data_processor.py aktualisiert
This commit is contained in:
@@ -2316,7 +2316,6 @@ class DataProcessor:
|
||||
batch_sheet_updates = []
|
||||
# Iteriere über die Ergebnisse des finalen Batches
|
||||
for row_num, result_dict in scraping_results.items():
|
||||
# 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.')]]},
|
||||
@@ -2401,7 +2400,6 @@ class DataProcessor:
|
||||
|
||||
# ANPASSUNG AN NEUE LOGIK
|
||||
for row_num, result_dict in scraping_results.items():
|
||||
# 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.')]]},
|
||||
@@ -2424,14 +2422,13 @@ class DataProcessor:
|
||||
|
||||
def _scrape_raw_text_task(self, task_info, scrape_function):
|
||||
"""
|
||||
Worker-Funktion. Ruft gehärtete Helper auf und gibt IMMER ein Dictionary zurück.
|
||||
Worker-Funktion. Ruft die gehärteten Helper auf und gibt IMMER ein Dictionary zurück.
|
||||
"""
|
||||
url = task_info.get('url')
|
||||
row_num = task_info.get('row_num')
|
||||
self.logger.debug(f" -> Scrape Task gestartet für Zeile {row_num}: {url}")
|
||||
|
||||
try:
|
||||
# Die Aufrufe der Helper-Funktionen sind jetzt im try-Block
|
||||
raw_text_result = get_website_raw(url)
|
||||
meta_details_result = scrape_website_details(url)
|
||||
|
||||
@@ -2439,16 +2436,13 @@ class DataProcessor:
|
||||
'row_num': row_num,
|
||||
'raw_text': raw_text_result,
|
||||
'meta_details': meta_details_result,
|
||||
'error': None
|
||||
}
|
||||
except Exception as e:
|
||||
# Dieser Block fängt jetzt Fehler, falls die Helper WIDER ERWARTEN doch abstürzen
|
||||
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.',
|
||||
'error': True
|
||||
}
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user