nonebot-plugin-parser 2.3.5__tar.gz → 2.3.7__tar.gz

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nonebot-plugin-parser
-Version: 2.3.5
+Version: 2.3.7
 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: acfun,bilibili,douyin,kuaishou,nga,nonebot,nonebot2,tiktok,twitter,video,weibo,xiaohongshu,youtube
 Author: fllesser
@@ -23,12 +23,12 @@ Requires-Dist: nonebot2>=2.4.3,<3.0.0
 Requires-Dist: pillow>=11.0.0
 Requires-Dist: tqdm>=4.67.1,<5.0.0
 Requires-Dist: aiofiles>=25.1.0
-Requires-Dist: curl-cffi>=0.13.0,<1.0.0
 Requires-Dist: httpx>=0.27.2,<1.0.0
 Requires-Dist: msgspec>=0.20.0,<1.0.0
 Requires-Dist: apilmoji[tqdm]>=0.2.4,<1.0.0
 Requires-Dist: beautifulsoup4>=4.12.0,<5.0.0
-Requires-Dist: bilibili-api-python>=17.4.0,<18.0.0
+Requires-Dist: curl-cffi>=0.13.0,!=0.14.0,<1.0.0
+Requires-Dist: bilibili-api-python>=17.4.1,<18.0.0
 Requires-Dist: nonebot-plugin-alconna>=0.59.4,<1.0.0
 Requires-Dist: nonebot-plugin-apscheduler>=0.5.0,<1.0.0
 Requires-Dist: nonebot-plugin-localstore>=0.7.4,<1.0.0
@@ -263,6 +263,9 @@ parser_bili_video_codes='["avc", "av01", "hev"]'
 # 360p(16), 480p(32), 720p(64), 1080p(80), 1080p+(112), 1080p_60(116), 4k(120)
 parser_bili_video_quality=80
 
+# [可选] 小红书 Cookie, 部分链接解析有水印，可填
+parser_xhs_ck=""
+
 # [可选] Youtube Cookie, Youtube 视频因人机检测下载失败，需填
 parser_ytb_ck=""
 

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/README.md

@@ -209,6 +209,9 @@ parser_bili_video_codes='["avc", "av01", "hev"]'
 # 360p(16), 480p(32), 720p(64), 1080p(80), 1080p+(112), 1080p_60(116), 4k(120)
 parser_bili_video_quality=80
 
+# [可选] 小红书 Cookie, 部分链接解析有水印，可填
+parser_xhs_ck=""
+
 # [可选] Youtube Cookie, Youtube 视频因人机检测下载失败，需填
 parser_ytb_ck=""
 

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nonebot-plugin-parser"
-version = "2.3.5"
+version = "2.3.7"
 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"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -43,12 +43,12 @@ dependencies = [
   "pillow>=11.0.0",
   "tqdm>=4.67.1,<5.0.0",
   "aiofiles>=25.1.0",
-  "curl_cffi>=0.13.0,<1.0.0",
   "httpx>=0.27.2,<1.0.0",
   "msgspec>=0.20.0,<1.0.0",
   "apilmoji[tqdm]>=0.2.4,<1.0.0",
   "beautifulsoup4>=4.12.0,<5.0.0",
-  "bilibili-api-python>=17.4.0,<18.0.0",
+  "curl_cffi>=0.13.0,<1.0.0,!=0.14.0",
+  "bilibili-api-python>=17.4.1,<18.0.0",
   "nonebot-plugin-alconna>=0.59.4,<1.0.0",
   "nonebot-plugin-apscheduler>=0.5.0,<1.0.0",
   "nonebot-plugin-localstore>=0.7.4,<1.0.0",
@@ -118,7 +118,7 @@ nonebug = { git = "https://github.com/nonebot/nonebug" }
 [tool.bumpversion]
 tag = true
 commit = true
-current_version = "2.3.5"
+current_version = "2.3.7"
 message = "release: bump vesion from {current_version} to {new_version}"
 
 [[tool.bumpversion.files]]

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/config.py

@@ -20,6 +20,8 @@ class Config(BaseModel):
     """bilibili cookies"""
     parser_ytb_ck: str | None = None
     """youtube cookies"""
+    parser_xhs_ck: str | None = None
+    """小红书 cookies"""
     parser_proxy: str | None = None
     """代理"""
     parser_need_upload: bool = False
@@ -113,6 +115,11 @@ class Config(BaseModel):
         """youtube cookies"""
         return self.parser_ytb_ck
 
+    @property
+    def xhs_ck(self) -> str | None:
+        """小红书 cookies"""
+        return self.parser_xhs_ck
+
     @property
     def proxy(self) -> str | None:
         """代理"""

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/matchers/rule.py

@@ -1,5 +1,5 @@
 import re
-from typing import Any, Literal
+from typing import Literal
 
 import msgspec
 from nonebot import logger
@@ -19,6 +19,32 @@ from ..config import gconfig
 PSR_SEARCHED_KEY: Literal["psr-searched"] = "psr-searched"
 
 
+# 定义 JSON 卡片的数据结构
+class MetaDetail(msgspec.Struct):
+    qqdocurl: str | None = None
+
+
+class MetaNews(msgspec.Struct):
+    jumpUrl: str | None = None
+
+
+class MetaMusic(msgspec.Struct):
+    jumpUrl: str | None = None
+
+
+class Meta(msgspec.Struct):
+    detail_1: MetaDetail | None = None
+    news: MetaNews | None = None
+    music: MetaMusic | None = None
+
+
+class RawData(msgspec.Struct):
+    meta: Meta | None = None
+
+
+raw_decoder = msgspec.json.Decoder(RawData)
+
+
 class SearchResult:
     """匹配结果"""
 
@@ -45,24 +71,6 @@ def _searched(state: T_State) -> SearchResult | None:
     return state.get(PSR_SEARCHED_KEY)
 
 
-def _escape_raw(raw: str) -> str:
-    """
-    转义原始字符串中的特殊字符
-    Args:
-        raw: 原始字符串
-
-    Returns:
-        str: 转义后的字符串
-    """
-    replacements = [
-        ("\\", ""),
-        ("&", "&"),
-    ]
-    for old, new in replacements:
-        raw = raw.replace(old, new)
-    return raw
-
-
 def _extract_url(hyper: Hyper) -> str | None:
     """处理 JSON 类型的消息段，提取 URL
 
@@ -79,24 +87,25 @@ def _extract_url(hyper: Hyper) -> str | None:
         return None
 
     try:
-        raw: dict[str, Any] = msgspec.json.decode(raw_str)
+        raw = raw_decoder.decode(raw_str)
     except msgspec.DecodeError:
         logger.exception(f"json 卡片解析失败: {raw_str}")
         return None
 
-    meta: dict[str, Any] | None = raw.get("meta")
-    if not meta:
+    if not raw.meta:
         return None
 
-    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:meta:{key1}:{key2}: {url}")
-            return url
-    return None
+    meta, url = raw.meta, None
+
+    if meta.detail_1:
+        url = meta.detail_1.qqdocurl
+    elif meta.news:
+        url = meta.news.jumpUrl
+    elif meta.music:
+        url = meta.music.jumpUrl
+
+    logger.debug(f"extract url[{url}] from raw#meta[{meta}]")
+    return url
 
 
 def _extract_text(message: UniMsg) -> str | None:

nonebot_plugin_parser-2.3.7/src/nonebot_plugin_parser/parsers/acfun/__init__.py

@@ -0,0 +1,151 @@
+import re
+import asyncio
+from typing import ClassVar
+from pathlib import Path
+from urllib.parse import urljoin
+
+import aiofiles
+from httpx import HTTPError, AsyncClient
+from nonebot import logger
+
+from ..base import (
+    DOWNLOADER,
+    COMMON_TIMEOUT,
+    DOWNLOAD_TIMEOUT,
+    Platform,
+    BaseParser,
+    PlatformEnum,
+    ParseException,
+    DownloadException,
+    DurationLimitException,
+    handle,
+    pconfig,
+)
+
+
+class AcfunParser(BaseParser):
+    # 平台信息
+    platform: ClassVar[Platform] = Platform(name=PlatformEnum.ACFUN, display_name="猴山")
+
+    def __init__(self):
+        super().__init__()
+        self.headers["referer"] = "https://www.acfun.cn/"
+
+    @handle("acfun.cn", r"(?:ac=|/ac)(?P<acid>\d+)")
+    async def _parse(self, searched: re.Match[str]):
+        acid = int(searched.group("acid"))
+        url = f"https://www.acfun.cn/v/ac{acid}"
+
+        video_info = await self.parse_video_info(url)
+        author = self.create_author(video_info.name, video_info.avatar_url)
+
+        video_task = asyncio.create_task(
+            self.download_video(
+                video_info.m3u8_url,
+                f"acfun_{acid}.mp4",
+                video_info.duration,
+            )
+        )
+
+        video_content = self.create_video_content(video_task, cover_url=video_info.coverUrl)
+
+        return self.result(
+            title=video_info.title,
+            text=video_info.text,
+            author=author,
+            timestamp=video_info.timestamp,
+            contents=[video_content],
+        )
+
+    async def parse_video_info(self, url: str):
+        """解析acfun链接获取详细信息
+
+        Args:
+            url (str): 链接
+
+        Returns:
+            video.VideoInfo
+        """
+        from . import video
+
+        # 拼接查询参数
+        url = f"{url}?quickViewId=videoInfo_new&ajaxpipe=1"
+
+        async with AsyncClient(headers=self.headers, timeout=COMMON_TIMEOUT) as client:
+            response = await client.get(url)
+            response.raise_for_status()
+            raw = response.text
+
+        matched = re.search(r"window\.videoInfo =(.*?)</script>", raw)
+        if not matched:
+            raise ParseException("解析 acfun 视频信息失败")
+
+        raw = str(matched.group(1))
+        raw = re.sub(r'\\{1,4}"', '"', raw)
+        raw = raw.replace('"{', "{").replace('}"', "}")
+        return video.decoder.decode(raw)
+
+    async def download_video(self, m3u8_url: str, file_name: str, duration: int) -> Path:
+        """下载acfun视频
+
+        Args:
+            m3u8_url (str): m3u8链接
+            file_name (str): 文件名
+            duration (int): 视频时长(秒)
+
+        Returns:
+            Path: 下载的mp4文件
+        """
+
+        if duration >= pconfig.duration_maximum:
+            raise DurationLimitException
+
+        video_file = pconfig.cache_dir / file_name
+        if video_file.exists():
+            return video_file
+
+        m3u8_slices = await self._get_m3u8_slices(m3u8_url)
+
+        try:
+            async with (
+                aiofiles.open(video_file, "wb") as f,
+                AsyncClient(headers=self.headers, timeout=DOWNLOAD_TIMEOUT) as client,
+            ):
+                total_size = 0
+                with DOWNLOADER.get_progress_bar(file_name) as bar:
+                    for url in m3u8_slices:
+                        async with client.stream("GET", url) as response:
+                            async for chunk in response.aiter_bytes(chunk_size=1024 * 1024):
+                                await f.write(chunk)
+                                total_size += len(chunk)
+                                bar.update(len(chunk))
+        except HTTPError:
+            video_file.unlink(missing_ok=True)
+            logger.exception("视频下载失败")
+            raise DownloadException("视频下载失败")
+        return video_file
+
+    async def _get_m3u8_slices(self, m3u8_url: str):
+        """拼接m3u8链接
+
+        Args:
+            m3u8_url (str): m3u8链接
+            m3u8_slice (str): m3u8切片
+
+        Returns:
+            list[str]: 视频链接
+        """
+        async with AsyncClient(headers=self.headers, timeout=COMMON_TIMEOUT) as client:
+            response = await client.get(m3u8_url)
+            response.raise_for_status()
+
+        slices_text = response.text
+
+        slices: list[str] = []
+        for line in slices_text.splitlines():
+            line = line.strip()
+            if not line or line.startswith("#"):
+                continue
+            slices.append(urljoin(m3u8_url, line))
+
+        return slices

nonebot_plugin_parser-2.3.7/src/nonebot_plugin_parser/parsers/acfun/video.py

@@ -0,0 +1,77 @@
+from msgspec import Struct
+from msgspec.json import Decoder
+
+
+class User(Struct):
+    name: str
+    headUrl: str
+
+
+class Representation(Struct):
+    url: str
+    m3u8Slice: str
+    qualityType: str
+
+    @property
+    def m3u8_slice(self) -> str:
+        return self.m3u8Slice.replace("\\\\n", "\n")
+
+
+class AdaptationSet(Struct):
+    representation: list[Representation]
+
+
+class KsPlay(Struct):
+    adaptationSet: list[AdaptationSet]
+
+
+class CurrentVideoInfo(Struct):
+    ksPlayJson: KsPlay
+    durationMillis: int
+
+    @property
+    def representations(self) -> list[Representation]:
+        return self.ksPlayJson.adaptationSet[0].representation
+
+
+class VideoInfo(Struct, kw_only=True):
+    title: str
+    description: str | None
+    createTimeMillis: int
+    user: User
+    currentVideoInfo: CurrentVideoInfo
+    coverUrl: str
+
+    @property
+    def name(self) -> str:
+        return self.user.name
+
+    @property
+    def avatar_url(self) -> str:
+        return self.user.headUrl
+
+    @property
+    def text(self) -> str | None:
+        return f"简介: {self.description}" if self.description else None
+
+    @property
+    def timestamp(self) -> int:
+        return self.createTimeMillis // 1000
+
+    @property
+    def duration(self) -> int:
+        return self.currentVideoInfo.durationMillis // 1000
+
+    @property
+    def m3u8_url(self) -> str:
+        representations = self.currentVideoInfo.representations
+
+        quality_types = ("1080p", "720p", "480p", "360p")
+        for r in representations:
+            if r.qualityType in quality_types:
+                return r.url
+
+        return representations[0].url
+
+
+decoder = Decoder(VideoInfo)

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/parsers/base.py

@@ -12,6 +12,7 @@ from .data import Platform, ParseResult, ParseResultKwargs
 from ..config import pconfig as pconfig
 from ..download import DOWNLOADER as DOWNLOADER
 from ..constants import IOS_HEADER, COMMON_HEADER, ANDROID_HEADER, COMMON_TIMEOUT
+from ..constants import DOWNLOAD_TIMEOUT as DOWNLOAD_TIMEOUT
 from ..constants import PlatformEnum as PlatformEnum
 from ..exception import TipException as TipException
 from ..exception import ParseException as ParseException

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/parsers/bilibili/__init__.py

@@ -88,7 +88,7 @@ class BilibiliParser(BaseParser):
     async def _parse_read(self, searched: Match[str]):
         """解析专栏信息"""
         read_id = int(searched.group("read_id"))
-        return await self.parse_read(read_id)
+        return await self.parse_read_with_opus(read_id)
 
     @handle("/opus/", r"bilibili\.com/opus/(?P<opus_id>\d+)")
     async def _parse_opus(self, searched: Match[str]):
@@ -175,14 +175,11 @@ class BilibiliParser(BaseParser):
         """
         from bilibili_api.dynamic import Dynamic
 
-        from .dynamic import DynamicItem
+        from .dynamic import DynamicData
 
         dynamic = Dynamic(dynamic_id, await self.credential)
+        dynamic_info = convert(await dynamic.get_info(), DynamicData).item
 
-        # 转换为结构体
-        dynamic_data = convert(await dynamic.get_info(), DynamicItem)
-        dynamic_info = dynamic_data.item
-        # 使用结构体属性提取信息
         author = self.create_author(dynamic_info.name, dynamic_info.avatar)
 
         # 下载图片
@@ -208,8 +205,8 @@ class BilibiliParser(BaseParser):
         opus = Opus(opus_id, await self.credential)
         return await self._parse_opus_obj(opus)
 
-    async def parse_read_old(self, read_id: int):
-        """解析专栏信息, 已废弃
+    async def parse_read_with_opus(self, read_id: int):
+        """解析专栏信息, 使用 Opus 接口
 
         Args:
             read_id (int): 专栏 id
@@ -297,45 +294,6 @@ class BilibiliParser(BaseParser):
             author=author,
         )
 
-    async def parse_read(self, read_id: int):
-        """专栏解析
-
-        Args:
-            read_id (int): 专栏 id
-
-        Returns:
-            texts: list[str], urls: list[str]
-        """
-        from bilibili_api.article import Article
-
-        from .article import TextNode, ImageNode, ArticleInfo
-
-        ar = Article(read_id)
-        # 加载内容
-        await ar.fetch_content()
-        data = ar.json()
-        article_info = convert(data, ArticleInfo)
-        logger.debug(f"article_info: {article_info}")
-
-        contents: list[MediaContent] = []
-        current_text = ""
-        for child in article_info.gen_text_img():
-            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)
-
-        return self.result(
-            title=article_info.title,
-            timestamp=article_info.timestamp,
-            text=current_text.strip(),
-            author=author,
-            contents=contents,
-        )
-
     async def parse_favlist(self, fav_id: int):
         """解析收藏夹信息
 

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/parsers/bilibili/dynamic.py

@@ -191,7 +191,7 @@ class DynamicInfo(Struct):
         return None
 
 
-class DynamicItem(Struct):
+class DynamicData(Struct):
     """动态项目"""
 
     item: DynamicInfo

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/parsers/data.py

@@ -58,7 +58,7 @@ class VideoContent(MediaContent):
         return f"时长: {minutes}:{seconds:02d}"
 
     def __repr__(self) -> str:
-        repr = f"VideoContent(path={repr_path_task(self.path_task)}"
+        repr = f"VideoContent({repr_path_task(self.path_task)}"
         if self.cover is not None:
             repr += f", cover={repr_path_task(self.cover)}"
         return repr + ")"
@@ -88,7 +88,7 @@ class GraphicsContent(MediaContent):
     """图片描述 渲染时居中显示"""
 
     def __repr__(self) -> str:
-        repr = f"GraphicsContent(path={repr_path_task(self.path_task)}"
+        repr = f"GraphicsContent({repr_path_task(self.path_task)}"
         if self.text:
             repr += f", text={self.text}"
         if self.alt:

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/parsers/douyin/__init__.py

@@ -1,7 +1,6 @@
 import re
 from typing import ClassVar
 
-import msgspec
 from httpx import AsyncClient
 from nonebot import logger
 
@@ -61,6 +60,8 @@ class DouyinParser(BaseParser):
         return f"https://m.douyin.com/share/{ty}/{vid}"
 
     async def parse_video(self, url: str):
+        from . import video
+
         async with AsyncClient(
             headers=self.ios_headers,
             timeout=COMMON_TIMEOUT,
@@ -81,9 +82,7 @@ class DouyinParser(BaseParser):
         if not matched or not matched.group(1):
             raise ParseException("can't find _ROUTER_DATA in html")
 
-        from .video import RouterData
-
-        video_data = msgspec.json.decode(matched.group(1).strip(), type=RouterData).video_data
+        video_data = video.decoder.decode(matched.group(1).strip()).video_data
         # 使用新的简洁构建方式
         contents = []
 
@@ -108,6 +107,8 @@ class DouyinParser(BaseParser):
         )
 
     async def parse_slides(self, video_id: str):
+        from . import slides
+
         url = "https://www.iesdouyin.com/web/api/v2/aweme/slidesinfo/"
         params = {
             "aweme_ids": f"[{video_id}]",
@@ -117,9 +118,7 @@ class DouyinParser(BaseParser):
             response = await client.get(url, params=params)
             response.raise_for_status()
 
-        from .slides import SlidesInfo
-
-        slides_data = msgspec.json.decode(response.content, type=SlidesInfo).aweme_details[0]
+        slides_data = slides.decoder.decode(response.content).aweme_details[0]
         contents = []
 
         # 添加图片内容

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/parsers/douyin/slides.py

@@ -1,6 +1,6 @@
 from random import choice
 
-from msgspec import Struct, field
+from msgspec import Struct, json, field
 
 
 class PlayAddr(Struct):
@@ -57,3 +57,6 @@ class SlidesData(Struct):
 
 class SlidesInfo(Struct):
     aweme_details: list[SlidesData] = field(default_factory=list)
+
+
+decoder = json.Decoder(SlidesInfo)

{nonebot_plugin_parser-2.3.5 → nonebot_plugin_parser-2.3.7}/src/nonebot_plugin_parser/parsers/douyin/video.py

@@ -1,7 +1,7 @@
 from random import choice
 from typing import Any
 
-from msgspec import Struct, field
+from msgspec import Struct, json, field
 
 from ..base import ParseException
 
@@ -93,3 +93,6 @@ class RouterData(Struct):
         elif page := self.loader_data.note_page:
             return page.video_info_res.video_data
         raise ParseException("can't find video_(id)/page or note_(id)/page in router data")
+
+
+decoder = json.Decoder(RouterData)