小学拼音弄一下

import re
from xpinyin import Pinyin

def remove_middle_characters(text):
    # 仅保留汉字
    chinese_chars = re.findall(r'[\u4e00-\u9fff]+', text)
    cleaned_text = ''.join(chinese_chars)

    # 如果字符数为偶数，则在中间添加空格
    if len(cleaned_text) % 2 == 0:
        middle_index = len(cleaned_text) // 2
        cleaned_text = cleaned_text[:middle_index] + ' ' + cleaned_text[middle_index:]

    return cleaned_text

# 从用户输入中读取多行文本
lines = []
print("请输入文本，输入'#'结束输入:")
while True:
    line = input("")
    if line == '#':
        break
    lines.append(line)

# 统计重复行
duplicate_lines = {}
for line in lines:
    if line in duplicate_lines:
        duplicate_lines[line] += 1
    else:
        duplicate_lines[line] = 1

# 计算行数和重复行的数量
line_count = len(lines)
duplicate_count = sum(1 for count in duplicate_lines.values() if count > 1)

# 计算重复行占总行数的百分比
if line_count > 0:
    duplicate_percentage = (duplicate_count / line_count) * 100
else:
    duplicate_percentage = 0

# 打印统计信息
print("统计：")
print("行数:", line_count)
print("重复行:", duplicate_count)
print("重复行占总行数的百分比: {:.2f}%".format(duplicate_percentage))

# 删除重复行
lines = list(set(lines))

# 删除中间字符并按要求修改
for i in range(len(lines)):
    lines[i] = remove_middle_characters(lines[i])

# 使用拼音排序
pinyin = Pinyin()
lines.sort(key=lambda x: pinyin.get_pinyin(x, ' '))

# 按行长度排序
lines.sort(key=lambda x: len(x))

# 去除重复行
lines = list(set(lines))

# 打印处理后的文本
print("处理后的文本:")
for line in lines:
    print(line)

# 再次统计重复行
duplicate_lines = {}
for line in lines:
    if line in duplicate_lines:
        duplicate_lines[line] += 1
    else:
        duplicate_lines[line] = 1

# 计算行数和重复行的数量
line_count = len(lines)
duplicate_count = sum(1 for count in duplicate_lines.values() if count > 1)

# 计算重复行占总行数的百分比
if line_count > 0:
    duplicate_percentage = (duplicate_count / line_count) * 100
else:
    duplicate_percentage = 0

# 打印统计信息
print("再次统计：")
print("行数:", line_count)
print("重复行:", duplicate_count)
print("重复行占总行数的百分比: {:.2f}%".format(duplicate_percentage))

折腾全网小学生正义词反义词

在这里插入图片描述