nonebot-plugin-parser 2.0.13__tar.gz → 2.1.0__tar.gz

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nonebot-plugin-parser
-Version: 2.0.13
+Version: 2.1.0
 Summary: NoneBot2 链接分享解析 Alconna 版, 通用媒体卡片渲染(PIL 实现), 支持 B站/抖音/快手/微博/小红书/youtube/tiktok/twitter/acfun/nga
 Keywords: nonebot,nonebot2,video,bilibili,youtube,tiktok,twitter,kuaishou,acfun,weibo,xiaohongshu,nga,douyin
 Author: fllesser
@@ -8,12 +8,12 @@ Author-email: fllesser <fllessive@gmail.com>
 Requires-Dist: msgspec>=0.19.0,<1.0.0
 Requires-Dist: httpx>=0.27.2,<1.0.0
 Requires-Dist: tqdm>=4.67.1,<5.0.0
-Requires-Dist: aiofiles>=24.1.0
+Requires-Dist: aiofiles>=25.1.0
 Requires-Dist: pillow>=11.0.0
 Requires-Dist: curl-cffi>=0.13.0,<1.0.0
-Requires-Dist: bilibili-api-python>=17.3.0,<18.0.0
+Requires-Dist: bilibili-api-python>=17.4.0,<18.0.0
 Requires-Dist: beautifulsoup4>=4.12.0,<5.0.0
-Requires-Dist: yt-dlp>=2025.9.26
+Requires-Dist: yt-dlp>=2025.10.14
 Requires-Dist: nonebot2>=2.4.3,<3.0.0
 Requires-Dist: nonebot-plugin-localstore>=0.7.4,<1.0.0
 Requires-Dist: nonebot-plugin-apscheduler>=0.5.0,<1.0.0

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nonebot-plugin-parser"
-version = "2.0.13"
+version = "2.1.0"
 description = "NoneBot2 链接分享解析 Alconna 版, 通用媒体卡片渲染(PIL 实现), 支持 B站/抖音/快手/微博/小红书/youtube/tiktok/twitter/acfun/nga"
 authors = [{ "name" = "fllesser", "email" = "fllessive@gmail.com" }]
 readme = "README.md"
@@ -24,14 +24,14 @@ dependencies = [
   "msgspec>=0.19.0,<1.0.0",
   "httpx>=0.27.2,<1.0.0",
   "tqdm>=4.67.1,<5.0.0",
-  "aiofiles>=24.1.0",
+  "aiofiles>=25.1.0",
   "pillow>=11.0.0",
 
   # 后续改为可选依赖
   "curl_cffi>=0.13.0,<1.0.0",
-  "bilibili-api-python>=17.3.0,<18.0.0",
+  "bilibili-api-python>=17.4.0,<18.0.0",
   "beautifulsoup4>=4.12.0,<5.0.0",
-  "yt-dlp>=2025.9.26",
+  "yt-dlp>=2025.10.14",
 
   "nonebot2>=2.4.3,<3.0.0",
   "nonebot-plugin-localstore>=0.7.4,<1.0.0",
@@ -68,18 +68,18 @@ test = [
 ]
 
 telegram = ["nonebot-adapter-telegram>=0.1.0b20"]
-pydantic_v1 = ["pydantic<2.0.0"]
-pydantic_v2 = ["pydantic>=2.0.0"]
+pydantic-v1 = ["pydantic<2.0.0"]                  # renovate:ignore
+pydantic-v2 = ["pydantic>=2.0.0"]
 
-all_extras = ["nonebot-plugin-htmlkit>=0.1.0rc3"]
+extras = ["nonebot-plugin-htmlkit>=0.1.0rc3"]
 
 [tool.uv]
 required-version = ">=0.9.2"
-default-groups = ["test", "dev", "all_extras"]
+default-groups = ["test", "dev", "extras"]
 conflicts = [
   [
-    { group = "pydantic_v1" },
-    { group = "pydantic_v2" },
+    { group = "pydantic-v1" },
+    { group = "pydantic-v2" },
     { group = "telegram" },
   ],
 ]
@@ -195,7 +195,7 @@ build-backend = "uv_build"
 
 
 [tool.bumpversion]
-current_version = "2.0.13"
+current_version = "2.1.0"
 commit = true
 message = "🔖 release: bump vesion from {current_version} to {new_version}"
 tag = true

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/src/nonebot_plugin_parser/__init__.py

@@ -12,7 +12,7 @@ from .utils import safe_unlink
 
 __plugin_meta__ = PluginMetadata(
     name="链接分享解析 Alconna 版",
-    description="全新通用媒体卡片渲染(PIL 实现)\n支持 B站/抖音/快手/微博/小红书/youtube/tiktok/twitter/acfun/nga",
+    description="通用媒体卡片渲染(PIL 实现)[B站|抖音|快手|微博|小红书|YouTube|TikTok|Twitter|AcFun|NGA]",
     usage="发送支持平台的(BV号/链接/小程序/卡片)即可",
     type="application",
     homepage="https://github.com/fllesser/nonebot-plugin-parser",

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/src/nonebot_plugin_parser/matchers/preprocess.py

@@ -4,7 +4,8 @@ from typing import Any, Literal
 
 from nonebot import logger
 from nonebot.matcher import Matcher
-from nonebot.message import event_preprocessor
+
+# from nonebot.message import event_preprocessor
 from nonebot.params import Depends
 from nonebot.plugin.on import get_matcher_source
 from nonebot.rule import Rule
@@ -42,30 +43,22 @@ def _kwd_regex_matched(state: T_State) -> re.Match[str] | None:
     return state.get(PSR_KWD_MATCHED_KEY)
 
 
-URL_KEY_MAPPING = {
-    "detail_1": "qqdocurl",
-    "news": "jumpUrl",
-    "music": "jumpUrl",
-}
-
-CHAR_REPLACEMENTS = {",": ",", "\\": "", "&": "&"}
-
-
-def _clean_url(url: str) -> str:
-    """清理 URL 中的特殊字符
-
+def _escape_raw(raw: str) -> str:
+    """
+    转义原始字符串中的特殊字符
     Args:
-        url: 原始 URL
+        raw: 原始字符串
 
     Returns:
-        str: 清理后的 URL
+        str: 转义后的字符串
     """
-    for old, new in CHAR_REPLACEMENTS.items():
-        url = url.replace(old, new)
-    return url
+    replacements = [(",", ","), ("\\", ""), ("&", "&")]
+    for old, new in replacements:
+        raw = raw.replace(old, new)
+    return raw
 
 
-def _extract_json_url(hyper: Hyper) -> str | None:
+def _extract_url(hyper: Hyper) -> str | None:
     """处理 JSON 类型的消息段，提取 URL
 
     Args:
@@ -75,12 +68,12 @@ def _extract_json_url(hyper: Hyper) -> str | None:
         Optional[str]: 提取的 URL, 如果提取失败则返回 None
     """
     data = hyper.data
-    raw_str = data.get("raw")
+    raw_str: str | None = data.get("raw")
 
     if raw_str is None:
         return None
-    # 处理转义字符
-    raw_str = raw_str.replace(",", ",")
+
+    raw_str = _escape_raw(raw_str)
 
     try:
         raw: dict[str, Any] = json.loads(raw_str)
@@ -92,24 +85,23 @@ def _extract_json_url(hyper: Hyper) -> str | None:
     if not meta:
         return None
 
-    for key1, key2 in URL_KEY_MAPPING.items():
-        if item := meta.get(key1):
-            if url := item.get(key2):
-                return _clean_url(url)
+    for key1, key2 in [("detail_1", "qqdocurl"), ("news", "jumpUrl"), ("music", "jumpUrl")]:
+        if url := meta.get(key1, {}).get(key2):
+            logger.debug(f"extract url from raw:{key1}:{key2}: {url}")
+            return url
     return None
 
 
-@event_preprocessor
-def extract_msg_text(message: UniMsg, state: T_State) -> None:
-    text: str | None = None
-
-    if hyper := message.get(Hyper, 1):
-        state[PSR_EXTRACT_KEY] = _extract_json_url(hyper.pop())
-        return
+# 纪念我写了一个存在了一年没人发现的 bug ()
+# @event_preprocessor
+# async def extract_msg_text(message: UniMsg, state: T_State):
+#     if hyper := next(iter(message.get(Hyper, 1)), None):
+#         state[PSR_EXTRACT_KEY] = _extract_url(hyper)
+#         return
 
-    # 提取纯文本
-    if text := message.extract_plain_text().strip():
-        state[PSR_EXTRACT_KEY] = text
+#     # 提取纯文本
+#     if text := message.extract_plain_text().strip():
+#         state[PSR_EXTRACT_KEY] = text
 
 
 class KeyPatternList(list[tuple[str, re.Pattern[str]]]):
@@ -138,14 +130,23 @@ class KeywordRegexRule:
     def __hash__(self) -> int:
         return hash(frozenset(self.key_pattern_list))
 
-    async def __call__(self, state: T_State, text: str = ExtractText()) -> bool:
+    async def __call__(self, message: UniMsg, state: T_State) -> bool:
+        text: str | None = None
+        if hyper := next(iter(message.get(Hyper, 1)), None):
+            text = _extract_url(hyper)
+
+        elif plain_text := message.extract_plain_text().strip():
+            text = plain_text
+
         if not text:
             return False
+
         for keyword, pattern in self.key_pattern_list:
             if keyword not in text:
                 continue
             if matched := pattern.search(text):
                 state[PSR_KWD_KEY] = keyword
+                state[PSR_EXTRACT_KEY] = text
                 state[PSR_KWD_MATCHED_KEY] = matched
                 return True
             logger.debug(f"keyword '{keyword}' is in '{text}', but not matched")

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/src/nonebot_plugin_parser/parsers/bilibili/__init__.py

@@ -165,7 +165,7 @@ class BilibiliParser(BaseParser):
         # 判断链接类型并解析
         logger.debug(f"解析其他类型链接: {url}")
         # 1. 动态
-        if "t.bilibili.com" in url:
+        if "t.bili" in url or "m.bili" in url:
             return await self.parse_dynamic(url)
 
         # 2.图文动态

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/src/nonebot_plugin_parser/parsers/data.py

@@ -160,7 +160,7 @@ class ParseResult:
     """渲染图片"""
 
     @property
-    def header(self) -> str:
+    def header(self) -> str | None:
         """头信息 仅用于 default render"""
         header = self.platform.display_name
         if self.author:

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/src/nonebot_plugin_parser/parsers/nga.py

@@ -38,6 +38,7 @@ class NGAParser(BaseParser):
             "Upgrade-Insecure-Requests": "1",
         }
         self.headers.update(extra_headers)
+        self.base_img_url = "https://img.nga.178.com/attachments"
 
     @staticmethod
     def nga_url(tid: str | int) -> str:
@@ -140,9 +141,13 @@ class NGAParser(BaseParser):
         # 提取文本 - postcontent0
         text = None
         content_tag = soup.find(id="postcontent0")
+        contents = []
         if content_tag and isinstance(content_tag, Tag):
             text = content_tag.get_text("\n", strip=True)
             # 清理 BBCode 标签并限制长度
+            img_urls: list[str] = re.findall(r"\[img\](.*?)\[/img\]", text)
+            img_urls = [self.base_img_url + url[1:] for url in img_urls]
+            contents.extend(self.create_image_contents(img_urls))
             text = self.clean_nga_text(text)
 
         return self.result(
@@ -150,6 +155,7 @@ class NGAParser(BaseParser):
             text=text,
             url=url,
             author=author,
+            contents=contents,
             timestamp=timestamp,
         )
 

{nonebot_plugin_parser-2.0.13 → nonebot_plugin_parser-2.1.0}/src/nonebot_plugin_parser/renders/default.py

@@ -20,20 +20,22 @@ class DefaultRenderer(BaseRenderer):
             Generator[UniMessage[Any], None, None]: 消息生成器
         """
 
-        texts = (
+        texts = [
             result.header,
             result.text,
             result.extra_info,
-            result.display_url,
-            result.repost_display_url,
-        )
+        ]
+
+        if self.append_url:
+            texts.extend((result.display_url, result.repost_display_url))
+
         texts = [text for text in texts if text]
         texts[:-1] = [text + "\n" for text in texts[:-1]]
-
         segs: list[Segment] = [Text(text) for text in texts]
-        cover_path = await result.cover_path
-        if cover_path is not None:
+
+        if cover_path := await result.cover_path:
             segs.insert(1, UniHelper.img_seg(cover_path))
+
         yield UniMessage(segs)
 
         async for message in self.render_contents(result):