oeasy-python-tutorial/convert_md_to_docx.py at main · overmind1980/oeasy-python-tutorial · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
import re
import requests
import os
from docx import Document
from docx.shared import Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH

def download_image(url, filename):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
            'Referer': 'https://www.shiyanlou.com/'
        }
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()
        with open(filename, 'wb') as f:
            f.write(response.content)
        return True
    except Exception as e:
        print(f"Failed to download {url}: {e}")
        return False

def markdown_to_docx(md_file, docx_file):
    with open(md_file, 'r', encoding='utf-8') as f:
        content = f.read()

    doc = Document()

    lines = content.split('\n')
    i = 0

    while i < len(lines):
        line = lines[i].strip()

        if line.startswith('---'):
            i += 1
            continue

        if line.startswith('#'):
            level = len(re.match(r'^#+', line).group())
            text = re.sub(r'^#+\s*', '', line)
            heading = doc.add_heading(text, level=min(level, 9))
            heading.alignment = WD_ALIGN_PARAGRAPH.LEFT

        elif line.startswith('!['):
            match = re.match(r'!\[([^\]]*)\]\(([^)]+)\)', line)
            if match:
                alt_text = match.group(1)
                img_url = match.group(2)

                img_filename = f"temp_img_{i}.png"
                if download_image(img_url, img_filename):
                    try:
                        doc.add_picture(img_filename, width=Inches(5))
                        last_paragraph = doc.paragraphs[-1]
                        last_paragraph.alignment = WD_ALIGN_PARAGRAPH.CENTER
                        os.remove(img_filename)
                    except Exception as e:
                        print(f"Failed to insert image: {e}")
                        if os.path.exists(img_filename):
                            os.remove(img_filename)

        elif line.startswith('- ['):
            match = re.match(r'- \[([^\]]+)\]\(([^)]+)\)', line)
            if match:
                link_text = match.group(1)
                link_url = match.group(2)
                p = doc.add_paragraph(link_text, style='List Bullet')
                p.add_run(f" ({link_url})")
            else:
                if line.startswith('-'):
                    text = re.sub(r'^-\s*', '', line)
                    doc.add_paragraph(text, style='List Bullet')

        elif line.startswith('-'):
            text = re.sub(r'^-\s*', '', line)
            doc.add_paragraph(text, style='List Bullet')

        elif line.startswith('*'):
            text = re.sub(r'^\*\s*', '', line)
            doc.add_paragraph(text, style='List Bullet')

        elif line.startswith('`'):
            code_text = re.sub(r'`', '', line)
            run = doc.add_paragraph().add_run(code_text)
            run.font.name = 'Courier New'

        elif line.strip() == '':
            doc.add_paragraph()

        else:
            if line:
                doc.add_paragraph(line)

        i += 1

    doc.save(docx_file)
    print(f"Successfully created {docx_file}")

if __name__ == "__main__":
    md_file = "/Users/easyo/Documents/oeasy/lanqiao/oeasy-python-tutorial/md/001-87321-先跑起来_python_三大系统选择_windows_mac_linux.sy.md"
    docx_file = "/Users/easyo/Documents/oeasy/lanqiao/oeasy-python-tutorial/md/001-87321-先跑起来_python_三大系统选择_windows_mac_linux.sy.docx"
    markdown_to_docx(md_file, docx_file)