web-cowork/wordpress_import.py at main · aiseed-dev/web-cowork · 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
"""aiseed web creator — WordPress WXR インポート"""

import re
import xml.etree.ElementTree as ET


def import_wordpress_xml(xml_path):
    """WordPress WXR (eXtended RSS) をパースしてブログ記事リストを返す"""
    tree = ET.parse(xml_path)
    root = tree.getroot()
    ns = {
        "content": "http://purl.org/rss/1.0/modules/content/",
        "wp": "http://wordpress.org/export/1.2/",
        "dc": "http://purl.org/dc/elements/1.1/",
        "excerpt": "http://wordpress.org/export/1.2/excerpt/",
    }
    # WXRバージョンが異なる場合のフォールバック
    for ver in ["1.0", "1.1", "1.2"]:
        ns_wp = f"http://wordpress.org/export/{ver}/"
        if root.find(f".//{{{ns_wp}}}wxr_version") is not None:
            ns["wp"] = ns_wp
            ns["excerpt"] = f"http://wordpress.org/export/{ver}/excerpt/"
            break

    posts = []
    for item in root.findall(".//item"):
        post_type = item.findtext(f"{{{ns['wp']}}}post_type", "post")
        if post_type != "post":
            continue
        status = item.findtext(f"{{{ns['wp']}}}status", "publish")
        title = item.findtext("title", "")
        slug = item.findtext(f"{{{ns['wp']}}}post_name", "")
        date_str = item.findtext(f"{{{ns['wp']}}}post_date", "")
        date = date_str[:10] if date_str else ""

        content_encoded = item.findtext(f"{{{ns['content']}}}encoded", "")
        content = content_encoded.replace("\r\n", "\n")

        excerpt = item.findtext(f"{{{ns['excerpt']}}}encoded", "")

        categories = []
        tags = []
        for cat in item.findall("category"):
            domain = cat.get("domain", "")
            if domain == "category":
                categories.append(cat.text or "")
            elif domain == "post_tag":
                tags.append(cat.text or "")

        if not slug:
            slug = re.sub(r'[^a-z0-9]+', '-', title.lower()).strip('-')

        posts.append({
            "title": title,
            "slug": slug,
            "date": date,
            "category": ", ".join(categories) if categories else "",
            "tags": ", ".join(tags) if tags else "",
            "excerpt": excerpt or "",
            "content": content,
            "status": status,
        })

    posts.sort(key=lambda p: p.get("date", ""), reverse=True)
    return posts