A script that searches through the text of all sub-directories' files for a string then prints to a created file

Question

I’m a scripting noob and I’m stuck on this problem.

I would like the code to do a few things:

Ask for user input for a string to search for.
Iterate through the sub-directories from a given file path.
Open files that have one of the extension types listed.
Open the file and search for the user inputted string.
Print the results from the query to a text file.

The code seems to take some time to run but turns up nothing.

import os.path

# Ask the user to enter string to search
search_str = input("Keyword or phrase:n")

# Store file names for later printing 
file_names = []

# Path to search 
path = os.path.dirname(os.path.realpath(__file__))

# Acceptable file extensions
extensions = {".xlsx", ".txt", ".pdf", ".doc", ".docx", ".mb", ".xlsm", ".xltx", ".xltm"}

# Create file to store search results
search_files = open('search.txt', 'w')
search_files.write(f'I searched for "{search_str}" in your files.nnHere is what I found:nn')


# Program to search files for keyword
def search_all_files_by_keyword(path):

    # Store file count number
    file_count = 0

    for root, dirs, files in os.walk(path):

        for file in files:

            try:

                # Apply file type filter, search for acceptable ext in extension
                ext = os.path.splitext(file)
                if ext in extensions:

                    # Define file pathway
                    file_path = os.path.join(root, file)

                    # Open file for reading
                    with open(file, 'r') as f:

                        # Read file and search for keyword or phrase
                        if search_str in f.read():

                            # Add file path to file_names and increase file_count, then close file
                            file_names.append(file_path)
                            file_count += 1
                            f.close()

                        # If keyword or phrase is not found, do nothing and close file
                        else:
                            f.close()

            except:
                pass

    # Print search results to file
    if file_count >= 1:
        search_files.write(f"{file_names}n")
    else:
        search_files.write(f'No results found for "{search_str}".')

# Run program 
search_all_files_by_keyword(path)

Asked By: sssucksatCoding

||

Source

Answer 1

Try the path module to search all folder/sub-folders this way:


import re
from pathlib import Path

# Ask the user to enter string to search
search_str = input("Keyword or phrase:n")

# Store file names for later printing
file_names = []

# Path to search
path = Path("path/to/directory") # Replace with your actual file path

# Acceptable file extensions
extensions = {".xlsx", ".txt", ".pdf", ".doc", ".docx", ".mb"]

# to search for string in a file
def search_in_file(file_path, search_str):
    with open(file_path, 'r', encoding='utf-8') as f:
        file_content = f.read()
        matches = re.findall(search_str, file_content)
        if matches:
            return matches
        else:
            return None

# Iterate through the sub-directories 
for file_path in path.glob("**/*"):
    if file_path.suffix in extensions:
        matches = search_in_file(file_path, search_str)
        
        if matches:
            file_names.append(str(file_path))
            
            with open("results.txt", "a", encoding='utf-8') as results_file:
                results_file.write(f"{file_path}n")
                results_file.write(f"{matches}nn")

Answered By: Daniel Hao

A script that searches through the text of all sub-directories' files for a string then prints to a created file

Question:

Answers: