nonebot-plugin-parser 2.0.1__tar.gz → 2.0.2__tar.gz

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nonebot-plugin-parser
-Version: 2.0.1
+Version: 2.0.2
 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
@@ -42,8 +42,7 @@ Description-Content-Type: text/markdown
 <br/>
 [![pre-commit](https://results.pre-commit.ci/badge/github/fllesser/nonebot-plugin-parser/master.svg)](https://results.pre-commit.ci/latest/github/fllesser/nonebot-plugin-parser/master)
 [![codecov](https://codecov.io/gh/fllesser/nonebot-plugin-parser/graph/badge.svg?token=VCS8IHSO7U)](https://codecov.io/gh/fllesser/nonebot-plugin-parser)
-[![pepy](https://static.pepy.tech/badge/nonebot-plugin-parser)](https://pepy.tech/projects/nonebot-plugin-parser)
-
+[![qqgroup](https://img.shields.io/badge/QQ%E7%BE%A4-820082006-orange?style=flat-square)](https://qm.qq.com/q/y4T4CjHimc)
 </div>
 
 > [!IMPORTANT]

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/README.md

@@ -12,8 +12,7 @@
 <br/>
 [![pre-commit](https://results.pre-commit.ci/badge/github/fllesser/nonebot-plugin-parser/master.svg)](https://results.pre-commit.ci/latest/github/fllesser/nonebot-plugin-parser/master)
 [![codecov](https://codecov.io/gh/fllesser/nonebot-plugin-parser/graph/badge.svg?token=VCS8IHSO7U)](https://codecov.io/gh/fllesser/nonebot-plugin-parser)
-[![pepy](https://static.pepy.tech/badge/nonebot-plugin-parser)](https://pepy.tech/projects/nonebot-plugin-parser)
-
+[![qqgroup](https://img.shields.io/badge/QQ%E7%BE%A4-820082006-orange?style=flat-square)](https://qm.qq.com/q/y4T4CjHimc)
 </div>
 
 > [!IMPORTANT]

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nonebot-plugin-parser"
-version = "2.0.1"
+version = "2.0.2"
 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"
@@ -185,7 +185,7 @@ build-backend = "uv_build"
 
 
 [tool.bumpversion]
-current_version = "2.0.1"
+current_version = "2.0.2"
 commit = true
 message = "🔖 release: bump vesion from {current_version} to {new_version}"
 tag = true

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/src/nonebot_plugin_parser/exception.py

@@ -18,3 +18,12 @@ class DownloadSizeLimitException(DownloadException):
     def __init__(self):
         self.message = "媒体大小超过配置限制，取消下载"
         super().__init__(self.message)
+
+
+class MultiException(ParseException):
+    """多个异常"""
+
+    def __init__(self, exceptions: list[ParseException]):
+        self.exceptions = exceptions
+        message = ",".join([e.message for e in exceptions])
+        super().__init__(f"[{message}]")

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/src/nonebot_plugin_parser/helper.py

@@ -7,7 +7,6 @@ from nonebot_plugin_alconna.uniseg import Segment, UniMessage, Voice
 from nonebot_plugin_alconna.uniseg.segment import CustomNode, Reference
 
 from .config import pconfig
-from .exception import ParseException
 
 
 class UniHelper:
@@ -103,7 +102,7 @@ class UniHelper:
         # 检测文件大小
         file_size_byte_count = int(video_path.stat().st_size)
         if file_size_byte_count == 0:
-            raise ParseException("视频文件大小为 0")
+            return Text("视频文件大小为 0")
         elif file_size_byte_count > 100 * 1024 * 1024:
             # 转为文件 Seg
             return cls.file_seg(video_path, display_name=video_path.name)

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/src/nonebot_plugin_parser/matchers/__init__.py

@@ -62,15 +62,11 @@ async def _(
     await _message_reaction(event, "resolving")
 
     cache_key = matched.group(0)
-    if result := RESULT_CACHE.get(cache_key):
-        logger.debug(f"命中缓存: {cache_key}")
-    else:
-        # 获取对应平台 parser
-        parser = KEYWORD_PARSER_MAP.get(keyword)
-
-        if parser is None:
-            logger.warning("没有找到对应平台的 Parser")
-            return
+    # 1. 获取缓存结果
+    result = RESULT_CACHE.get(cache_key)
+    if result is None:
+        # 2. 获取对应平台 parser
+        parser = KEYWORD_PARSER_MAP[keyword]
 
         try:
             result = await parser.parse(matched)
@@ -78,16 +74,22 @@ async def _(
             # await UniMessage(str(e)).send()
             await _message_reaction(event, "fail")
             raise
-
-        # 缓存解析结果
-        RESULT_CACHE[cache_key] = result
+    else:
+        logger.debug(f"命中缓存: {cache_key}, 结果: {result}")
 
     # 3. 渲染内容消息并发送
-    renderer = get_renderer(result.platform.name)
-    async for message in renderer.render_messages(result):
-        await message.send()
-
-    # 4. 添加成功的消息响应
+    try:
+        renderer = get_renderer(result.platform.name)
+        async for message in renderer.render_messages(result):
+            await message.send()
+    except Exception:
+        await _message_reaction(event, "fail")
+        raise
+
+    # 4. 无 raise 再缓存解析结果
+    RESULT_CACHE[cache_key] = result
+
+    # 5. 添加成功的消息响应
     await _message_reaction(event, "done")
 
 

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/src/nonebot_plugin_parser/parsers/data.py

@@ -1,13 +1,9 @@
 from asyncio import Task
 from dataclasses import dataclass, field
 from datetime import datetime
-from itertools import chain
 from pathlib import Path
 from typing import Any
 
-from ..exception import ParseException
-from ..helper import Segment, UniHelper, UniMessage
-
 
 @dataclass(repr=False)
 class MediaContent:
@@ -137,15 +133,6 @@ class ParseResult:
     repost: "ParseResult | None" = None
     """转发的内容"""
 
-    def __hash__(self) -> int:
-        return hash(
-            (
-                self.platform.name,
-                self.timestamp,
-                self.url,
-            )
-        )
-
     @property
     def header(self) -> str:
         header = self.platform.display_name
@@ -167,9 +154,6 @@ class ParseResult:
     def extra_info(self) -> str:
         return self.extra.get("info", "")
 
-    def formart_datetime(self, fmt: str = "%Y-%m-%d %H:%M:%S") -> str:
-        return datetime.fromtimestamp(self.timestamp).strftime(fmt) if self.timestamp else ""
-
     @property
     def video_contents(self) -> list[VideoContent]:
         return [cont for cont in self.contents if isinstance(cont, VideoContent)]
@@ -197,35 +181,8 @@ class ParseResult:
                 return await cont.get_cover_path()
         return None
 
-    async def contents_to_segs(self):
-        """将内容列表转换为消息段
-
-        Returns:
-            tuple[list[Segment], list[str | Segment | UniMessage]]: 消息段
-            separate_segs: 必须单独发送的消息段(视频、语音、文件)
-            forwardable_segs: 可以合并转发的消息段(文本和图片)
-        """
-        separate_segs: list[Segment] = []
-        forwardable_segs: list[str | Segment | UniMessage] = []
-
-        for cont in chain(self.contents, self.repost.contents if self.repost else ()):
-            try:
-                path = await cont.get_path()
-                match cont:
-                    case VideoContent():
-                        separate_segs.append(UniHelper.video_seg(path))
-                    case ImageContent():
-                        forwardable_segs.append(UniHelper.img_seg(path))
-                    case AudioContent():
-                        separate_segs.append(UniHelper.record_seg(path))
-                    case DynamicContent():
-                        forwardable_segs.append(UniHelper.video_seg(path))
-                    case GraphicsContent(_, text):
-                        forwardable_segs.append(text + UniHelper.img_seg(path))
-            except ParseException as e:
-                forwardable_segs.append(e.message)
-
-        return separate_segs, forwardable_segs
+    def formart_datetime(self, fmt: str = "%Y-%m-%d %H:%M:%S") -> str:
+        return datetime.fromtimestamp(self.timestamp).strftime(fmt) if self.timestamp else ""
 
     def __str__(self) -> str:
         return f"title: {self.title}\nplatform: {self.platform}\nauthor: {self.author}\ncontents: {self.contents}"

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/src/nonebot_plugin_parser/parsers/twitter.py

@@ -1,3 +1,4 @@
+from itertools import chain
 import re
 from typing import Any, ClassVar
 
@@ -73,41 +74,40 @@ class TwitterParser(BaseParser):
         from .data import ParseData
 
         soup = BeautifulSoup(html_content, "html.parser")
-        data = ParseData()
+        data = ParseData(name="无用户名")
 
         # 1. 提取缩略图链接
-        img_tag = soup.find("img")
-        if img_tag and isinstance(img_tag, Tag):
-            src = img_tag.get("src")
-            if src and isinstance(src, str):
-                data.cover_url = src
+        thumb_tag = soup.find("img")
+        if isinstance(thumb_tag, Tag):
+            if cover := thumb_tag.get("src"):
+                data.cover_url = str(cover)
 
         # 2. 提取下载链接
-        download_links = soup.find_all("a", class_="tw-button-dl")
-        # class="abutton is-success is-fullwidth  btn-premium mt-3"
-        download_items = soup.find_all("a", class_="abutton")
-        for link in download_links + download_items:
-            if isinstance(link, Tag) and (href := link.get("href")) and isinstance(href, str):
-                href = href
-            else:
+        tw_button_tags = soup.find_all("a", class_="tw-button-dl")
+        abutton_tags = soup.find_all("a", class_="abutton")
+        for tag in chain(tw_button_tags, abutton_tags):
+            if not isinstance(tag, Tag):
+                continue
+            href = tag.get("href")
+            if href is None:
                 continue
-            text = link.get_text(strip=True)
 
-            if "下载图片" in text:
-                # 从图片下载链接中提取原始图片URL
-                data.images_urls.append(href)
-            elif "下载 gif" in text:
-                data.dynamic_urls.append(href)  # GIF和MP4是同一个文件
-            elif "下载 MP4" in text:
-                # 从GIF/MP4下载链接中提取原始视频URL
+            href = str(href)
+            text = tag.get_text(strip=True)
+            if "下载 MP4" in text:
                 data.video_url = href
                 break
+            elif "下载图片" in text:
+                data.images_urls.append(href)
+            elif "下载 gif" in text:
+                data.dynamic_urls.append(href)
 
         # 3. 提取标题
         title_tag = soup.find("h3")
         if title_tag:
             data.title = title_tag.get_text(strip=True)
 
+        return data
         # # 4. 提取Twitter ID
         # twitter_id_input = soup.find("input", {"id": "TwitterId"})
         # if (
@@ -116,6 +116,3 @@ class TwitterParser(BaseParser):
         #     and (value := twitter_id_input.get("value"))
         #     and isinstance(value, str)
         # ):
-        data.name = "暂时无法获取用户名"
-
-        return data

nonebot_plugin_parser-2.0.2/src/nonebot_plugin_parser/renders/base.py

@@ -0,0 +1,73 @@
+from abc import ABC, abstractmethod
+from collections.abc import AsyncGenerator
+from itertools import chain
+from pathlib import Path
+from typing import Any, ClassVar
+
+from ..exception import MultiException, ParseException
+from ..helper import Segment, UniHelper, UniMessage
+from ..parsers import ParseResult
+from ..parsers.data import AudioContent, DynamicContent, GraphicsContent, ImageContent, VideoContent
+
+
+class BaseRenderer(ABC):
+    """统一的渲染器，将解析结果转换为消息"""
+
+    templates_dir: ClassVar[Path] = Path(__file__).parent / "templates"
+    """模板目录"""
+
+    @abstractmethod
+    async def render_messages(self, result: ParseResult) -> AsyncGenerator[UniMessage[Any], None]:
+        """消息生成器
+
+        Args:
+            result (ParseResult): 解析结果
+
+        Returns:
+            AsyncGenerator[UniMessage[Any], None]: 消息生成器
+        """
+        if False:
+            yield
+        raise NotImplementedError
+
+    async def render_contents(self, result: ParseResult) -> AsyncGenerator[UniMessage[Any], None]:
+        """渲染媒体内容消息
+
+        Args:
+            result (ParseResult): 解析结果
+
+        Returns:
+            AsyncGenerator[UniMessage[Any], None]: 消息生成器
+        """
+        raises: list[ParseException] = []
+        forwardable_segs: list[str | Segment | UniMessage] = []
+        for cont in chain(result.contents, result.repost.contents if result.repost else ()):
+            try:
+                path = await cont.get_path()
+            except ParseException as e:
+                forwardable_segs.append(e.message)
+                raises.append(e)
+                # 继续渲染其他内容
+                continue
+
+            match cont:
+                case VideoContent():
+                    yield UniMessage(UniHelper.video_seg(path))
+                case AudioContent():
+                    yield UniMessage(UniHelper.record_seg(path))
+                case ImageContent():
+                    forwardable_segs.append(UniHelper.img_seg(path))
+                case DynamicContent():
+                    forwardable_segs.append(UniHelper.video_seg(path))
+                case GraphicsContent(_, text):
+                    forwardable_segs.append(text + UniHelper.img_seg(path))
+
+        if forwardable_segs:
+            if all(isinstance(seg, str) for seg in forwardable_segs):
+                yield UniMessage(forwardable_segs)
+            else:
+                forward_msg = UniHelper.construct_forward_message(forwardable_segs)
+                yield UniMessage(forward_msg)
+
+        if raises:
+            raise MultiException(raises)

{nonebot_plugin_parser-2.0.1 → nonebot_plugin_parser-2.0.2}/src/nonebot_plugin_parser/renders/default.py

@@ -19,7 +19,13 @@ class DefaultRenderer(BaseRenderer):
             Generator[UniMessage[Any], None, None]: 消息生成器
         """
 
-        texts: list[str] = [result.header, result.text, result.extra_info, result.display_url]
+        texts: list[str] = [
+            result.header,
+            result.text,
+            result.extra_info,
+            result.display_url,
+            result.repost_display_url,
+        ]
         texts = [text for text in texts if text]
         texts[:-1] = [seg + "\n" for seg in texts[:-1]]
 

nonebot_plugin_parser-2.0.1/src/nonebot_plugin_parser/renders/base.py

@@ -1,54 +0,0 @@
-from abc import ABC, abstractmethod
-from collections.abc import AsyncGenerator
-from pathlib import Path
-from typing import Any, ClassVar
-
-from ..helper import UniHelper as UniHelper
-from ..helper import UniMessage as UniMessage
-from ..parsers import ParseResult as ParseResult
-
-
-class BaseRenderer(ABC):
-    """统一的渲染器，将解析结果转换为消息"""
-
-    templates_dir: ClassVar[Path] = Path(__file__).parent / "templates"
-    """模板目录"""
-
-    @abstractmethod
-    async def render_messages(self, result: ParseResult) -> AsyncGenerator[UniMessage[Any], None]:
-        """消息生成器
-
-        Args:
-            result (ParseResult): 解析结果
-
-        Returns:
-            AsyncGenerator[UniMessage[Any], None]: 消息生成器
-        """
-        if False:
-            yield
-        raise NotImplementedError
-
-    async def render_contents(self, result: ParseResult) -> AsyncGenerator[UniMessage[Any], None]:
-        """渲染内容消息
-
-        Args:
-            result (ParseResult): 解析结果
-
-        Returns:
-            AsyncGenerator[UniMessage[Any], None]: 消息生成器
-        """
-        separate_segs, forwardable_segs = await result.contents_to_segs()
-
-        # 处理可以合并转发的消息段
-        if forwardable_segs:
-            # 如果只有 str 类型, 则不使用转发消息
-            if all(isinstance(seg, str) for seg in forwardable_segs):
-                yield UniMessage(forwardable_segs)
-            else:
-                forward_msg = UniHelper.construct_forward_message(forwardable_segs)
-                yield UniMessage(forward_msg)
-
-        # 处理必须单独发送的消息段
-        if separate_segs:
-            for seg in separate_segs:
-                yield UniMessage(seg)