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
2025-04-17 09:48:32 +00:00
parent c0e5605754
commit 8d38803e1c
1 changed files with 22 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
brancheneinstufung.py
View File

@@ -2208,6 +2208,7 @@ def _process_batch(sheet, batches, row_numbers):
# Komplette Funktion process_website_batch (MIT Batched Google Sheet Updates)
# Komplette Funktion process_website_batch (NEUE STRUKTUR - ECHTER BATCH WORKFLOW)
# Komplette Funktion process_website_batch (NUR SCRAPING)
# Komplette Funktion process_website_batch (Korrigierte Config-Referenzen)
def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index_in_sheet):
"""
Batch-Prozess NUR für Website-Scraping (Rohtext AR).
@@ -2216,10 +2217,6 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
"""
debug_print(f"Starte Website-Scraping NUR ROHDATEN (Batch) für Zeilen {start_row_index_in_sheet} bis {end_row_index_in_sheet}...")
# --- Konfiguration ---
MAX_SCRAPING_WORKERS = Config.MAX_SCRAPING_WORKERS # Aus Config holen
update_batch_row_limit = Config.UPDATE_BATCH_ROW_LIMIT # Aus Config holen
# --- Lade Daten ---
if not sheet_handler.load_data(): return
all_data = sheet_handler.get_all_data_with_headers()
@@ -2227,7 +2224,7 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
header_rows = 5
# --- Indizes und Buchstaben ---
rohtext_col_key = "Website Rohtext" # Spalte AR
rohtext_col_key = "Website Rohtext"
rohtext_col_index = COLUMN_MAP.get(rohtext_col_key)
website_col_idx = COLUMN_MAP.get("CRM Website")
version_col_idx = COLUMN_MAP.get("Version")
@@ -2255,6 +2252,11 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
total_skipped_url_count = 0
total_error_count = 0
# Verwende Werte aus Config
processing_batch_size = Config.PROCESSING_BATCH_SIZE
max_scraping_workers = Config.MAX_SCRAPING_WORKERS
update_batch_row_limit = Config.UPDATE_BATCH_ROW_LIMIT # Annahme: UPDATE_BATCH_ROW_LIMIT ist auch in Config definiert
for i in range(start_row_index_in_sheet, end_row_index_in_sheet + 1):
row_index_in_list = i - 1
if row_index_in_list >= len(all_data): continue
@@ -2265,10 +2267,8 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
cell_value_ar = None
if len(row) > rohtext_col_index:
cell_value_ar = str(row[rohtext_col_index]).strip()
# Überspringen, wenn NICHT leer oder k.A.
if cell_value_ar and cell_value_ar.lower() not in ["", "k.a.", "k.a. (nur cookie-banner erkannt)", "k.a. (fehler)"]:
should_skip = True
# else: Spalte nicht vorhanden -> nicht überspringen
# Debug Log
log_debug = (i < start_row_index_in_sheet + 5 or i > end_row_index_in_sheet - 5 or i % 500 == 0)
@@ -2289,16 +2289,18 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
tasks_for_processing_batch.append({"row_num": i, "url": website_url})
# --- Verarbeitungs-Batch ausführen ---
if len(tasks_for_processing_batch) >= PROCESSING_BATCH_SIZE or i == end_row_index_in_sheet:
# HIER KORRIGIERT: Verwende processing_batch_size
if len(tasks_for_processing_batch) >= processing_batch_size or i == end_row_index_in_sheet:
if tasks_for_processing_batch:
batch_start_row = tasks_for_processing_batch[0]['row_num']
batch_end_row = tasks_for_processing_batch[-1]['row_num']
batch_task_count = len(tasks_for_current_processing_batch) # Korrigiert
batch_task_count = len(tasks_for_processing_batch)
debug_print(f"\n--- Starte Scraping-Batch ({batch_task_count} Tasks, Zeilen {batch_start_row}-{batch_end_row}) ---")
scraping_results = {}
debug_print(f" Scrape {batch_task_count} Websites parallel (max {MAX_SCRAPING_WORKERS} worker)...") # Korrigiert
with concurrent.futures.ThreadPoolExecutor(max_workers=MAX_SCRAPING_WORKERS) as executor:
# HIER KORRIGIERT: Verwende max_scraping_workers
debug_print(f" Scrape {batch_task_count} Websites parallel (max {max_scraping_workers} worker)...")
with concurrent.futures.ThreadPoolExecutor(max_workers=max_scraping_workers) as executor:
future_to_task = {executor.submit(scrape_raw_text_task, task): task for task in tasks_for_processing_batch}
for future in concurrent.futures.as_completed(future_to_task):
task = future_to_task[future]
@@ -2306,12 +2308,15 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
result = future.result()
scraping_results[result['row_num']] = result['raw_text']
if result['error']: total_error_count += 1
total_processed_count += 1 # Zähle hier jeden Versuch
# Zähle erst hier, wenn Ergebnis da ist
except Exception as exc:
row_num = task['row_num']; err_msg = f"Generischer Fehler Scraping Task Zeile {row_num}: {exc}"
debug_print(err_msg); scraping_results[row_num] = "k.A. (Fehler)"; total_error_count +=1; total_processed_count += 1
debug_print(err_msg); scraping_results[row_num] = "k.A. (Fehler)"; total_error_count +=1
debug_print(f" Scraping für Batch beendet.")
# Zähle hier die Anzahl der tatsächlich bearbeiteten Ergebnisse
current_batch_processed_count = len(scraping_results)
total_processed_count += current_batch_processed_count
debug_print(f" Scraping für Batch beendet. {current_batch_processed_count} Ergebnisse erhalten ({total_error_count} Fehler in diesem Batch).")
# --- Sheet Updates vorbereiten (NUR AR und AP) ---
if scraping_results:
@@ -2320,7 +2325,7 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
for row_num, raw_text_res in scraping_results.items():
row_updates = [
{'range': f'{rohtext_col_letter}{row_num}', 'values': [[raw_text_res]]},
# {'range': f'{ts_col_letter}{row_num}', 'values': [[current_timestamp]]}, # AT wird NICHT mehr gesetzt
# KEIN AT Timestamp mehr
{'range': f'{version_col_letter}{row_num}', 'values': [[current_version]]}
]
batch_sheet_updates.extend(row_updates)
@@ -2330,7 +2335,8 @@ def process_website_batch(sheet_handler, start_row_index_in_sheet, end_row_index
tasks_for_processing_batch = []
# --- Sheet Updates senden (wenn update_batch_row_limit erreicht) ---
# Hinweis: Diese Logik sendet jetzt seltener, erst wenn genug Updates gesammelt wurden
# HIER KORRIGIERT: Verwende update_batch_row_limit
# Prüfe die Anzahl der *Zellen* in all_sheet_updates
if len(all_sheet_updates) >= update_batch_row_limit * 2: # *2 weil 2 Updates pro Zeile
debug_print(f" Sende gesammelte Sheet-Updates ({len(all_sheet_updates)} Zellen)...")
success = sheet_handler.batch_update_cells(all_sheet_updates)