python-将英文文章切割为单词，并添加发音和释义

justfly99

20230712，进行了小修改，主要是以下2个：
1、支持选择多个文件进行转换
2、将单个字符和2个字符的单词给过滤了，如a,at等。

成品地址(源码在压缩包里)：https://wwch.lanzoul.com/iPQBt124yqmf
PS：这次解压后，执行的是article2words v1.01.exe的







经历多次Chatgpt后的成品，虽然图形界面有点丑，不过也懒得弄了。
不足：有些带时态或复数的单词，无法添加发音和释义的。




成品见这里：https://wwch.lanzoul.com/in1Zg11uejab
解压后执行main.exe即可。

源码见这里(如果有人优化了，希望也能给我一份优化后的代码)：

[Python] 纯文本查看 复制代码

?

001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144

import tkinter as tk from tkinter import filedialog from tkinter import messagebox from functools import partial from threading import Thread import pandas as pd import re import requests from lxml import etree from openpyxl import load_workbook from concurrent.futures import ThreadPoolExecutor from openpyxl.styles import Font, NamedStyle     def get_word_info(word):     # 构造请求URL     url = f'https://www.youdao.com/w/eng/{word}'       try:         paraphrase = ""         data = requests.get(url).text         html = etree.HTML(data)         British_pronunciation = html.xpath('//*[@id="phrsListTab"]/h2/div/span[1]/span/text()')[0]         American_pronunciation = html.xpath('//*[@id="phrsListTab"]/h2/div/span[2]/span/text()')[0]         li_elements = html.xpath('//*[@id="phrsListTab"]/div/ul')         for li in li_elements:             paraphrase = ''.join(li.xpath('.//text()'))         return British_pronunciation, American_pronunciation, paraphrase     except Exception as e:         print(e, word)         return None     def process_text_file(file_path):     # 读取文本文件     with open(file_path, 'r') as file:         content = file.read()       # 将内容分隔为单词列表     words = re.split(r"\b[,.:?!()'\"\s\n\t\r]+?\b", content)       # 全部转换为小写     lowercase_words = [word.lower() for word in words]       # 去重     unique_words = list(set(lowercase_words))       # 排序     sorted_words = sorted(unique_words)       # 清洗     filtered_words = [word for word in sorted_words if "'" not in word and not re.search(r'[\u4e00-\u9fff]', word) and not re.search(r'\d', word)]  # 删除包含乱码、数字和缩写的单词       # 导出到Excel     df = pd.DataFrame(filtered_words, columns=['Words'])     output_file = file_path.replace('.txt', '.xlsx')     df.to_excel(output_file, index=False)       # 打开Excel文件     workbook = load_workbook(output_file)     worksheet = workbook.active     worksheet.cell(row=1, column=2, value="British_pronunciation")     worksheet.cell(row=1, column=3, value="American_pronunciation")     worksheet.cell(row=1, column=4, value="paraphrase")       # 创建样式并设置为加粗     bold_style = NamedStyle(name="bold_style")     bold_style.font = Font(bold=True)     worksheet.cell(row=1, column=2).style = bold_style     worksheet.cell(row=1, column=3).style = bold_style     worksheet.cell(row=1, column=4).style = bold_style       # 使用线程池处理请求     with ThreadPoolExecutor() as executor:         futures = [executor.submit(get_word_info, word) for word in filtered_words]           # 遍历每个单元格，获取单词并添加发音和释义         row_index = 2  # 设置初始单元格         for future, row in zip(futures, worksheet.iter_rows(min_row=2, max_col=4)):             word = row[0].value             word_info = future.result()               if word_info:                 British_pronunciation, American_pronunciation, paraphrase = word_info                 worksheet.cell(row=row_index, column=2).value = British_pronunciation                 worksheet.cell(row=row_index, column=3).value = American_pronunciation                 worksheet.cell(row=row_index, column=4).value = paraphrase             else:                 # 如果单词发音获取不到，则检查单词是否s,ed,ing结尾，如果是，则去除s,d,ing后再试试                 if word.endswith(('s', 'ed', 'ing')):                     word_without_suffix = re.sub(r'(s|d|ing)$', '', word)                     word_info = get_word_info(word_without_suffix)                     if word_info:                         British_pronunciation, American_pronunciation, paraphrase = word_info                         worksheet.cell(row=row_index, column=2).value = British_pronunciation                         worksheet.cell(row=row_index, column=3).value = American_pronunciation                         worksheet.cell(row=row_index, column=4).value = paraphrase               row_index += 1       # 保存修改后的Excel文件     workbook.save(output_file)     messagebox.showinfo('Success', 'Process completed successfully.')     def browse_file(file_entry):     file_path = filedialog.askopenfilename(filetypes=[('Text Files', '*.txt')])     if file_path:         file_entry.delete(0, tk.END)         file_entry.insert(tk.END, file_path)     def execute_function(file_entry):     file_path = file_entry.get()     if not file_path:         messagebox.showerror('Error', 'Please select a file.')         return       execute_button.config(state=tk.DISABLED)     thread = Thread(target=process_text_file, args=(file_path,))     thread.start()     # Create the main window window = tk.Tk() window.title('英文文章切割为单词 V1.0') window.configure(bg='sky blue')   # Create the file browse widget file_label = tk.Label(window, text='Select a text file:', bg='sky blue') file_label.pack()   file_entry = tk.Entry(window, width=50) file_entry.pack()   browse_button = tk.Button(window, text='Browse', command=partial(browse_file, file_entry)) browse_button.pack()   # Create the execute button execute_button = tk.Button(window, text='Execute', command=partial(execute_function, file_entry)) execute_button.pack()   # Start the main loop window.mainloop()

justfly99

szair 发表于 2023-7-12 15:07
问一下，以后接口会不会到某天就失效了呢？希望持续更新，谢谢

实话实说，依靠别人不如自己学会修改，代码里面调用是有道的接口，涉及的代码就几行，使用的etree和xpath定位到具体的位置的，这两块的知识点其实不多的，网上找点文章学习一下很快可以上手的

    url = f'https://www.youdao.com/w/eng/{word}'

    try:
        paraphrase = ""
        data = requests.get(url).text
        html = etree.HTML(data)
        British_pronunciation = html.xpath('//*[@id="phrsListTab"]/h2/div/span[1]/span/text()')[0]
        American_pronunciation = html.xpath('//*[@id="phrsListTab"]/h2/div/span[2]/span/text()')[0]
        li_elements = html.xpath('//*[@id="phrsListTab"]/div/ul')
        for li in li_elements:
            paraphrase = ''.join(li.xpath('.//text()'))
        return British_pronunciation, American_pronunciation, paraphrase

justfly99

毋庸讳言 发表于 2023-7-10 19:47
这个怎么使用呢？

下载后，双击 main.exe，然后点击 Browser，选择带有英文文章的 txt 文件，点击Execute，然后就在你 txt 文件的目录下，找到 txt 文件同名的 excel 文件，打开就行了

gaogao0000

楼主厉害,加油

ckchen123

楼主厉害,加油

zhuvsyue

666哇

jxcllj

谢谢楼主分享。

markhoo911

我靠，这个不错啊，挺实用的

Lcx丶

楼主厉害,加油

word11

感谢大哥的分享，内容很精彩

m1250674036

不错不错，感谢分享 收藏备用

blindcat

跟楼主学习学习