Read specific folder's name from folder's path Python-CodePudding

I'm trying to read the folder name at the specific place from the file path. My current code:

import os

# search for and input multiple files 
def get_files(source):
    matches = []
    for root, dirnames, filenames in os.walk(source):
        for filename in filenames:
            matches.append(os.path.join(root, filename))
    return matches

def parse(files):
    for file in files:
        xml_information = {}
        metadata = []
        # Get the file path
        filepath = os.path.dirname(file)
        xml_information['file_path'] = '%s' % filepath
        
        # Get customer name
        customer = filepath.split("\\")[5]
        xml_information['customer_name'] = '%s' % customer
        metadata.append(xml_information)
        print(metadata)

path = 'C:\\Users\\quan.nguyen\\SAGE\\Lania Thompson - Searching Project Files'

parse(get_files(path))

My program searches through folders and find the files and report back their folder path. However, I would like to read the folder path as well as the folder name at the sixth place which is customer name. When I run customer = filepath.split("\\")[5] it report an error:

Traceback (most recent call last):
  File "*hidden*", line 33, in <module>
    parse(get_files(path))
  File "*hidden*", line 26, in parse
    customer = filepath.split("\\")[5]
               ~~~~~~~~~~~~~~~~~~~~^^^
IndexError: list index out of range

However, when I run with customer = filepath.split("\\")[4], the program works and reads the last folder specified in path which is Lania Thompson - Searching Project Files. The result is as follows:

[{'file_path': 'C:\\Users\\quan.nguyen\\SAGE\\Lania Thompson - Searching Project Files\\Hazor Ltd\\PCS Mah\\Machine', 'customer_name': 'Lania Thompson - Searching Project Files'}]

My expecting result is Hazor Ltd:

[{'file_path': 'C:\\Users\\quan.nguyen\\SAGE\\Lania Thompson - Searching Project Files\\Hazor Ltd\\PCS Mah\\Machine', 'customer_name': 'Hazor Ltd'}]

The names are made up except from my name

CodePudding user response：

So I have worked out the code using the pathlib library. The code is:

import os
from pathlib import Path

# search for and input multiple files 
def get_files(source):
    matches = []
    for root, dirnames, filenames in os.walk(source):
        for filename in filenames:
            matches.append(os.path.join(root, filename))
    return matches

def parse(files):
    for file in files:
        xml_information = {}
        metadata = []
        # Get the file path
        filepath = os.path.dirname(file)
        
        # Get customer name
        p = Path(filepath)
        files = [f for f in p.rglob('*') if f.is_file()]

        for f in files:
            xml_information['Customer'] = f.parts[5]
        metadata.append(xml_information)
        print(metadata)

path = 'C:\\Users\\quan.nguyen\\SAGE\\Lania Thompson - Searching Project Files'

parse(get_files(path))

change the number [5] in xml_information['Customer'] = f.parts[5] for the place you want to get the folder's name from.