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

data_processor.py aktualisiert

Browse Source
This commit is contained in:
Floke
2025-07-18 18:09:22 +00:00
parent db6bcda460
commit 0fec249c70
1 changed files with 19 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
data_processor.py
View File

@@ -2316,6 +2316,14 @@ class DataProcessor:
batch_sheet_updates = []
# Iteriere über die Ergebnisse des finalen Batches
for row_num, result_dict in scraping_results.items():
# Sicherheitsprüfung: Stelle sicher, dass result_dict ein Dictionary ist.
if not isinstance(result_dict, dict):
self.logger.error(f"Fehlerhaftes Ergebnis für Zeile {row_num}: Erwartete dict, bekam {type(result_dict)}. Überspringe Update für diese Zeile.")
# Setze nur den Timestamp, um eine Endlosschleife zu verhindern
batch_sheet_updates.append({'range': f'{self.sheet_handler._get_col_letter(col_indices["Website Scrape Timestamp"] + 1)}{row_num}', 'values': [[current_timestamp]]})
continue
# result_dict ist jetzt garantiert ein Dictionary
batch_sheet_updates.extend([
{'range': f'{self.sheet_handler._get_col_letter(col_indices["Website Rohtext"] + 1)}{row_num}', 'values': [[result_dict.get('raw_text', 'k.A.')]]},
{'range': f'{self.sheet_handler._get_col_letter(col_indices["Website Meta-Details"] + 1)}{row_num}', 'values': [[result_dict.get('meta_details', 'k.A.')]]},
@@ -2400,13 +2408,20 @@ class DataProcessor:
# ANPASSUNG AN NEUE LOGIK
for row_num, result_dict in scraping_results.items():
# Sicherheitsprüfung: Stelle sicher, dass result_dict ein Dictionary ist.
if not isinstance(result_dict, dict):
self.logger.error(f"Fehlerhaftes Ergebnis für Zeile {row_num}: Erwartete dict, bekam {type(result_dict)}. Überspringe Update für diese Zeile.")
# Setze nur den Timestamp, um eine Endlosschleife zu verhindern
batch_sheet_updates.append({'range': f'{self.sheet_handler._get_col_letter(col_indices["Website Scrape Timestamp"] + 1)}{row_num}', 'values': [[current_timestamp]]})
continue
# result_dict ist jetzt garantiert ein Dictionary
batch_sheet_updates.extend([
{'range': f'{self.sheet_handler._get_col_letter(col_indices["Website Rohtext"] + 1)}{row_num}', 'values': [[result_dict.get('raw_text', 'k.A.')]]},
{'range': f'{self.sheet_handler._get_col_letter(col_indices["Website Meta-Details"] + 1)}{row_num}', 'values': [[result_dict.get('meta_details', 'k.A.')]]},
{'range': f'{self.sheet_handler._get_col_letter(col_indices["Website Scrape Timestamp"] + 1)}{row_num}', 'values': [[current_timestamp]]},
{'range': f'{self.sheet_handler._get_col_letter(col_indices["Version"] + 1)}{row_num}', 'values': [[current_version]]}
])
all_sheet_updates.extend(batch_sheet_updates)
# --- Finale Sheet Updates senden ---
if all_sheet_updates:
@@ -2435,14 +2450,15 @@ class DataProcessor:
return {
'row_num': row_num,
'raw_text': raw_text_result,
'meta_details': meta_details_result,
'meta_details': meta_details_result
}
except Exception as e:
# Dieses Sicherheitsnetz fängt alle unerwarteten Fehler ab, die die Helper nicht fangen.
self.logger.error(f"FATALER FEHLER im Scraping Worker für Zeile {row_num}: {e}", exc_info=True)
return {
'row_num': row_num,
'raw_text': f'k.A. (FATALER WORKER FEHLER: {e})',
'meta_details': 'k.A.',
'meta_details': f'k.A. (FATALER WORKER FEHLER: {e})'
}