从一组文件中删除停止字

Question

import pathlib

stop_words = open("StopWordList.txt")
stop_words.read()

for path in pathlib.Path(r'C:\Users\Usuario\Desktop\HelloWorld\emails').iterdir():
    if path.is_file():
        current_file = open(path, "r")
        lines = current_file.read()
        words = lines.split()

        for y in stop_words:
            if not y in stop_words:

                appendFile = open('filteredtext.txt', 'a')
                appendFile.write(" "+y)
                appendFile.close()

Answer 1

我没有测试它（我没有带有停止词的文件），但我会这样做

import pathlib
import sys


if len(sys.argv) > 1:
    folder = sys.argv[1] # get folder as parameter
else:
    folder = r'C:\Users\Usuario\Desktop\HelloWorld\emails'


stop_words = open("StopWordList.txt").read().lower()  # to compare lowercase stopwords with lowercase words

for path in pathlib.Path(folder).iterdir():
    if path.is_file():

        # --- read all text at once ---

        input_file = open(path) #  it use `r` as default
        text = input_file.read()
        input_file.close()

        original_words = text.split()  # text -> words

        # --- remove stopwords ---

        filtered_words = []

        for word in original_words:
            temp_word = word.lower().rstrip('.,!?')
            if temp_word not in stop_words:   # check lowercase without `.,!?`
                filtered_words.appeend(word)  # keep original word

        # --- save all text at once ---

        output_path = path + '-filtered'  # create new filename

        text = " ".join(filtered_words)  # words -> text

        output_file = open('output_path', 'w')
        output_file.write(text)
        output_file.close()

它不会删除.，！？并且不会转换为小写。

最终您可以将代码拆分为函数

import pathlib
import sys

# --- functions ---

def read_words(path):

    input_file = open(path) #  it use `r` as default
    text = input_file.read()
    input_file.close()

    words = text.split()  # text -> words

    return words

def filter_words(words, stopwords):

    filtered_words = []

    for word in all_words:
        temp_word = word.lower().rstrip('.,!?')
        if temp_word not in stop_words:
            filtered_words.appeend(word)

    return filtered_words

def write_words(path, words):

    text = " ".join(words)  # words -> text

    output_file = open(path, 'w')
    output_file.write(text)
    output_file.close()

# --- main ---

if len(sys.argv) > 1:
    folder = sys.argv[1] # get folder as parameter
else:
    folder = r'C:\Users\Usuario\Desktop\HelloWorld\emails'

stop_words = open("StopWordList.txt").read().lower()  # to compare lowercase stopwords with lowercase words

for path in pathlib.Path(folder).iterdir():
    if path.is_file():
        words = read_words(path)
        words = fiter_words(words, stopwords)
        write_words(path + '-fitered', words)