更新爬虫方案文档，增加服务与支持-详细页面的输出信息；优化基础爬虫类，增强标题提取和内容去重逻辑；根据doc2md.py调整图片处理逻辑以改善Word文档生成效果。

zeroerr_crawler/config.py

@@ -102,8 +102,6 @@ CRAWL_TASKS = {
         "static_pages": [
             "/about/about-us.html",
             "/about/contact-us.html",
-            "/about/join-us.html",
-            "/about/152.html",  # 诚招代理
         ],
         "content_selector": "div.about_us1,div.page-title,div.about_company,div.contact_us,div.web_contact",  # 多区域布局
         "title_selector": "h1,h2",
@@ -129,5 +127,17 @@ CRAWL_TASKS = {
         "title_selector": "h1",
         "title_index": 0,
     },
+    # 服务与支持详细页面（从索引页提取）
+    "service_detail": {
+        "name": "服务与支持-详细页面",
+        "output_dir": "服务与支持",  # 输出到同一个目录
+        "index_url": "/Service/index.html",
+        "link_pattern": "/Service/",
+        "link_suffix": ".html",
+        "exclude_patterns": ["index.html"],
+        "content_selector": "div.news_text_p,div.news_text,div.content,div.content-section",  # 多种布局支持
+        "title_selector": "h1",
+        "title_index": 1,
+    },
 }