Python 读取文件并统计单词出现次数

#
#   py_count_words.py
#   py_learn
#
#   Created by Z. Steve on 2023/8/23 10:30.
#
import re
from collections import Counter


def count_words(text):
    # 使用正则表达式将文本拆分为单词
    words = re.findall(r'\b\w+\b', text.lower())  # 转换为小写以进行不区分大小写的统计
    word_count = Counter(words)
    return word_count


def read_file():
    fs = open(file='/Users/stevexiaohuzhao/PycharmProjects/py_learn/words.txt', mode='r', encoding='utf-8')
    txt = fs.read()
    fs.close()
    return txt


article = read_file()
word_count = count_words(article)

# 打印每个单词及其出现次数
for word, count in word_count.items():
    print(f"{word}: {count}")

#
#   py_words_stat.py
#   py_learn
#
#   Created by Z. Steve on 2023/8/23 17:14.
#
import re
from collections import Counter


# 读取文件内容
def read_file(filename):
    f = open(file=filename, mode='r', encoding='utf-8')
    content = f.read()
    f.close()
    return content


# 通过 Counter 来统计
def count_words(text):
    result = re.findall(r'\b\w+\b', text)
    # print(result)               # ['hello', 'welcome', ...]
    # print(type(result))         # <class 'list'>
    return Counter(result)


# 不用 Counter, 自己写代码统计
def count_words_byself(text):
    words_list = re.findall(r'\b\w+\w', text)
    word_count_dict = {}
    for w in words_list:
        if w not in word_count_dict.keys():
            word_count_dict[w] = 1
        else:
            word_count_dict[w] += 1
    return word_count_dict


# text = read_file('/Users/stevexiaohuzhao/PycharmProjects/py_learn/words.txt')
# r = count_words(text)
# # print(r)            # Counter({'the': 22, 'a': 21, 'to': 20, 'Harden': 12, 'in': 12, 'country': 11, .......})
# # print(type(r))      # <class 'collections.Counter'>
#
# for item, c in r.items():
#     print(f'{item} = {c}')

text = read_file('/Users/stevexiaohuzhao/PycharmProjects/py_learn/words.txt')
r = count_words_byself(text)
print(r)
print(type(r))
for k, v in r.items():
    print(f'{k} = {v}')