统计文章词频

所属作业: 文件 数据结构: 字典 算法: 排序

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
article = list(open("The_Red_Headed_League.txt", "r", encoding="utf-8"))
books = {}
for line in article:
    words = line.replace(",", " ").replace(".", " ").split()
    for word in words:
        lower_word = word.lower()
        if lower_word not in books:
            books[lower_word] = 0
        books[lower_word] += 1
word_list = sorted(books.items(), key=lambda x: (-x[1], x[0]))
writer = open("word_list.txt", "w")
for word, count in word_list:
    writer.write(f"{word} {count}\n")