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

bugfix

Browse Source
This commit is contained in:
Floke
2025-04-16 14:42:01 +00:00
parent 1e2205e2ce
commit 567eceded3
1 changed files with 22 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
brancheneinstufung.py
View File

@@ -2212,6 +2212,7 @@ def _process_batch(sheet, batches, row_numbers):
# time.sleep(Config.RETRY_DELAY) # Entfernt # time.sleep(Config.RETRY_DELAY) # Entfernt
# Komplette Funktion process_website_batch (prüft jetzt Timestamp AT mit erzwungenem Debugging) # Komplette Funktion process_website_batch (prüft jetzt Timestamp AT mit erzwungenem Debugging)
# Komplette Funktion process_website_batch (mit Vereinfachung und explizitem Skip-Log)
def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index_in_sheet): def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index_in_sheet):
""" """
Batch-Prozess für Website-Scraping. Lädt Daten neu, prüft für jede Zeile Batch-Prozess für Website-Scraping. Lädt Daten neu, prüft für jede Zeile
@@ -2220,23 +2221,18 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
""" """
debug_print(f"Starte Website-Scraping (Batch) für Zeilen {start_row_index_in_sheet} bis {end_row_index_in_sheet}...") debug_print(f"Starte Website-Scraping (Batch) für Zeilen {start_row_index_in_sheet} bis {end_row_index_in_sheet}...")
# --- NEU: Daten explizit neu laden ---
if not sheet_handler.load_data(): if not sheet_handler.load_data():
debug_print("FEHLER beim Laden der Daten in process_website_batch.") debug_print("FEHLER beim Laden der Daten in process_website_batch.")
return return
all_data = sheet_handler.get_all_data_with_headers() all_data = sheet_handler.get_all_data_with_headers()
# --- Ende Daten neu laden ---
if not all_data or len(all_data) <= 5: if not all_data or len(all_data) <= 5:
debug_print("FEHLER/WARNUNG: Keine Daten zum Verarbeiten in process_website_batch gefunden.") debug_print("FEHLER/WARNUNG: Keine Daten zum Verarbeiten in process_website_batch gefunden.")
return return
sheet = sheet_handler.sheet sheet = sheet_handler.sheet
# Hole Indizes
timestamp_col_key = "Website Scrape Timestamp" timestamp_col_key = "Website Scrape Timestamp"
timestamp_col_index = COLUMN_MAP.get(timestamp_col_key) timestamp_col_index = COLUMN_MAP.get(timestamp_col_key)
website_col_idx = COLUMN_MAP.get("CRM Website") # Korrigiert zu idx website_col_idx = COLUMN_MAP.get("CRM Website")
rohtext_col_idx = COLUMN_MAP.get("Website Rohtext") rohtext_col_idx = COLUMN_MAP.get("Website Rohtext")
summary_col_idx = COLUMN_MAP.get("Website Zusammenfassung") summary_col_idx = COLUMN_MAP.get("Website Zusammenfassung")
version_col_idx = COLUMN_MAP.get("Version") version_col_idx = COLUMN_MAP.get("Version")
@@ -2262,27 +2258,38 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
row = all_data[row_index_in_list] row = all_data[row_index_in_list]
# --- WIEDER AKTIVIERT: Timestamp-Prüfung für jede Zeile (AT) --- # --- Timestamp-Prüfung für jede Zeile (AT) ---
ts_value_at = "INDEX_FEHLER" ts_value_at = "INDEX_FEHLER"
ts_at_is_set = False should_skip = False # Standardmäßig nicht überspringen
if len(row) > timestamp_col_index: if len(row) > timestamp_col_index:
ts_value_at = row[timestamp_col_index] ts_value_at = row[timestamp_col_index]
ts_at_is_set = bool(str(ts_value_at).strip()) # Vereinfachte Prüfung: Ist der String (nach strip) NICHT leer?
# Debug Log if str(ts_value_at).strip():
log_debug = (i < start_row_index_in_sheet + 5 or i > end_row_index_in_sheet - 5 or i % 500 == 0) should_skip = True
if log_debug:
debug_print(f"Zeile {i} (Website Check): Prüfe Timestamp {ts_col_letter} (Index {timestamp_col_index}). Rohwert='{ts_value_at}', Strip='{str(ts_value_at).strip()}', Überspringen? -> {ts_at_is_set}")
if ts_at_is_set: # Debug Log (zeigt jetzt die 'should_skip' Variable)
log_debug = (i < start_row_index_in_sheet + 5 or i > end_row_index_in_sheet - 5 or i % 500 == 0 or i in range(2122, 2132)) # Zeige es für die Problemzone
if log_debug:
debug_print(f"Zeile {i} (Website Check): Prüfe Timestamp {ts_col_letter}. Rohwert='{ts_value_at}'. Überspringen? -> {should_skip}")
if should_skip:
# --- NEU: Explizites Logging VOR dem continue ---
debug_print(f"Zeile {i}: *** WIRD ÜBERSPRUNGEN (Timestamp AT vorhanden) ***")
skipped_count += 1 skipped_count += 1
continue continue # Springe zur nächsten Iteration
# --- Ende Timestamp-Prüfung --- # --- Ende Timestamp-Prüfung ---
# WENN die Funktion hier ankommt, DARF 'should_skip' NICHT True gewesen sein.
debug_print(f"Zeile {i}: Timestamp AT nicht vorhanden oder leer. Verarbeitung wird gestartet.")
# (Rest der Logik zum Scrapen und Updaten wie zuvor)
website_url = row[website_col_idx] if len(row) > website_col_idx else "" website_url = row[website_col_idx] if len(row) > website_col_idx else ""
if not website_url or website_url.strip().lower() == "k.a.": if not website_url or website_url.strip().lower() == "k.a.":
# debug_print(f"Zeile {i}: Kein gültiger Website-Eintrag.") # Weniger Lärm
skipped_url_count += 1 skipped_url_count += 1
continue continue
debug_print(f"Zeile {i}: Verarbeite Website {website_url}...") # Loggen, dass es wirklich passiert
raw_text = get_website_raw(website_url) raw_text = get_website_raw(website_url)
summary = summarize_website_content(raw_text) summary = summarize_website_content(raw_text)
processed_count += 1 processed_count += 1