nonebot-plugin-parser 2.0.8__tar.gz → 2.0.9__tar.gz

{nonebot_plugin_parser-2.0.8 → nonebot_plugin_parser-2.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nonebot-plugin-parser
-Version: 2.0.8
+Version: 2.0.9
 Summary: NoneBot2 链接分享解析器自动解析, BV号/链接/小程序/卡片 | B站/抖音/快手/微博/小红书/youtube/tiktok/twitter/acfun
 Keywords: nonebot,nonebot2,video,bilibili,youtube,tiktok,twitter,kuaishou,acfun,weibo,xiaohongshu,nga,douyin
 Author: fllesser

{nonebot_plugin_parser-2.0.8 → nonebot_plugin_parser-2.0.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nonebot-plugin-parser"
-version = "2.0.8"
+version = "2.0.9"
 description = "NoneBot2 链接分享解析器自动解析, BV号/链接/小程序/卡片 | B站/抖音/快手/微博/小红书/youtube/tiktok/twitter/acfun"
 authors = [{ "name" = "fllesser", "email" = "fllessive@gmail.com" }]
 readme = "README.md"
@@ -186,7 +186,7 @@ build-backend = "uv_build"
 
 
 [tool.bumpversion]
-current_version = "2.0.8"
+current_version = "2.0.9"
 commit = true
 message = "🔖 release: bump vesion from {current_version} to {new_version}"
 tag = true

{nonebot_plugin_parser-2.0.8 → nonebot_plugin_parser-2.0.9}/src/nonebot_plugin_parser/matchers/__init__.py

@@ -12,7 +12,7 @@ from ..config import pconfig
 from ..parsers import BaseParser, ParseResult
 from ..renders import get_renderer
 from ..utils import LimitedSizeDict
-from .preprocess import KeyPatternMatched, Keyword, on_keyword_regex
+from .preprocess import Keyword, KwdRegexMatched, on_keyword_regex
 
 
 def _get_enabled_parser_classes() -> list[type[BaseParser]]:
@@ -60,7 +60,7 @@ parser_matcher = on_keyword_regex(*_get_enabled_patterns())
 async def _(
     event: Event,
     keyword: str = Keyword(),
-    matched: re.Match[str] = KeyPatternMatched(),
+    matched: re.Match[str] = KwdRegexMatched(),
 ):
     """统一的解析处理器"""
     # 响应用户处理中

{nonebot_plugin_parser-2.0.8 → nonebot_plugin_parser-2.0.9}/src/nonebot_plugin_parser/matchers/preprocess.py

@@ -13,9 +13,9 @@ from nonebot_plugin_alconna.uniseg import Hyper, UniMsg
 
 from .filter import is_not_in_disabled_groups
 
-R_KEYWORD_KEY: Literal["_r_keyword"] = "_r_keyword"
-R_EXTRACT_KEY: Literal["_r_extract"] = "_r_extract"
-R_KEY_REGEX_MATCHED_KEY: Literal["_r_key_regex_matched"] = "_r_key_regex_matched"
+PSR_KWD_KEY: Literal["_psr_kwd"] = "_psr_kwd"
+PSR_EXTRACT_KEY: Literal["_psr_extract"] = "_psr_extract"
+PSR_KWD_MATCHED_KEY: Literal["_psr_kwd_matched"] = "_psr_kwd_matched"
 
 
 def ExtractText() -> str:
@@ -23,7 +23,7 @@ def ExtractText() -> str:
 
 
 def _extract_text(state: T_State) -> str | None:
-    return state.get(R_EXTRACT_KEY)
+    return state.get(PSR_EXTRACT_KEY)
 
 
 def Keyword() -> str:
@@ -31,15 +31,15 @@ def Keyword() -> str:
 
 
 def _keyword(state: T_State) -> str | None:
-    return state.get(R_KEYWORD_KEY)
+    return state.get(PSR_KWD_KEY)
 
 
-def KeyPatternMatched() -> re.Match[str]:
-    return Depends(_key_pattern_matched)
+def KwdRegexMatched() -> re.Match[str]:
+    return Depends(_kwd_regex_matched)
 
 
-def _key_pattern_matched(state: T_State) -> re.Match[str] | None:
-    return state.get(R_KEY_REGEX_MATCHED_KEY)
+def _kwd_regex_matched(state: T_State) -> re.Match[str] | None:
+    return state.get(PSR_KWD_MATCHED_KEY)
 
 
 URL_KEY_MAPPING = {
@@ -104,12 +104,12 @@ def extract_msg_text(message: UniMsg, state: T_State) -> None:
     text: str | None = None
 
     if hyper := message.get(Hyper, 1):
-        state[R_EXTRACT_KEY] = _extract_json_url(hyper.pop())
+        state[PSR_EXTRACT_KEY] = _extract_json_url(hyper.pop())
         return
 
     # 提取纯文本
     if text := message.extract_plain_text().strip():
-        state[R_EXTRACT_KEY] = text
+        state[PSR_EXTRACT_KEY] = text
 
 
 class KeyPatternList(list[tuple[str, re.Pattern[str]]]):
@@ -145,8 +145,8 @@ class KeywordRegexRule:
             if keyword not in text:
                 continue
             if matched := pattern.search(text):
-                state[R_KEYWORD_KEY] = keyword
-                state[R_KEY_REGEX_MATCHED_KEY] = matched
+                state[PSR_KWD_KEY] = keyword
+                state[PSR_KWD_MATCHED_KEY] = matched
                 return True
             logger.debug(f"keyword '{keyword}' is in '{text}', but not matched")
         return False

{nonebot_plugin_parser-2.0.8 → nonebot_plugin_parser-2.0.9}/src/nonebot_plugin_parser/parsers/bilibili/__init__.py

@@ -61,21 +61,23 @@ class BilibiliParser(BaseParser):
         """
         # 从匹配对象中获取原始URL, 视频ID, 页码
         url, video_id, page_num = str(matched.group(0)), str(matched.group(1)), matched.group(2)
-
         # 处理短链
         if "b23.tv" in url or "bili2233.cn" in url:
             url = await self.get_redirect_url(url, self.headers)
 
         if not video_id:
-            if _matched := re.search(r"(BV[\dA-Za-z]{10})[^?]*?(?:\?[^#]*?p=(\d{1,3}))?", url):
-                video_id = _matched.group(1)
-                page_num = _matched.group(2)
-            elif _matched := re.search(r"av(\d{6,})[^?]*?(?:\?[^#]*?p=(\d{1,3}))?", url):
-                video_id = _matched.group(1)
-                page_num = _matched.group(2)
+            # https://www.bilibili.com/video/BV1584y167sD?a=20&p=40
+            if _matched := re.search(r"(?:(BV[\dA-Za-z]{10})|av(\d{6,}))", url):
+                video_id = _matched.group(1) or _matched.group(2)
             else:
                 return await self.parse_others(url)
 
+            # 匹配页码参数
+            if _matched := re.search(r"(?:&|\?)p=(\d{1,3})", url):
+                page_num = _matched.group(1)
+            else:
+                page_num = None
+
         avid, bvid = None, None
         page_num = int(page_num) if page_num and page_num.isdigit() else 1
 
@@ -282,18 +284,11 @@ class BilibiliParser(BaseParser):
         current_text = ""
 
         for node in opus_data.gen_text_img():
-            match node:
-                case ImageNode():
-                    contents.append(
-                        self.create_graphics_content(
-                            node.url,
-                            current_text.strip(),
-                            node.alt,
-                        )
-                    )
-                    current_text = ""
-                case TextNode():
-                    current_text += node.text
+            if isinstance(node, ImageNode):
+                contents.append(self.create_graphics_content(node.url, current_text.strip(), node.alt))
+                current_text = ""
+            elif isinstance(node, TextNode):
+                current_text += node.text
 
         return self.result(
             title=opus_data.title,
@@ -358,18 +353,11 @@ class BilibiliParser(BaseParser):
         contents: list[MediaContent] = []
         current_text = ""
         for child in article_info.gen_text_img():
-            match child:
-                case ImageNode():
-                    contents.append(
-                        self.create_graphics_content(
-                            child.url,
-                            current_text.strip(),
-                            child.alt,
-                        )
-                    )
-                    current_text = ""
-                case TextNode():
-                    current_text += child.text
+            if isinstance(child, ImageNode):
+                contents.append(self.create_graphics_content(child.url, current_text.strip(), child.alt))
+                current_text = ""
+            elif isinstance(child, TextNode):
+                current_text += child.text
 
         author = self.create_author(*article_info.author_info)
 

{nonebot_plugin_parser-2.0.8 → nonebot_plugin_parser-2.0.9}/src/nonebot_plugin_parser/renders/base.py

@@ -44,6 +44,7 @@ class BaseRenderer(ABC):
         """
         failed_count = 0
         forwardable_segs: list[ForwardNodeInner] = []
+        dynamic_segs: list[ForwardNodeInner] = []
 
         for cont in chain(result.contents, result.repost.contents if result.repost else ()):
             try:
@@ -65,7 +66,7 @@ class BaseRenderer(ABC):
                 case ImageContent():
                     forwardable_segs.append(UniHelper.img_seg(path))
                 case DynamicContent():
-                    forwardable_segs.append(UniHelper.video_seg(path))
+                    dynamic_segs.append(UniHelper.video_seg(path))
                 case GraphicsContent() as graphics:
                     graphics_msg = UniHelper.img_seg(path)
                     if graphics.text is not None:
@@ -76,11 +77,13 @@ class BaseRenderer(ABC):
 
         if forwardable_segs:
             if pconfig.need_forward_contents or len(forwardable_segs) > 4:
-                forward_msg = UniHelper.construct_forward_message(forwardable_segs)
+                forward_msg = UniHelper.construct_forward_message(forwardable_segs + dynamic_segs)
                 yield UniMessage(forward_msg)
             else:
-                for seg in forwardable_segs:
-                    yield UniMessage(seg)
+                yield UniMessage(forwardable_segs)
+
+                if dynamic_segs:
+                    yield UniMessage(UniHelper.construct_forward_message(dynamic_segs))
 
         if failed_count > 0:
             message = f"{failed_count} 项媒体下载失败"