Python script to combine RTF files in a folder to CSV with filename as a separate column

I've tried a plethora of solutions which don't work. I've figured out how to get the converted data into a csv column, but all text is in 1 cell and I haven't figured out how to get the FileNames added as a column.

import pandas as pd import os from striprtf.striprtf import rtf_to_text dir_path = 'C:\\Users\\mairi\\Desktop\\testing txt to excel\\' def getFiles(): list = [] FileNames = [] for path in os.listdir(dir_path): if os.path.isfile(os.path.join(dir_path,path)): with open (os.path.join(dir_path,path)) as file: text = file.read() rtfText = rtf_to_text(text,encoding='utf-8') for text in rtfText: list.append(rtfText) FileNames.append(os.path.basename(rtfText)) return list return FileNames list = getFiles() FileNames = getFiles() Data = pd.DataFrame(columns: 'list','FileNames') NewPath = 'C:\\Users\\mairi\\Desktop\\testing txt to excel\\NEW\\' Data.to_csv(os.path.join(NewPath,r'Data.csv'), index = False, header = False) 

I've tried for a few days to scrape Stackoverflow and find a solution and now I seem to be getting duplicate file data in each row ?

I think my main issues are. Possible that I need to create an empty dataframe before the function, but I haven't got it working yet.

• separating the text so each new line is a new cell
• Distinct file content so there aren't duplicate rows
• adding the FileNames.

Hopefully, the outcome looks like this...

Thank you for any help :)

1 Answer

A friend helped me solve this pickle :)

I was converting and saving all text in the document instead of stripping it line by line.

import pandas as pd import os from striprtf.striprtf import rtf_to_text # Data structure class fileLine: def __init__(self, fileName, textLine): self.fileName = fileName self.textLine = textLine # Data files directories data_dir_path = 'C:\\Users\\mairi\\Desktop\\testing txt to excel\\' output_dir_path = 'C:\\Users\\mairi\\Desktop\\testing txt to excel\\NEW\\' # Get all lines of all RTF files in a giver directory def getRTFLines(): list = [] # For each file in the given directory for filename in os.listdir(data_dir_path): filePath = os.path.join(data_dir_path, filename) # Check if it's an RTF file if os.path.isfile(filePath) and filePath.endswith('.rtf'): # Open the RTF file with open(filePath, encoding='utf-8', errors='ignore') as file: # Read all the RTF file's content text = file.read() # Decode the RTF file's content rtfText = rtf_to_text(text, encoding='utf-8') # For each line in the RTF file for line in rtfText.splitlines(): # Check if it's an empty line if line: # Insert the line in our data structure list.append(fileLine(filename, line)) return list # Read data list = getRTFLines() # Convert data to csv file data = [[x.fileName, x.textLine] for x in list] df = pd.DataFrame(data, columns=['File Name', 'Text Line']) df.to_csv(os.path.join(output_dir_path,r'rtfData-3.csv'), escapechar="")