Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[34588f42] Keine Zusammenfassung angegeben.

Browse Source 
Keine Zusammenfassung angegeben.
This commit is contained in:
Floke
2026-04-18 13:58:53 +00:00
parent 995b3ff829
commit e8ebac4d8e
3 changed files with 76 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
fotograf-de-scraper/backend/main.py
View File

@@ -141,120 +141,6 @@ def get_logo_base64():
logger.warning(f"Logo file not found at {logo_path}")
return None
def sync_job_participants(job_id: str, account_type: str, db: Session):
logger.info(f"Syncing participants for job {job_id} ({account_type})")
username = os.getenv(f"{account_type.upper()}_USER")
password = os.getenv(f"{account_type.upper()}_PW")
with tempfile.TemporaryDirectory() as temp_dir:
driver = setup_driver(download_path=temp_dir)
try:
if not login(driver, username, password):
raise Exception("Login failed during sync.")
# Navigate to job names list
job_url = f"https://app.fotograf.de/config_jobs_settings/index/{job_id}"
driver.get(job_url)
wait = WebDriverWait(driver, 20)
personen_tab = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "[data-qa-id='link:photo-jobs-tabs-names_list']")))
driver.execute_script("arguments[0].click();", personen_tab)
export_btn = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, SELECTORS["export_dropdown"])))
driver.execute_script("arguments[0].click();", export_btn)
time.sleep(1)
csv_btn = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, SELECTORS["export_csv_link"])))
driver.execute_script("arguments[0].click();", csv_btn)
# Wait for download
csv_file = None
for _ in range(30):
files = [f for f in os.listdir(temp_dir) if f.endswith('.csv')]
if files:
csv_file = os.path.join(temp_dir, files[0])
break
time.sleep(1)
if not csv_file:
raise Exception("CSV download timeout during sync.")
# Parse CSV
df = None
for sep in [";", ","]:
try:
df = pd.read_csv(csv_file, sep=sep, encoding="utf-8-sig")
if len(df.columns) > 1: break
except: continue
if df is None:
df = pd.read_csv(csv_file, sep=";", encoding="latin1")
# Clean columns
df.columns = df.columns.str.strip().str.replace("\"", "")
# Map columns - based on user feedback
# Expected columns: Child ID, Email der Eltern (1), Vorname Eltern (1), Nachname Eltern (1), Vorname Kind, Zugangscode (1), Logins (1), Bestellungen
def get_col(df, patterns):
for p in patterns:
for col in df.columns:
if p.lower() in col.lower():
return col
return None
col_child_id = get_col(df, ["Child ID"])
col_email = get_col(df, ["Email der Eltern", "E-Mail der Eltern"])
col_parent_vn = get_col(df, ["Vorname Eltern", "Parent First Name"])
col_parent_nn = get_col(df, ["Nachname Eltern", "Parent Last Name"])
col_child_vn = get_col(df, ["Vorname Kind", "Child First Name"])
col_child_nn = get_col(df, ["Nachname Kind", "Child Last Name"])
col_code = get_col(df, ["Zugangscode", "Access Code"])
col_group = get_col(df, ["Gruppe", "Klasse", "Group", "Class"])
col_logins = get_col(df, ["Logins"])
col_orders = get_col(df, ["Bestellungen", "Orders"])
# Delete old entries for this job
db.query(JobParticipant).filter(JobParticipant.job_id == job_id).delete()
added = 0
for _, row in df.iterrows():
try:
logins_val = 0
try: logins_val = int(row[col_logins]) if col_logins and pd.notna(row[col_logins]) else 0
except: pass
orders_val = 0
if col_orders and pd.notna(row[col_orders]):
val = str(row[col_orders]).lower()
if val and val != "0" and val != "nein" and val != "false":
orders_val = 1
participant = JobParticipant(
job_id=job_id,
child_id=str(row[col_child_id]) if col_child_id and pd.notna(row[col_child_id]) else None,
vorname_kind=str(row[col_child_vn]) if col_child_vn and pd.notna(row[col_child_vn]) else None,
nachname_kind=str(row[col_child_nn]) if col_child_nn and pd.notna(row[col_child_nn]) else None,
vorname_eltern=str(row[col_parent_vn]) if col_parent_vn and pd.notna(row[col_parent_vn]) else None,
nachname_eltern=str(row[col_parent_nn]) if col_parent_nn and pd.notna(row[col_parent_nn]) else None,
email_eltern=str(row[col_email]).strip().lower() if col_email and pd.notna(row[col_email]) else None,
zugangscode=str(row[col_code]) if col_code and pd.notna(row[col_code]) else None,
gruppe=str(row[col_group]) if col_group and pd.notna(row[col_group]) else None,
logins=logins_val,
has_orders=orders_val
)
db.add(participant)
added += 1
except Exception as e:
logger.warning(f"Error adding participant row: {e}")
db.commit()
logger.info(f"Sync complete. {added} participants stored for job {job_id}")
return added
finally:
driver.quit()
def generate_pdf_from_csv(csv_path: str, institution: str, date_info: str, list_type: str, output_path: str):
logger.info(f"Generating PDF for {institution} from {csv_path}")
df = None
@@ -1193,6 +1079,30 @@ def sync_participants(job_id: str, account_type: str, db: Session):
finally:
driver.quit()
@app.get("/api/jobs/{job_id}/fast-stats")
async def get_fast_stats(job_id: str, db: Session = Depends(get_db)):
participants = db.query(JobParticipant).filter(JobParticipant.job_id == job_id).all()
if not participants:
return []
groups = {}
for p in participants:
g_name = p.gruppe or "Unbekannt"
if g_name not in groups:
groups[g_name] = {
"Album": g_name,
"Kinder_insgesamt": 0,
"Kinder_mit_Käufen": 0,
"Kinder_Alle_Bilder_gekauft": 0
}
groups[g_name]["Kinder_insgesamt"] += 1
if p.has_orders:
groups[g_name]["Kinder_mit_Käufen"] += 1
statistics = list(groups.values())
statistics.sort(key=lambda x: x["Album"])
return statistics
@app.post("/api/jobs/{job_id}/sync-participants")
async def sync_participants_api(job_id: str, account_type: str, db: Session = Depends(get_db)):
try: