【CET4/6】4级词汇大纲获取

"""
-*- coding:utf-8 -*-
@Time   :2021/3/1 18:56
@Author :
@File   :cet4.py
@Version：1.0
"""

#
# 1 数据来源
# 中国教育在线网_词汇：https://www.eol.cn/html/en/cetwords/cet4.shtml
#
# 2 词性（10种）
# 1、名词 noun n
# 2、代词 pronoun pron
# 3、形容词 adjective adj
# 4、副词 adverb adv
# 5、verb v
# 6、数词 numeral num
# 7、冠词 article art
# 8、介词 preposition prep
# 9、连词 conjunction conj
# 10、感叹词 interjection interj
#
#

from html.parser import HTMLParser
import xlwt


def del_kg(str_d: str):
    """
    删除字符串前面的空格
    :param str_d:
    :return:
    """
    if str_d.startswith(' '):
        return False, str_d[1:]
    return True, str_d


class My(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.str_data = []

    def handle_data(self, data):
        if self.lasttag == 'p':
            if not data.startswith('
') and not data.find('.') == -1:
                while True:
                    re, me = del_kg(data)
                    if not re:
                        data = me
                    else:
                        self.str_data.append(data)
                        break


def write_excel(file, data: list):
    wb = xlwt.Workbook()
    st = wb.add_sheet('aa')
    rows = len(data)
    for i in range(len(data)):
        for i_i in range(len(data[i])):
            st.write(i, i_i, data[i][i_i])

    wb.save(file)


if __name__ == '__main__':
    file = 'C:\Users\Administrator\Desktop\cet4.txt'
    with open(file, 'r', encoding='utf-8') as f:
        da = f.read()
        pa = My()
        pa.feed(da)
        pa.handle_data(da)

        # 去重
        re_l_da = list(set(pa.str_data))
        re_l_da.sort(key=pa.str_data.index)
        pa.str_data = re_l_da

        a = []
        b = []
        for i in pa.str_data:
            result = i.split(' ')
            if len(result) == 2:
                a_ls = []
                a_ls.append(result[0])
                a_ls.append(result[1])
                a.append(a_ls)
            else:
                b.append(i)
        # print(*pa.str_data, sep='
')
        print('aa=', len(a))  # 4471
        print(*a, sep='
')
        print(len(b))
        print(len(pa.str_data))
        print(*b, sep='
')
    da_da = []

    write_excel('aaa.xls', a)