feat: parse some other media like article

frontend/pages/sns.vue

@@ -54,7 +54,57 @@
                   {{ post.contentDesc }}
                 </div>
 
-                <div v-if="post.media && post.media.length > 0" class="mt-2" :class="{ 'privacy-blur': privacyMode }">
+                <div v-if="post.type === 3" class="mt-2 max-w-[360px]" :class="{ 'privacy-blur': privacyMode }">
+                  <a :href="post.contentUrl" target="_blank" class="block bg-gray-100 p-2 rounded-sm border border-gray-200 no-underline hover:bg-gray-200 transition-colors">
+                    <div class="flex items-center gap-3">
+                      <img
+                          v-if="post.contentUrl && !hasArticleThumbError(post.id)"
+                          :src="getArticleThumbProxyUrl(post.contentUrl)"
+                          class="w-12 h-12 object-cover flex-shrink-0 bg-white"
+                          alt=""
+                          @error="onArticleThumbError(post.id)"
+                      />
+                      <div v-else class="w-12 h-12 flex items-center justify-center bg-gray-200 text-gray-400 flex-shrink-0 text-xs">
+                        文章
+                      </div>
+
+                      <div class="flex-1 flex flex-col justify-between overflow-hidden h-12">
+                        <div class="text-[13px] text-gray-900 leading-tight line-clamp-2">{{ post.title }}</div>
+                      </div>
+                    </div>
+                    <div class="text-[11px] text-[#576b95] mt-1 pt-1 border-t border-gray-200/50">
+                      公众号文章分享
+                    </div>
+                  </a>
+                </div>
+
+                <div v-else-if="post.type === 28 && post.finderFeed && Object.keys(post.finderFeed).length > 0" class="mt-2 max-w-[360px]" :class="{ 'privacy-blur': privacyMode }">
+                  <div class="block bg-gray-100 p-2 rounded-sm border border-gray-200 no-underline hover:bg-gray-200 transition-colors">
+                    <!-- 浏览器没有看微信视频号的环境，暂时不进行跳转！！-->
+                    <div class="flex items-start gap-3">
+                      <div class="relative w-14 h-16 flex-shrink-0 bg-black overflow-hidden rounded-sm">
+                        <img
+                            v-if="post.finderFeed.thumbUrl"
+                            :src="getProxyExternalUrl(post.finderFeed.thumbUrl)"
+                            class="w-full h-full object-cover opacity-80"
+                            alt="finder cover"
+                        />
+                        <div class="absolute inset-0 flex items-center justify-center pointer-events-none">
+                          <svg class="w-5 h-5 text-white/90" fill="currentColor" viewBox="0 0 24 24"><path d="M8 5v14l11-7z"/></svg>
+                        </div>
+                      </div>
+                      <div class="flex-1 flex flex-col overflow-hidden">
+                        <div class="text-xs text-gray-500 truncate">{{ post.finderFeed.nickname }}</div>
+                        <div class="text-[13px] text-gray-900 leading-tight line-clamp-2 mt-[2px]">{{ post.finderFeed.desc || post.title }}</div>
+                      </div>
+                    </div>
+                    <div class="text-[11px] text-[#576b95] mt-1 pt-1 border-t border-gray-200/50">
+                      视频号 · 动态
+                    </div>
+                  </div>
+                </div>
+
+                <div v-else-if="post.media && post.media.length > 0" class="mt-2" :class="{ 'privacy-blur': privacyMode }">
                   <div v-if="post.media.length === 1" class="max-w-[360px]">
                     <div
                         v-if="!hasMediaError(post.id, 0) && getMediaThumbSrc(post, post.media[0], 0)"
@@ -107,7 +157,6 @@
                       />
                       <span v-else class="text-[10px] text-gray-400">图片失败</span>
 
-                      <!-- 视频缩略图的播放提示 -->
                       <div v-if="Number(m?.type || 0) === 6" class="absolute inset-0 flex items-center justify-center pointer-events-none">
                         <div class="w-10 h-10 rounded-full bg-black/45 flex items-center justify-center">
                           <svg class="w-5 h-5 text-white" fill="currentColor" viewBox="0 0 24 24"><path d="M8 5v14l11-7z"/></svg>
@@ -422,6 +471,21 @@ const onMediaError = (postId, idx) => {
   mediaErrors.value[mediaErrorKey(postId, idx)] = true
 }
 
+const articleThumbErrors = ref({})
+
+const hasArticleThumbError = (postId) => !!articleThumbErrors.value[postId]
+
+const onArticleThumbError = (postId) => {
+  articleThumbErrors.value[postId] = true
+}
+
+// （原有的函数保持不变）
+const getArticleThumbProxyUrl = (contentUrl) => {
+  const u = String(contentUrl || '').trim()
+  if (!u) return ''
+  return `${mediaBase}/api/sns/article_thumb?url=${encodeURIComponent(u)}`
+}
+
 // Right-click context menu (copy text / JSON) to help debug SNS parsing issues.
 const contextMenu = ref({ visible: false, x: 0, y: 0, post: null })
 
@@ -954,4 +1018,13 @@ onUnmounted(() => {
   document.removeEventListener('click', onGlobalClick)
   document.removeEventListener('keydown', onGlobalKeyDown)
 })
+
+const getProxyExternalUrl = (url) => {
+  // 目前难以计算enc，代理获取封面图（thumbnail）
+  const u = String(url || '').trim()
+  if (!u) return ''
+  return `${mediaBase}/api/chat/media/proxy_image?url=${encodeURIComponent(u)}`
+}
+
+
 </script>

src/wechat_decrypt_tool/routers/sns.py

@@ -4,6 +4,8 @@ from pathlib import Path
 import hashlib
 import json
 import re
+import httpx
+import html # 修复&转义的问题！！！
 import sqlite3
 import time
 import xml.etree.ElementTree as ET
@@ -93,6 +95,10 @@ def _parse_timeline_xml(xml_text: str, fallback_username: str) -> dict[str, Any]
         "media": [],
         "likes": [],
         "comments": [],
+        "type": 1,  # 默认类型
+        "title": "",
+        "contentUrl": "",
+        "finderFeed": {}
     }
 
     xml_str = str(xml_text or "").strip()
@@ -113,43 +119,62 @@ def _parse_timeline_xml(xml_text: str, fallback_username: str) -> dict[str, Any]
             if isinstance(v, str) and v.strip():
                 return v.strip()
         return ""
+    # &amp转义！！
+    def _clean_url(u: str) -> str:
+        if not u:
+            return ""
 
-    out["username"] = (
+        cleaned = html.unescape(u)
-        _find_text(".//TimelineObject/username", ".//TimelineObject/user_name", ".//TimelineObject/userName", ".//username")
+        cleaned = cleaned.replace("&", "&")
-        or fallback_username
+        return cleaned.strip()
-    )
+
+    out["username"] = _find_text(".//TimelineObject/username", ".//TimelineObject/user_name",
+                                 ".//username") or fallback_username
     out["createTime"] = _safe_int(_find_text(".//TimelineObject/createTime", ".//createTime"))
     out["contentDesc"] = _find_text(".//TimelineObject/contentDesc", ".//contentDesc")
     out["location"] = _build_location_text(root.find(".//location"))
 
+    # --- 提取内容类型 ---
+    post_type = _safe_int(_find_text(".//ContentObject/type", ".//type"))
+    out["type"] = post_type
+
+    # --- 如果是公众号文章 (Type 3) ---
+    if post_type == 3:
+        out["title"] = _find_text(".//ContentObject/title")
+        out["contentUrl"] = _clean_url(_find_text(".//ContentObject/contentUrl"))
+
+    # --- 如果是视频号 (Type 28) ---
+    if post_type == 28:
+        out["title"] = _find_text(".//ContentObject/title")
+        out["contentUrl"] = _clean_url(_find_text(".//ContentObject/contentUrl"))
+        out["finderFeed"] = {
+            "nickname": _find_text(".//finderFeed/nickname"),
+            "desc": _find_text(".//finderFeed/desc"),
+            "thumbUrl": _clean_url(
+                _find_text(".//finderFeed/mediaList/media/thumbUrl", ".//finderFeed/mediaList/media/coverUrl")),
+            "url": _clean_url(_find_text(".//finderFeed/mediaList/media/url"))
+        }
+
     media: list[dict[str, Any]] = []
     try:
         for m in root.findall(".//mediaList//media"):
             mt = _safe_int(m.findtext("type"))
+            url_el = m.find("url") if m.find("url") is not None else m.find("urlV")
+            thumb_el = m.find("thumb") if m.find("thumb") is not None else m.find("thumbV")
 
-            # WeChat stores important download/auth hints in attributes (key/enc_idx/token/md5...).
+            url = _clean_url(url_el.text if url_el is not None else "")
-            # NOTE: xml.etree.ElementTree.Element is falsy when it has no children.
+            thumb = _clean_url(thumb_el.text if thumb_el is not None else "")
-            # So we must check `is None` instead of using `or`, otherwise `<url>` would be treated as missing.
-            url_el = m.find("url")
-            if url_el is None:
-                url_el = m.find("urlV")
-            thumb_el = m.find("thumb")
-            if thumb_el is None:
-                thumb_el = m.find("thumbV")
-
-            url = str((url_el.text if url_el is not None else "") or "").strip()
-            thumb = str((thumb_el.text if thumb_el is not None else "") or "").strip()
 
             url_attrs = dict(url_el.attrib) if url_el is not None and url_el.attrib else {}
             thumb_attrs = dict(thumb_el.attrib) if thumb_el is not None and thumb_el.attrib else {}
-
             media_id = str(m.findtext("id") or "").strip()
             size_el = m.find("size")
             size = dict(size_el.attrib) if size_el is not None and size_el.attrib else {}
+
             if not url and not thumb:
                 continue
-            media.append(
+
-                {
+            media.append({
                 "type": mt,
                 "id": media_id,
                 "url": url,
@@ -157,10 +182,9 @@ def _parse_timeline_xml(xml_text: str, fallback_username: str) -> dict[str, Any]
                 "urlAttrs": url_attrs,
                 "thumbAttrs": thumb_attrs,
                 "size": size,
-                }
+            })
-            )
     except Exception:
-        media = []
+        pass
     out["media"] = media
 
     likes: list[str] = []
@@ -789,6 +813,11 @@ def list_sns_timeline(
 
             # Enrich with parsed XML when available.
             location = str(r.get("location") or "")
+
+            post_type = 1
+            title = ""
+            content_url = ""
+            finder_feed = {}
             try:
                 tid_u = int(r.get("id") or 0)
                 tid_s = (tid_u & 0xFFFFFFFFFFFFFFFF)
@@ -799,6 +828,12 @@ def list_sns_timeline(
                     parsed = _parse_timeline_xml(xml, uname)
                     if parsed.get("location"):
                         location = str(parsed.get("location") or "")
+
+                    post_type = parsed.get("type", 1)
+                    title = parsed.get("title", "")
+                    content_url = parsed.get("contentUrl", "")
+                    finder_feed = parsed.get("finderFeed", {})
+
                     pmedia = parsed.get("media") or []
                     if isinstance(pmedia, list) and isinstance(media, list) and pmedia:
                         # Merge by index (best-effort).
@@ -835,6 +870,10 @@ def list_sns_timeline(
                     "media": media,
                     "likes": likes,
                     "comments": comments,
+                    "type": post_type,
+                    "title": title,
+                    "contentUrl": content_url,
+                    "finderFeed": finder_feed,
                 }
             )
 
@@ -911,6 +950,10 @@ def list_sns_timeline(
                 "media": parsed.get("media") or [],
                 "likes": parsed.get("likes") or [],
                 "comments": parsed.get("comments") or [],
+                "type": parsed.get("type", 1),
+                "title": parsed.get("title", ""),
+                "contentUrl": parsed.get("contentUrl", ""),
+                "finderFeed": parsed.get("finderFeed", {}),
             }
         )
 
@@ -987,6 +1030,7 @@ async def get_sns_media(
         )
 
         if exact_match_path:
+            print(f"=====exact_match_path======={exact_match_path}=============")
             try:
                 payload, mtype = _read_and_maybe_decrypt_media(Path(exact_match_path), account_dir)
                 if payload and str(mtype or "").startswith("image/"):
@@ -997,6 +1041,8 @@ async def get_sns_media(
             except Exception:
                 pass
 
+        print("no exact match path")
+
     # 0) User-picked cache key override (stable across candidate ordering).
     pick_key = _normalize_hex32(pick)
     if pick_key:
@@ -1105,3 +1151,37 @@ async def get_sns_media(
         raise
     except Exception as e:
         raise HTTPException(status_code=502, detail=f"Fetch sns media failed: {e}")
+
+
+@router.get("/api/sns/article_thumb", summary="提取公众号文章封面图")
+async def proxy_article_thumb(url: str):
+    u = str(url or "").strip()
+    if not u.startswith("http"):
+        raise HTTPException(status_code=400, detail="Invalid URL")
+
+    try:
+        async with httpx.AsyncClient(timeout=10.0) as client:
+            headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
+            resp = await client.get(u, headers=headers)
+            resp.raise_for_status()
+            html_text = resp.text
+
+            match = re.search(r'["\'](https?://[^"\']*?mmbiz_[a-zA-Z]+[^"\']*?)["\']', html_text)
+
+            if not match:
+                raise HTTPException(status_code=404, detail="未在 HTML 中找到图片 URL")
+
+            img_url = match.group(1)
+            img_url = html.unescape(img_url).replace("&amp;", "&")
+
+            img_resp = await client.get(img_url, headers=headers)
+            img_resp.raise_for_status()
+
+            return Response(
+                content=img_resp.content,
+                media_type=img_resp.headers.get("Content-Type", "image/jpeg")
+            )
+
+    except Exception as e:
+        logger.warning(f"[sns] 提取公众号封面失败 url={u[:50]}... : {e}")
+        raise HTTPException(status_code=404, detail="无法获取文章封面")