feat: GEO/SEO structured data + search ranking tracker

2026-06-09 17:18:09 +08:00
parent 23ff63baa9
commit 8595bbc521
26 changed files with 961 additions and 51 deletions
@@ -5,7 +5,7 @@
 """
 import json, datetime, logging, sys, re
 from pathlib import Path
-from typing import Dict, List
+from typing import Dict, List, Optional

 PROJECT_ROOT = Path(__file__).parent.parent
 sys.path.insert(0, str(PROJECT_ROOT))
@@ -69,6 +69,90 @@ def _load_platform_config() -> dict:

 PLATFORM_CONFIG = _load_platform_config()

+PLATFORM_NAMES = {
+    "zhihu": "知乎专栏",
+    "wechat": "微信公众号",
+    "xiaohongshu": "小红书",
+}
+
+def _extract_description(content: str, max_len: int = 200) -> str:
+    """从 markdown 正文提取第一段有意义的文字作为 description"""
+    text = re.sub(r'^#\s+.*$', '', content, flags=re.MULTILINE)
+    text = re.sub(r'[#*>`~\[\]()\n]', ' ', text)
+    paragraphs = [p.strip() for p in text.split('\n\n') if p.strip()]
+    for p in paragraphs:
+        p = re.sub(r'\s+', ' ', p).strip()
+        if len(p) >= 15 and not p.startswith('http'):
+            return p[:max_len]
+    return content.replace('\n', ' ')[:max_len]
+
+
+def _extract_tags_list(tags_html: str) -> list:
+    """从 HTML tags 块提取纯标签列表"""
+    return re.findall(r'<span class="tag">([^<]+)</span>', tags_html)
+
+
+def inject_geo_metadata(html: str, title: str, content: str, platform: str, tags_html: str = "") -> str:
+    """向 HTML <head> 注入 SEO/GEO 结构化元数据"""
+    description = _extract_description(content)
+    tags_list = _extract_tags_list(tags_html)
+    platform_name = PLATFORM_NAMES.get(platform, platform)
+    today = datetime.datetime.now().strftime("%Y-%m-%d")
+
+    # JSON-LD Article schema
+    json_ld = {
+        "@context": "https://schema.org",
+        "@type": "Article",
+        "headline": title,
+        "description": description,
+        "datePublished": today,
+        "dateModified": today,
+        "author": {
+            "@type": "Organization",
+            "name": "宇之然",
+            "url": "https://yu-zhi-ran.com"
+        },
+        "publisher": {
+            "@type": "Organization",
+            "name": "宇之然",
+            "url": "https://yu-zhi-ran.com"
+        },
+        "mainEntityOfPage": {
+            "@type": "WebPage",
+            "@id": f"https://yu-zhi-ran.com/article/{platform}"
+        },
+    }
+    if tags_list:
+        json_ld["keywords"] = ", ".join(tags_list[:8])
+
+    json_ld_str = json.dumps(json_ld, ensure_ascii=False)
+
+    meta_tags = f"""
+  <meta name="description" content="{description}">
+  <meta name="keywords" content="{', '.join(tags_list[:8]) if tags_list else ''}">
+  <meta property="og:type" content="article">
+  <meta property="og:title" content="{title}">
+  <meta property="og:description" content="{description[:150]}">
+  <meta property="og:site_name" content="宇之然 | {platform_name}">
+  <meta property="article:published_time" content="{today}">
+  <meta property="article:author" content="宇之然">
+  <script type="application/ld+json">
+{json_ld_str}
+  </script>"""
+
+    # 注入到 </head> 之前
+    html = html.replace("</head>", meta_tags + "\n</head>")
+
+    # 为 wechat + xiaohongshu 追加 Weibo/Wechat 兼容 meta
+    if platform in ("wechat", "xiaohongshu"):
+        html = html.replace("</head>", """
+  <meta property="og:image" content="https://yu-zhi-ran.com/og-image.png">
+  <meta name="weibo:webpage:source" content="宇之然">
+</head>""")
+
+    return html
+
+
 class Writer:
    def __init__(self, topic_id: str):
        self.topic_id = topic_id
@@ -443,11 +527,12 @@ class Writer:
        else:
            html = html.replace("<!-- TAGS -->", "")

+        html = inject_geo_metadata(html, title, adapted, platform, tags_html)
        return html

-    def save_html(self, html: str, platform: str) -> str:
+    def save_html(self, html: str, platform: str, *, title: str = "", content: str = "") -> str:
        try:
-            save_article(self.topic_id, platform, html)
+            save_article(self.topic_id, platform, html, title=title, content=content)
            logger.info(f"文章写入数据库: {platform}_{self.topic_id}")
            return f"db:{platform}_{self.topic_id}"
        except Exception as e:
@@ -463,8 +548,9 @@ class Writer:
        results = {}
        for platform in ["zhihu", "wechat", "xiaohongshu"]:
            markdown = self.generate_platform_markdown(platform)
+            title = self._optimize_title(platform)
            html = self.generate_platform_html(markdown, platform)
-            results[platform] = str(self.save_html(html, platform))
+            results[platform] = str(self.save_html(html, platform, title=title, content=markdown))
        self.mark_draft()
        logger.info(f"撰写完成，状态已更新为待审查")
        return {"ok": True, "files": results}