | `https://graph.microsoft.com/v1.0` |
| Tenant ID | `7d269944-37a4-43a1-8140-c7517dc426e9` |
| Client ID | `4b222bfd-78c9-4239-a53f-43006b3ed07f` |
| Auth | client credentials (msal) |
| MongoDB | Hodnota |
|-----------------|----------------------------------------|
| URI | `mongodb://192.168.1.76:27017` |
| DB | `emaily` |
| Kolekce emailů | `<mailbox>` (např. `ordinace@buzalkova.cz`) |
| Index příloh | `attachments_index` |
---
## 1) parse_emails_graph_v1.3.py — import emailů → MongoDB
Čte **všechny složky** schránky rekurzivně (Inbox, Sent, Deleted, archivy …) přes
Graph API a importuje každou zprávu jako dokument do MongoDB. `_id` = Internet
Message-ID (fallback `graphid:<id>`). Upsert → bezpečné přerušit a opakovat.
Z každé zprávy extrahuje: předmět, odesílatel, příjemci To/CC/BCC, časy (UTC),
HTML tělo (max 2 MB) + text preview, přílohy (metadata + `graph_att_id`),
internet headers (SPF/DKIM/Received/X-*), MAPI-ekvivalenty (důležitost, příznak,
konverzační vlákno, kategorie, In-Reply-To, References), `isRead`, `isDraft`,
`folder_path`, `inferenceClassification`.
```bash
# První import (vše):
docker exec -it python-runner python /scripts/parse_emails_graph_v1.3.py --mailbox ordinace@buzalkova.cz
# Test na 50 zprávách bez indexů:
docker exec -it python-runner python /scripts/parse_emails_graph_v1.3.py --mailbox ordinace@buzalkova.cz --limit 50 --no-indexes
# Pravidelný sync na pozadí (log do souboru):
docker exec -d python-runner bash -c "python /scripts/parse_emails_graph_v1.3.py --mailbox ordinace@buzalkova.cz --mode sync > /scripts/parse_emails.log 2>&1"
```
> **`-d` = detached:** příkaz se hned vrátí a skript běží dál v kontejneru i po
> zavření terminálu / odpojení SSH. Bez `-d` (resp. s `-it`) skript skončí ve chvíli,
> kdy se spojení zavře. Pro dlouhé běhy vždy pouštěj s `-d` a logem do souboru,
> průběh pak sleduj přes `tail -f` (viz [Sledování průběhu](#sledování-průběhu)).
### Parametry
| Parametr | Popis |
|---|---|
| `--mailbox` | **Povinný.** Schránka (e-mail), zároveň název kolekce v MongoDB. |
| `--mode` | `full` (výchozí — plný upsert), `new-only` (jen nové), `sync` (existující: aktualizuje `is_read`/`flag_status`/`categories`/`modified_at`/`folder_path`; nové importuje celé — ideální pro pravidelné spouštění). |
| `--folder` | Import jen jedné složky (např. `Inbox`). |
| `--limit N` | Zpracuje jen prvních N zpráv (test). |
| `--no-indexes` | Nevytváří indexy na konci. |
---
## 2) download_attachments_v1.3.py — stažení příloh → /mnt/Emails
Stahuje skutečné přílohy (`is_inline=False`) všech emailů z MongoDB přes Graph API
do `/mnt/Emails/<schránka>/Attachments/`. Primárně přes `graph_att_id` (přímé ID),
name-matching jako fallback pro staré emaily.
Deduplikace podle **SHA256** obsahu:
- stejný hash → soubor už existuje → přeskočí
- kolize názvu (stejný název, jiný hash) → `faktura_2.pdf`, `faktura_3.pdf`
Po uložení aktualizuje MongoDB: každá příloha dostane `file_hash` + `local_path`;
kolekce `emaily.attachments_index` (`_id`=hash, filename, path, size_bytes,
mime_type, mailbox, first_seen_at, ref_count). Emaily kde mají všechny přílohy
`file_hash` se přeskočí → bezpečné opakovat.
```bash
# Interaktivně (vidíš výstup, skončí zavřením terminálu):
docker exec -it python-runner python /scripts/download_attachments_v1.3.py --mailbox ordinace@buzalkova.cz
# Na pozadí (běží dál i po zavření terminálu, log do souboru):
docker exec -d python-runner bash -c "python /scripts/download_attachments_v1.3.py --mailbox ordinace@buzalkova.cz > /scripts/download_attachments.log 2>&1"
```
> `-d` = detached — stejné chování jako u skriptu výše (viz poznámka v sekci 1).
### Parametry
| Parametr | Popis |
|---|---|
| `--mailbox` | **Povinný.** Schránka (e-mail) = kolekce v MongoDB. |
| `--limit N` | Zpracuje jen prvních N emailů (test). |
| `--force-recheck` | Znovu ověří i už stažené přílohy. |
| `--no-indexes` | Nevytváří indexy na konci. |
---
## Sledování průběhu
```bash
docker exec -it python-runner tail -f /scripts/parse_emails.log
```
---
## Nainstalované Python balíčky
```
extract-msg 0.55.0
msal (Graph API auth)
requests
pymongo 4.17.0
python-dateutil 2.9.0.post0
extract-msg 0.55.0
cryptography 48.0.0
beautifulsoup4 4.13.5
oletools 0.60.2
@@ -112,11 +197,8 @@ docker exec python-runner pip install <balicek>
---
## Logika parse_emails (oba skripty)
## Historie
- Čte všechny `.msg` soubory z MSGS_DIR
- Extrahuje: předmět, odesílatel, příjemci (To/CC/BCC), tělo (text+HTML), přílohy, internet headers, všechny raw MAPI properties
- Ukládá do MongoDB: `emaily``vbuzalka@its.jnj.com`
- `_id` = Internet Message-ID (nebo `filename:<stem>` jako fallback)
- Upsert → bezpečné opakování, `--skip-existing` pro pokračování
- Indexy: received_at, sent_at, sender.email, filename (unique), full-text (subject+body+to+cc)
| Datum | Změna |
|---|---|
| 2026-06-02 | Přechod z `.msg` souborů na Microsoft Graph API. Skript `parse_emails_tower_v1.1.py` (import lokálních `.msg`) nahrazen `parse_emails_graph_v1.3.py`; přidán `download_attachments_v1.3.py`. Staré verze v `Trash/`. |
+2
View File
@@ -3,6 +3,8 @@
- [Pracovat v maintree](feedback_worktree.md) — vždy pracuj v `U:/janssen/`, ne ve worktree větvích
- [Projekt Covance UCO3001](project_covance.md) — report vzorků studie 77242113UCO3001, skript `create_report.py`, zdroj + logika OK statusů
- [EDC import do MongoDB](project_edc_mongo.md) — skript `medidata/edc_import.py`, import Data Listing + QueryDetails CSV do MongoDB (192.168.1.76), kolekce `queries` + `queries_snapshots` pro tracking vývoje queries v čase
- [IWRS notifikace v Mongo](project_iwrs_mongo.md) — parser `IWRS/Patients/parse_notifications_to_mongo.py` čte texty notifikací z MySQL a ukládá strukturovaná data do `studie.iwrs` (lot, expirace, clinical response, audit trail)
- [Dropbox file transfer](project_dropbox_file_transfer.md) — přenos souborů z JNJ PC do Dropboxu přes msgreceiver kontejner na Unraidu
- [Graph email import](project_graph_email_import.md) — import JNJ emailů do schránky vladimir.buzalka@buzalka.cz přes Graph API
- [Memory sync přes Giteu](setup_memory_sync.md) — paměť je v `claude-memory/` v janssen repu, junction + git push synchronizuje mezi PC
- [Claude Code learning path](project_claude_learning.md) — Level 2 Intermediate, mezery: Skills/Subagenty/Hooks/Print mode, tutoriál v `claude-howto/`