上传并发布至博客园脚本

目录

参考官方文档

MetaWeblog

上传图片

基础数据

blog_id = "blog_id"
username = "username"
access_token = "access_token"
rpc_url = "https://rpc.cnblogs.com/metaweblog/" + blog_id
file_path = "image path"

文件数据

import mimetypes
from xmlrpc.client import Binary

mime_type, _ = mimetypes.guess_type(file_path)
mime_type = "application/octet-stream" if mime_type is None else mime_type
with open(file_path, "rb") as f:
    image_data = f.read()
file_data ={
    "name": "image name",
    "type": mime_type,
    "bits": Binary(image_data),
}

上传

from xmlrpc.client import ServerProxy

# 上传
server = ServerProxy(rpc_url)
result = server.metaWeblog.newMediaObject(
    blog_id,
    username,
    access_token,
    struct,
)

# 解析结果
if isinstance(result, dict) and "url" in result:
    img_url = result["url"]

上传文章

基础数据

blog_id = "blog_id"
username = "username"
access_token = "access_token"
rpc_url = "https://rpc.cnblogs.com/metaweblog/" + blog_id
blog_url = "https://www.cnblogs.com/" + blog_id
file_path = "markdown path"
with open(file_path, "r", encoding="utf-8") as f:
    content = f.read()

解析并上传文档中图片

这里未考虑文档中网络图片的情况，还可以优化

import re

patterns = [
    r"!\[.*?\]\((.*?)\)",
    r"<img.*?src=\"(.*?)\".*?>",
]
image_paths = {}
for pattern in patterns:
    image_paths |= {
        path: os.path.normpath(os.path.join(os.path.dirname(markdown_path), path))
        for path in re.findall(pattern, content)
    }

上传参考上传图片部分

# 上传后得到字典 img_path->img_url
# 以下内容只是例子
image_urls = {
    "C:\\test.png": "http://xxx.xxx.xxx/1234567890.jpg"
}

解析 YAML Front Matter 获取

YAML Front Matter - Typora Support

# 根据内容分割
parts = content.split("---", 2)

# 解析YAML Front Matter
front_matter_content = parts[1].strip()
markdown_content = parts[2].strip()
front_matter = yaml.safe_load(front_matter_content)
if front_matter is None:
    front_matter = {}

# 构建Post结构体字典
post_args = {}
# 标题
post_args["title"] = front_matter.get("title", Path(file_path).stem)
# 正文
post_args["description"] = markdown_content
# 当前时间
post_args["dateCreated"] = datetime.now()
# 分类
categories = front_matter.get("categories", [])
if isinstance(categories, list):
    post_args["categories"] = categories
elif isinstance(categories, str):
    post_args["categories"] = [categories]
else:
    post_args["categories"] = []
if "[Markdown]" in post_args["categories"]:       # 这里注意，如果上传格式是Markdown不是HTML，需要在分类中添加"[Markdown]"
    post_args["categories"].remove("[Markdown]")
post_args["categories"].insert(0, "[Markdown]")
# 标签 (tags/keywords -> mt_keywords)
tags = front_matter.get("tags", [])
keywords = front_matter.get("keywords", "")
if tags:
    if isinstance(tags, list):
        post_args["mt_keywords"] = ", ".join(tags)
    elif isinstance(tags, str):
        post_args["mt_keywords"] = tags
elif keywords:
    post_args["mt_keywords"] = keywords
# 其他可选的metaweblog字段
slug = front_matter.get("slug") or front_matter.get("wp_slug")
if slug:
    post_args["wp_slug"] = slug
if "mt_allow_comments" in front_matter:
    post_args["mt_allow_comments"] = front_matter["mt_allow_comments"]
if "mt_allow_pings" in front_matter:
    post_args["mt_allow_pings"] = front_matter["mt_allow_pings"]
if "mt_excerpt" in front_matter:
    post_args["mt_excerpt"] = front_matter["mt_excerpt"]
if "mt_text_more" in front_matter:
    post_args["mt_text_more"] = front_matter["mt_text_more"]

上传

修改文档中的图片路径

for k, v in img_path.items():
    post_args["description"] = post_args["description"].replace(
        k, image_urls.get(v, v)
    )

上传文章

post_id = self.server.metaWeblog.newPost(
            blog_id, username, access_token, post_args, True
        )
return blog_url + "/p/" + str(post_id)
posted @ 2025-08-30 13:31  ling-yuan  阅读(12)  评论(0)    收藏  举报