Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 26 additions & 0 deletions processing.py
Original file line number Diff line number Diff line change
Expand Up @@ -85,4 +85,30 @@ def get_URL_Tittle(text: str):
except Exception as e :
print('Error delete_special_patterns: {0}'.format(e))
return result

@staticmethod
def get_normalized_text(folder_path: str, file_name: str) -> str:
"""Extrae el texto de un archivo de texto plano y lo normaliza

Parameters
----------
ruta_carpeta : str
string con la ruta de la carpeta donde se encuentre el archivo a normalizar
nombre_archivo : str
nombre del archivo que desea normalizar

Returns
-------
posicion 1 : str
texto normalizado con encoding utf-8
"""
text = ''
try:
with open(f'{folder_path}/{file_name}', 'r', encoding='latin1') as file:
text = file.read()
text = self.proper_encoding(text)
return text
except Exception as e:
print(f'Error: {e}')