Python 统计红楼梦、Jane Eyre词频方法

包含去除标点符号和换行、空格等因素

import pandas as pd




def question1():

    words = ['贾宝玉', '宝玉', '林黛玉', '黛玉']

    with open("HLM-UTF-8.txt", 'r', encoding='UTF-8') as r:

        lines = r.readlines()

        with open('result1.txt', 'w', encoding='UTF-8') as w:

            for word in words:

                w.write(word + '出现的行数及行如下：\n')

                for line in lines:

                    if word in line:

                        w.write(str(lines.index(line) + 1) + line)

            w.close()

        r.close()




def question2():

    result = {}

    with open("HLM-UTF-8.txt", 'r', encoding='UTF-8') as r:

        lines = r.readlines()

        for line in lines:

            line = line.strip()

            for char in '!"#$&()*+,-./:;<=>?@[\\]^_{|}·~‘’\n\'＂＃＄％＆＇（）＊＋，－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､　、〃〈〉《》「」『』【】〔〕〖〗〘〙〚〛〜〝〞〟〰〾〿–—‘’‛“”„‟…‧﹏﹑﹔·！？｡。\u3000':

                line = line.replace(char, "")

            for char in line:

                if char in list(result.keys()):

                    result[char] += 1

                else:

                    result[char] = 1

        df = pd.DataFrame(result, index=[0]).T

        df.to_csv("result2.csv", encoding='utf-8-sig')

        r.close()




def question3():

    result = {}

    with open('JaneEyre.txt', 'r') as r:

        lines = r.readlines()

        for line in lines:

            line = line.lower()

            for char in '!"#$&()*+,-./:;<=>?@[\\]^_{|}·~‘’\u3000\n\'':

                line = line.replace(char, "")

                words = line.split(' ')

            for word in words:

                if word in list(result.keys()):

                    result[word] += 1

                else:

                    result[word] = 1

        del result['']

        df = pd.DataFrame(result, index=[0]).T

        df.to_csv("result3.csv")

        r.close()




if __name__ == '__main__':

    # question1()

    question2()

    # question3()