Python自动化实现将JavaScript代码转换为Word文档

pip install spire.doc
pip install pygments

from spire.doc import *
from pygments import highlight
from pygments.lexers import JavascriptLexer
from pygments.formatters import HtmlFormatter

def convert_js_to_word(input_file: str, output_file: str) -> None:
    """将 JavaScript 文件转换为带有语法高亮的 Word 文档。"""

    with open(input_file, "r", encoding="utf-8") as file:
        js_code = file.read()

    document = Document()
    section = document.AddSection()
    section.PageSetup.Margins.All = 50

    title_paragraph = section.AddParagraph()
    title_text = title_paragraph.AppendText(f"源代码：{input_file}")
    title_text.CharacterFormat.FontName = "微软雅黑"
    title_text.CharacterFormat.FontSize = 14
    title_text.CharacterFormat.Bold = True
    title_paragraph.Format.AfterSpacing = 10

    html_formatter = HtmlFormatter(
        nowrap=True,
        style='colorful',
        noclasses=True
    )

    highlighted_html = highlight(js_code, JavascriptLexer(), html_formatter)

    code_paragraph = section.AddParagraph()
    code_paragraph.AppendHTML(
        f'<pre style="font-family: Consolas; font-size: 10pt;">{highlighted_html}</pre>'
    )

    document.SaveToFile(output_file, FileFormat.Docx)
    document.Close()

    print(f"已将 {input_file} 转换为 {output_file}")

convert_js_to_word("app.js", "JavaScriptCode.docx")

from pygments.lexers import JsxLexer

highlighted_html = highlight(jsx_code, JsxLexer(), html_formatter)

pip install spire.doc pygments

from spire.doc import *
from pygments import highlight
from pygments.lexers import JavascriptLexer, JsxLexer  # 如果需要处理React JSX
from pygments.formatters import HtmlFormatter

def convert_js_to_word(input_file: str, output_file: str) -> None:
    """将JavaScript文件转换为带语法高亮的Word文档。"""
    # 1. 读取源码
    with open(input_file, "r", encoding="utf-8") as file:
        js_code = file.read()

    # 2. 初始化Word文档
    document = Document()
    section = document.AddSection()
    section.PageSetup.Margins.All = 50  # 收窄页边距，为长代码行留出空间

    # 添加标题（可选）
    title_paragraph = section.AddParagraph()
    title_text = title_paragraph.AppendText(f"源代码：{input_file}")
    title_text.CharacterFormat.FontName = "微软雅黑"
    title_text.CharacterFormat.FontSize = 14
    title_text.CharacterFormat.Bold = True
    title_paragraph.Format.AfterSpacing = 10

    # 3. 用Pygments生成带内联样式的HTML（关键参数：noclasses=True）
    html_formatter = HtmlFormatter(
        nowrap=True, 
        style='colorful',  # 可选：monokai, vim, vs 等
        noclasses=True     # 必须为True，否则颜色样式会丢失
    )
    highlighted_html = highlight(js_code, JavascriptLexer(), html_formatter)

    # 4. 将高亮HTML导入Word
    code_paragraph = section.AddParagraph()
    # <pre>标签不可省略，用于保留代码的换行和空格缩进
    code_paragraph.AppendHTML(
        f'<pre style="font-family: Consolas; font-size: 10pt;">{highlighted_html}</pre>'
    )

    # 5. 保存并关闭
    document.SaveToFile(output_file, FileFormat.Docx)
    document.Close()
    print(f"已将 {input_file} 转换为 {output_file}")

# 使用示例
convert_js_to_word("app.js", "JavaScriptCode.docx")

from pygments.lexers import JsxLexer
highlighted_html = highlight(jsx_code, JsxLexer(), html_formatter)

from docx import Document
from docx.shared import Pt, RGBColor
from docx.enum.text import WD_COLOR_INDEX
from pygments import lex
from pygments.lexers import JavascriptLexer
from pygments.styles import get_style_by_name

def convert_js_to_word_manual(input_file, output_file):
    with open(input_file, "r", encoding="utf-8") as f:
        code = f.read()

    doc = Document()
    # 设置一个等宽字体段落
    paragraph = doc.add_paragraph()
    paragraph.style.font.name = "Consolas"
    paragraph.style.font.size = Pt(10)

    # 获取Pygments样式并建立token类型到颜色的映射
    style = get_style_by_name("colorful")
    # 简化处理：实际应用中需更精细地将Token类型映射到颜色
    token_color_map = {
        "Token.Keyword": RGBColor(0x00, 0x00, 0xFF),  # 蓝色
        "Token.String": RGBColor(0x00, 0x80, 0x00),   # 绿色
        "Token.Comment": RGBColor(0x80, 0x80, 0x80),  # 灰色
        # ... 其他类型
    }

    for token_type, value in lex(code, JavascriptLexer()):
        run = paragraph.add_run(value)
        # 根据token类型设置颜色（需要更完善的映射逻辑）
        for token_name, color in token_color_map.items():
            if str(token_type).startswith(token_name):
                run.font.color.rgb = color
                break
        run.font.name = "Consolas"
        run.font.size = Pt(10)

    doc.save(output_file)

pip install python-docx

# 示例：将 src 目录下所有 .js 文件导出，并保留注释
python export_code_to_docx.py --include ./src --ext js --output my_code.docx --no-comments