djhx-blogger 0.1.0__py3-none-any.whl

djhx_blogger/__main__.py

@@ -0,0 +1,4 @@
+from .cli import app
+
+if __name__ == '__main__':
+    app()

djhx_blogger/cli.py

@@ -0,0 +1,47 @@
+from pathlib import Path
+
+import typer
+
+from .deploy import compress_dir, deploy_blog
+from .gen import generate_blog
+from .log_config import log_init
+log_init()
+
+app = typer.Typer()
+
+
+@app.command()
+def run(
+    origin: Path = typer.Argument(..., exists=True, readable=True, help="原始博客内容目录（必填）"),
+    target: Path = typer.Option(
+        Path.cwd(),
+        "--target", "-t",
+        help="生成的静态博客输出目录，默认为当前目录。",
+    ),
+    server: str = typer.Option(
+        None,
+        "--server", "-s",
+        help="目标服务器（域名或 IP 地址），可选。",
+    ),
+    server_target: str = typer.Option(
+        None,
+        "--server-target", "-T",
+        help="目标服务器的部署路径"
+    ),
+    deploy: bool = typer.Option(
+        False,
+        "--deploy/--no-deploy",
+        help="是否将静态博客部署到远程服务器。",
+    ),
+):
+    typer.echo(f"原始目录: {origin}")
+    typer.echo(f"输出目录: {target}")
+    typer.echo(f"目标服务器: {server or '(未指定)'}")
+    typer.echo(f"目标服务器部署地址: {server_target}")
+    typer.echo(f"是否部署: {'是' if deploy else '否'}")
+
+    root_node = generate_blog(str(origin))
+
+    if deploy and server and server_target:
+        tar_path = compress_dir(root_node.destination_path)
+        deploy_blog(server, tar_path, server_target)

djhx_blogger/deploy.py

@@ -0,0 +1,65 @@
+import tarfile
+from getpass import getpass
+from pathlib import Path
+
+from fabric import Connection, Config
+
+from .log_config import app_logger
+
+logger = app_logger
+
+
+def compress_dir(blog_path: Path) -> Path:
+    """
+    将指定目录压缩为 public.tar.gz
+    """
+    logger.info(f'压缩目录: {blog_path}')
+    output_tar = blog_path.parent / 'public.tar.gz'
+
+    with tarfile.open(output_tar, "w:gz") as tar:
+        tar.add(str(blog_path), arcname="public")
+
+    logger.info(f'压缩完成: {output_tar}')
+    return output_tar
+
+
+def deploy_blog(server_name: str, local_tar_path: Path, remote_web_root: str):
+    """
+    将 tar.gz 文件部署到远程服务器
+    """
+    logger.info(f'开始部署 -> 服务器: {server_name}，文件: {local_tar_path}')
+
+    sudo_pass = getpass("[sudo]: ")
+    config = Config(overrides={'sudo': {'password': sudo_pass}})
+    c = Connection(host=server_name, user='koril', config=config, connect_kwargs={'password': sudo_pass})
+
+    remote_home_path = f'/home/{c.user}'
+    remote_tar_path = f'{remote_home_path}/{local_tar_path.name}'
+    remote_target_path = f'{remote_web_root}blog'
+
+    try:
+        # 上传
+        c.put(str(local_tar_path), remote=remote_home_path)
+        logger.info('上传完成')
+
+        # 删除旧备份
+        c.sudo(f'rm -rf {remote_web_root}blog.bak')
+        logger.info('旧 blog.bak 删除')
+
+        # 备份 blog
+        c.sudo(f'mv {remote_target_path} {remote_target_path}.bak')
+        logger.info('blog -> blog.bak')
+
+        # 移动 tar.gz 并解压
+        c.sudo(f'mv {remote_tar_path} {remote_web_root}')
+        c.sudo(f'tar -xzf {remote_web_root}{local_tar_path.name} -C {remote_web_root}')
+        logger.info('解压完成')
+
+        # 清理
+        c.sudo(f'rm {remote_web_root}{local_tar_path.name}')
+        c.sudo(f'mv {remote_web_root}public {remote_target_path}')
+        logger.info('部署完成')
+
+    except Exception as e:
+        logger.exception(f"部署失败")
+        raise

djhx_blogger/gen.py

@@ -0,0 +1,367 @@
+import shutil
+import time
+from collections import deque, OrderedDict
+from importlib import resources
+from pathlib import Path
+
+import markdown
+from bs4 import BeautifulSoup
+from jinja2 import Template
+
+from .log_config import app_logger
+
+logger = app_logger
+
+ignore_item = ['.git', 'LICENSE']
+
+def load_template(name: str) -> str:
+    """读取 static/template/ 下的模板文件"""
+    file_path = resources.files("djhx_blogger.static.template").joinpath(name)
+    return file_path.read_text(encoding="utf-8")
+
+
+class Node:
+    cache_map = {}
+
+    def __init__(self, source_path, destination_path, node_type):
+        # 该节点的源目录路径
+        self.source_path = source_path
+        # 该节点生成的结果目录路径
+        self.destination_path = destination_path
+        # 子节点
+        self.children = []
+        # 节点类型：
+        # 1. category 包含多个子目录
+        # 2. article 包含一个 index.md 文件和 images 目录
+        # 3. leaf index.md 或者 images 目录
+        self.node_type = node_type
+        # 描述分类或者文章的元信息（比如：文章的标题，简介和日期）
+        self.metadata = None
+
+        Node.cache_map[source_path] = self
+
+    def __str__(self):
+        return f'path={self.source_path}'
+
+
+def walk_dir(dir_path_str: str, destination_blog_dir_name: str) -> Node:
+    """
+    遍历目录，构造树结构
+    :param dir_path_str: 存放博客 md 文件的目录的字符串
+    :param destination_blog_dir_name: 生成博客目录的名称
+    :return: 树结构的根节点
+    """
+
+    start = int(time.time() * 1000)
+    q = deque()
+    dir_path = Path(dir_path_str)
+    q.append(dir_path)
+
+    # 生成目录的根路径
+    destination_root_dir = dir_path.parent.joinpath(destination_blog_dir_name)
+    logger.info(f'源路经: {dir_path}, 目标路径: {destination_root_dir}')
+
+    root = None
+
+    # 层次遍历
+    while q:
+        item = q.popleft()
+        if item.name in ignore_item:
+            logger.info(f'略过: {item.name}')
+            continue
+        if Path.is_dir(item):
+            [q.append(e) for e in item.iterdir()]
+
+        # node 类型判定
+        node_type = 'leaf'
+        if Path.is_dir(item):
+            node_type = 'category'
+            # 如果目录包含 index.md 则是文章目录节点
+            for e in item.iterdir():
+                if e.name == 'index.md':
+                    node_type = 'article'
+                    break
+
+        if not root:
+            root = Node(item, destination_root_dir, node_type)
+        else:
+            cur_node = Node.cache_map[item.parent]
+            # 计算相对路径
+            relative_path = item.relative_to(dir_path)
+            # 构造目标路径
+            destination_path = destination_root_dir / relative_path
+            if destination_path.name == 'index.md':
+                destination_path = destination_path.parent / Path('index.html')
+            n = Node(item, destination_path, node_type)
+            cur_node.children.append(n)
+    end = int(time.time() * 1000)
+    logger.info(f'构造树耗时: {end - start} ms')
+
+    return root
+
+
+def md_to_html(md_file_path: Path) -> str:
+    """
+    markdown -> html
+    :param md_file_path: markdown 文件的路径对象
+    :return: html str
+    """
+
+    def remove_metadata(content: str) -> str:
+        """
+        删除文章开头的 YAML 元信息
+        :param content: markdown 内容
+        """
+        lines = content.splitlines()
+        if lines and lines[0] == '---':
+            for i in range(1, len(lines)):
+                if lines[i] == '---':
+                    return '\n'.join(lines[i + 1:])
+        return md_content
+
+    with open(md_file_path, mode='r', encoding='utf-8') as md_file:
+        md_content = md_file.read()
+        md_content = remove_metadata(md_content)
+        return markdown.markdown(
+            md_content,
+            extensions=[
+                'markdown.extensions.toc',
+                'markdown.extensions.tables',
+                'markdown.extensions.sane_lists',
+                'markdown.extensions.fenced_code'
+            ]
+        )
+
+
+def gen_article_index(md_file_path: Path, article_name):
+
+    bs1 = BeautifulSoup(load_template('article.html'), "html.parser")
+    bs2 = BeautifulSoup(md_to_html(md_file_path), "html.parser")
+
+    article_metadata = read_metadata(md_file_path)
+
+    article_tag = bs1.find('article')
+    # 添加 h1 标题
+    h1_tag = bs1.new_tag('h1')
+    h1_tag.string = article_name
+    article_tag.insert(0, h1_tag)
+
+    # 添加日期信息
+    time_tag = bs1.new_tag('time', datetime=article_metadata["date"])
+    time_tag.string = '时间: ' + article_metadata["date"]
+
+    # 添加摘要信息
+    summary_tag = bs1.new_tag('p')
+    summary_tag.string = '摘要: ' + article_metadata["summary"]
+
+    # 包裹元信息
+    meta_wrapper = bs1.new_tag('div', **{"class": "article-meta"})
+    meta_wrapper.append(time_tag)
+    meta_wrapper.append(bs1.new_tag('br'))
+    meta_wrapper.append(summary_tag)
+
+    # 插入到 h1 之后
+    h1_tag.insert_after(meta_wrapper)
+
+    # 添加标题和正文之间的换行符
+    article_tag.append(bs1.new_tag('hr'))
+    # 添加正文内容
+    article_tag.append(bs2)
+    # 修改页面标题
+    bs1.find('title').string = f'文章 | {article_name}'
+
+    return bs1.prettify()
+
+
+def gen_category_index(categories: list, category_name) -> str:
+    template = Template(load_template('category.html'))
+    html = template.render(categories=categories, category_name=category_name)
+    return html
+
+
+def sort_categories(item):
+    """
+    对 categories 排序，type = category 排在所有 type = article 前
+    category 按照 name 字典顺序 a-z 排序
+    article 按照 metadata 的 date 字段（格式：2024-02-03T14:44:42+08:00）降序排列。
+    :param item:
+    :return:
+    """
+    from datetime import datetime
+    if item['type'] == 'category':
+        # 分类优先，按 name 排序
+        return 0, item['name'].lower()
+    elif item['type'] == 'article':
+        # 文章按日期降序排序，优先级次于 category
+        # 将日期解析为 datetime 对象，若无日期则排在最后
+        date = item['metadata'].get('date')
+        parsed_date = datetime.fromisoformat(date) if date else datetime(year=1970, month=1, day=1)
+        return 1, -parsed_date.timestamp()
+
+
+def gen_blog_dir(root: Node):
+    """
+    根据目录树构造博客目录
+    :param root: 树结构根节点
+    :return:
+    """
+
+    start = int(time.time() * 1000)
+
+    q = deque()
+    q.append(root)
+
+    # 清理之前生成的 root destination
+    if Path.exists(root.destination_path):
+        logger.info(f'存在目标目录: {root.destination_path}，进行删除')
+        shutil.rmtree(root.destination_path)
+
+    while q:
+        node = q.popleft()
+        [q.append(child) for child in node.children]
+
+        # 对三种不同类型的节点分别进行处理
+
+        if node.node_type == 'category' and node.source_path.name != 'images':
+            Path.mkdir(node.destination_path, parents=True, exist_ok=True)
+            category_index = node.destination_path / Path('index.html')
+            categories = []
+            for child in node.children:
+                if child:
+                    if child.node_type == 'article':
+                        child.metadata = read_metadata(child.source_path / Path('index.md'))
+                    relative_path = child.destination_path.name / Path('index.html')
+                    categories.append({
+                        'type': child.node_type,
+                        'name': child.destination_path.name,
+                        'href': relative_path,
+                        'metadata': child.metadata,
+                    })
+            categories.sort(key=sort_categories)
+            with open(category_index, mode='w', encoding='utf-8') as f:
+                f.write(gen_category_index(categories, node.source_path.name))
+
+        if node.node_type == 'category' and node.source_path.name == 'images':
+            Path.mkdir(node.destination_path, parents=True, exist_ok=True)
+
+        if node.node_type == 'article':
+            Path.mkdir(node.destination_path, parents=True, exist_ok=True)
+
+        if node.node_type == 'leaf':
+            Path.mkdir(node.destination_path.parent, parents=True, exist_ok=True)
+            if node.source_path.name == 'index.md':
+                with open(node.destination_path, mode='w', encoding='utf-8') as f:
+                    f.write(gen_article_index(node.source_path, node.source_path.parent.name))
+            else:
+                shutil.copy(node.source_path, node.destination_path)
+
+    end = int(time.time() * 1000)
+    logger.info(f'生成目标目录耗时: {end - start} ms')
+
+
+def gen_blog_archive(blog_dir_str, public_name, root: Node):
+    """
+    生成博客 archive 页面
+    按照年份分栏，日期排序，展示所有的博客文章
+    """
+
+    root_node_path = root.destination_path
+    blog_dir = Path(blog_dir_str)
+
+    q = deque()
+    q.append(root)
+    articles = []
+    while q:
+        node = q.popleft()
+        [q.append(child) for child in node.children]
+        if node.node_type == 'article':
+            articles.append(node)
+
+    archives = OrderedDict()
+    # 先将所有文章按日期降序排列
+    articles_sorted = sorted(articles, key=lambda a: a.metadata['date'], reverse=True)
+
+    for article in articles_sorted:
+        article_name = article.source_path.name
+        full_path = article.destination_path / Path('index.html')
+        base_path = blog_dir.with_name(public_name)
+        url = full_path.relative_to(base_path)
+
+        article_datetime = article.metadata.get('date')
+        article_year = article_datetime[:4]
+        article_date = article_datetime[:10]
+        if article_year not in archives:
+            archives[article_year] = {
+                'articles': [],
+                'total': 0,
+            }
+
+        archives[article_year]['articles'].append({
+            'date': article_date,
+            'title': article_name,
+            'url': url
+        })
+        archives[article_year]['total'] += 1
+
+
+    template = Template(load_template('archive.html'))
+    html = template.render(archives=archives)
+
+    root_node_path.joinpath('archive.html').write_text(data=html, encoding='utf-8')
+
+
+def cp_resource(dir_path_str: str):
+    """将包内 static 资源复制到目标目录下的 public/"""
+    dir_path = Path(dir_path_str)
+    public_dir = dir_path.parent / "public"
+
+    # 1. 复制 css/
+    css_src = str(resources.files("djhx_blogger.static").joinpath("css"))
+    css_dst = public_dir / "css"
+    shutil.copytree(css_src, css_dst, dirs_exist_ok=True)
+
+    # 2. 复制 images/
+    images_src = str(resources.files("djhx_blogger.static").joinpath("images"))
+    images_dst = public_dir / "images"
+    shutil.copytree(images_src, images_dst, dirs_exist_ok=True)
+
+
+def read_metadata(md_file_path):
+    import re
+    with open(md_file_path, 'r', encoding='utf-8') as file:
+        content = file.read()
+
+    # 正则提取元数据
+    match = re.match(r'^---\n([\s\S]*?)\n---\n', content)
+    if match:
+        metadata = match.group(1)
+        return parse_metadata(metadata)
+    return {}
+
+
+def parse_metadata(metadata):
+    """
+    将元数据解析为字典
+    title, date, summary
+    """
+    meta_dict = {}
+    for line in metadata.split('\n'):
+        if ':' in line:
+            key, value = map(str.strip, line.split(':', 1))
+            meta_dict[key] = value
+    return meta_dict
+
+
+def generate_blog(blog_dir: str):
+    start = time.time()
+    public_name = 'public'
+
+    logger.info("开始生成博客文件结构...")
+    root_node = walk_dir(blog_dir, public_name)
+    gen_blog_dir(root_node)
+    gen_blog_archive(blog_dir, public_name, root_node)
+    cp_resource(str(blog_dir))
+
+    end = time.time()
+    logger.info(f'生成静态博客 {blog_dir}, 任务完成, 总耗时: {int((end-start)*1000)} ms')
+    return root_node

djhx_blogger/log_config.py

@@ -0,0 +1,38 @@
+import logging.config
+
+log_name = 'djhx_blogger'
+
+log_config_dict = {
+    'version': 1,
+    'disable_existing_loggers': False,
+    'formatters': {
+        'default': {
+            'format': '[%(asctime)s] - %(levelname)-8s :: %(message)s',
+        }
+    },
+    'handlers': {
+        'console_handler': {
+            'class': 'logging.StreamHandler',
+            'stream': 'ext://sys.stdout',
+            'formatter': 'default',
+            'level': 'DEBUG',
+        },
+    },
+    'loggers': {
+        log_name: {
+            'handlers': ['console_handler'],
+            'level': 'DEBUG',
+            'propagate': False,
+        }
+    },
+    'root': {
+        'handlers': ['console_handler'],
+        'level': 'WARNING',
+    }
+}
+
+def log_init():
+    logging.config.dictConfig(log_config_dict)
+
+
+app_logger = logging.getLogger(log_name)

djhx_blogger-0.1.0.dist-info/METADATA

@@ -0,0 +1,12 @@
+Metadata-Version: 2.4
+Name: djhx-blogger
+Version: 0.1.0
+Summary: Add your description here
+Requires-Python: >=3.13
+License-File: LICENSE
+Requires-Dist: beautifulsoup4>=4.14.2
+Requires-Dist: fabric>=3.2.2
+Requires-Dist: jinja2>=3.1.6
+Requires-Dist: markdown>=3.9
+Requires-Dist: typer>=0.20.0
+Dynamic: license-file

djhx_blogger-0.1.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+djhx_blogger/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+djhx_blogger/__main__.py,sha256=MwMXMO3kuvG-luTG4lnLwjEnqnm20lI-amV9sETColo,61
+djhx_blogger/cli.py,sha256=v5VmlVI5sZEFca1C5VEmi7u9GMpvNBVd3NBLZSfKpks,1445
+djhx_blogger/deploy.py,sha256=tHJrOHaW8vQqN-YfpRLpjZOaUDXrWk_NVXnvPM014Hc,2056
+djhx_blogger/gen.py,sha256=AhShduRqJWYqdBPYVXnsSQ0v4Z9QWhtRI78olNIkHl4,12409
+djhx_blogger/log_config.py,sha256=aEvShHNahBO52w5I6WU4U2yTMAO7qIezcH2K1vSnbVo,871
+djhx_blogger-0.1.0.dist-info/licenses/LICENSE,sha256=Whbb1w0-YAwWeAth-B6_jXSPWx9Fum73B0R-Z_lzUjA,1085
+djhx_blogger-0.1.0.dist-info/METADATA,sha256=j0rHWln9Zz5bKDABfig0ceqROGGAxjO1Y3nqgFVIpHk,325
+djhx_blogger-0.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+djhx_blogger-0.1.0.dist-info/top_level.txt,sha256=FZNu1SEldZAx_j_NmZoOxLha4G8-0KndmlFiPjPfJIk,13
+djhx_blogger-0.1.0.dist-info/RECORD,,

djhx_blogger-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

djhx_blogger-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Koril33
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

djhx_blogger-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+djhx_blogger