nonebot-plugin-parser 2.0.0__tar.gz → 2.0.1__tar.gz

{nonebot_plugin_parser-2.0.0 → nonebot_plugin_parser-2.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nonebot-plugin-parser
-Version: 2.0.0
+Version: 2.0.1
 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
@@ -150,9 +150,10 @@ Windows 参考(原项目推荐): https://www.jianshu.com/p/5015a477de3c
 |    parser_need_upload     |  否   |          False           |                                                                                                                          音频解析，是否需要上传群文件                                                                                                                           |
 |     parser_use_base64     |  否   |          False           |                                            视频，图片，音频是否使用 base64 发送，注意：编解码和传输 base64 会占用更多的内存,性能和带宽, 甚至可能会使 websocket 连接崩溃，因此该配置项仅推荐 nonebot 和 协议端不在同一机器的用户配置                                             |
 |  parser_duration_maximum  |  否   |           480            |                                                                                                                          视频最大解析时长，单位：_秒_                                                                                                                           |
-|      parser_max_size      |  否   |           90            |                                                                                                              音视频下载最大文件大小，单位 MB，超过该配置将阻断下载                                                                                                              |
+|      parser_max_size      |  否   |            90            |                                                                                                              音视频下载最大文件大小，单位 MB，超过该配置将阻断下载                                                                                                              |
 | parser_disabled_platforms |  否   |            []            |                               全局禁止的解析，示例 parser_disabled_platforms=["bilibili", "douyin"] 表示禁止了哔哩哔哩和抖, 请根据自己需求填写["bilibili", "douyin", "kuaishou", "twitter", "youtube", "acfun", "tiktok", "weibo", "xiaohongshu"]                               |
-| parser_render_type        |  否   |         "common"        |                                               渲染器类型，可选 "default"(无图片渲染), "common"(PIL 通用图片渲染), "htmlkit"(htmlkit)                                                                                                                |
+|    parser_render_type     |  否   |         "common"         |                                                                                             渲染器类型，可选 "default"(无图片渲染), "common"(PIL 通用图片渲染), "htmlkit"(htmlkit)                                                                                              |
+|     parser_append_url     |  否   |          False           |                                                                                                                           是否在解析结果中附加原始URL                                                                                                                           |
 
 ## 🎉 使用
 ### 指令表

{nonebot_plugin_parser-2.0.0 → nonebot_plugin_parser-2.0.1}/README.md

@@ -120,9 +120,10 @@ Windows 参考(原项目推荐): https://www.jianshu.com/p/5015a477de3c
 |    parser_need_upload     |  否   |          False           |                                                                                                                          音频解析，是否需要上传群文件                                                                                                                           |
 |     parser_use_base64     |  否   |          False           |                                            视频，图片，音频是否使用 base64 发送，注意：编解码和传输 base64 会占用更多的内存,性能和带宽, 甚至可能会使 websocket 连接崩溃，因此该配置项仅推荐 nonebot 和 协议端不在同一机器的用户配置                                             |
 |  parser_duration_maximum  |  否   |           480            |                                                                                                                          视频最大解析时长，单位：_秒_                                                                                                                           |
-|      parser_max_size      |  否   |           90            |                                                                                                              音视频下载最大文件大小，单位 MB，超过该配置将阻断下载                                                                                                              |
+|      parser_max_size      |  否   |            90            |                                                                                                              音视频下载最大文件大小，单位 MB，超过该配置将阻断下载                                                                                                              |
 | parser_disabled_platforms |  否   |            []            |                               全局禁止的解析，示例 parser_disabled_platforms=["bilibili", "douyin"] 表示禁止了哔哩哔哩和抖, 请根据自己需求填写["bilibili", "douyin", "kuaishou", "twitter", "youtube", "acfun", "tiktok", "weibo", "xiaohongshu"]                               |
-| parser_render_type        |  否   |         "common"        |                                               渲染器类型，可选 "default"(无图片渲染), "common"(PIL 通用图片渲染), "htmlkit"(htmlkit)                                                                                                                |
+|    parser_render_type     |  否   |         "common"         |                                                                                             渲染器类型，可选 "default"(无图片渲染), "common"(PIL 通用图片渲染), "htmlkit"(htmlkit)                                                                                              |
+|     parser_append_url     |  否   |          False           |                                                                                                                           是否在解析结果中附加原始URL                                                                                                                           |
 
 ## 🎉 使用
 ### 指令表

{nonebot_plugin_parser-2.0.0 → nonebot_plugin_parser-2.0.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nonebot-plugin-parser"
-version = "2.0.0"
+version = "2.0.1"
 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 = "2.0.0"
+current_version = "2.0.1"
 commit = true
 message = "🔖 release: bump vesion from {current_version} to {new_version}"
 tag = true

{nonebot_plugin_parser-2.0.0 → nonebot_plugin_parser-2.0.1}/src/nonebot_plugin_parser/config.py

@@ -43,6 +43,8 @@ class Config(BaseModel):
     """资源最大大小 默认 100 单位 MB"""
     parser_duration_maximum: int = 480
     """视频/音频最大时长"""
+    parser_append_url: bool = False
+    """是否在解析结果中附加原始URL"""
     parser_disabled_platforms: list[PlatformNames] = []
     """禁止的解析器"""
     parser_bili_video_codes: list[VideoCodecs] = [VideoCodecs.AVC, VideoCodecs.AV1, VideoCodecs.HEV]
@@ -120,6 +122,11 @@ class Config(BaseModel):
         """是否使用 base64 编码发送图片，音频，视频"""
         return self.parser_use_base64
 
+    @property
+    def append_url(self) -> bool:
+        """是否在解析结果中附加原始URL"""
+        return self.parser_append_url
+
 
 pconfig: Config = get_plugin_config(Config)
 """配置"""

{nonebot_plugin_parser-2.0.0 → nonebot_plugin_parser-2.0.1}/src/nonebot_plugin_parser/parsers/data.py

@@ -195,8 +195,6 @@ class ParseResult:
         for cont in self.contents:
             if isinstance(cont, VideoContent):
                 return await cont.get_cover_path()
-            if isinstance(cont, ImageContent):
-                return await cont.get_path()
         return None
 
     async def contents_to_segs(self):
@@ -261,7 +259,7 @@ class ParseData:
     url: str | None = None
     video_url: str | None = None
     cover_url: str | None = None
-    images_urls: list[str] | None = None
-    dynamic_urls: list[str] | None = None
+    images_urls: list[str] = field(default_factory=list)
+    dynamic_urls: list[str] = field(default_factory=list)
     extra: dict[str, Any] = field(default_factory=dict)
     repost: "ParseData | None" = None

{nonebot_plugin_parser-2.0.0 → nonebot_plugin_parser-2.0.1}/src/nonebot_plugin_parser/parsers/douyin/video.py

@@ -43,8 +43,8 @@ class VideoData(Struct):
     video: Video | None = None
 
     @property
-    def images_urls(self) -> list[str] | None:
-        return [image.url_list[0] for image in self.images] if self.images else None
+    def images_urls(self) -> list[str]:
+        return [image.url_list[0] for image in self.images] if self.images else []
 
     @property
     def video_url(self) -> str | None:
@@ -65,14 +65,14 @@ class VideoData(Struct):
     @property
     def parse_data(self) -> ParseData:
         """转换为ParseData对象"""
-
+        images_urls = self.images_urls
         return ParseData(
             title=self.desc,
             name=self.author.nickname,
             avatar_url=self.avatar_url,
             timestamp=self.create_time,
-            images_urls=self.images_urls,
-            video_url=self.video_url if self.images_urls is None else None,
+            images_urls=images_urls,
+            video_url=self.video_url if len(images_urls) == 0 else None,
             cover_url=self.cover_url,
         )
 

{nonebot_plugin_parser-2.0.0 → nonebot_plugin_parser-2.0.1}/src/nonebot_plugin_parser/parsers/kuaishou.py

@@ -86,7 +86,7 @@ class Atlas(Struct):
     @property
     def img_urls(self):
         if len(self.cdn_list) == 0 or len(self.img_route_list) == 0:
-            return None
+            return []
         cdn = random.choice(self.cdn_list).cdn
         return [f"https://{cdn}/{url}" for url in self.img_route_list]
 

nonebot_plugin_parser-2.0.1/src/nonebot_plugin_parser/parsers/twitter.py

@@ -0,0 +1,121 @@
+import re
+from typing import Any, ClassVar
+
+import httpx
+
+from ..exception import ParseException
+from .base import BaseParser
+from .data import ParseResult, Platform
+
+
+class TwitterParser(BaseParser):
+    # 平台信息
+    platform: ClassVar[Platform] = Platform(name="twitter", display_name="小蓝鸟")
+
+    # URL 正则表达式模式（keyword, pattern）
+    patterns: ClassVar[list[tuple[str, str]]] = [
+        ("x.com", r"https?://x.com/[0-9-a-zA-Z_]{1,20}/status/([0-9]+)"),
+    ]
+
+    async def _req_xdown_api(self, url: str) -> dict[str, Any]:
+        headers = {
+            "Accept": "application/json, text/plain, */*",
+            "Content-Type": "application/x-www-form-urlencoded",
+            "Origin": "https://xdown.app",
+            "Referer": "https://xdown.app/",
+            **self.headers,
+        }
+        data = {"q": url, "lang": "zh-cn"}
+        async with httpx.AsyncClient(headers=headers, timeout=self.timeout) as client:
+            url = "https://xdown.app/api/ajaxSearch"
+            response = await client.post(url, data=data)
+            return response.json()
+
+    async def parse(self, matched: re.Match[str]) -> ParseResult:
+        """解析 URL 获取内容信息并下载资源
+
+        Args:
+            matched: 正则表达式匹配对象，由平台对应的模式匹配得到
+
+        Returns:
+            ParseResult: 解析结果（已下载资源，包含 Path)
+
+        Raises:
+            ParseException: 解析失败时抛出
+        """
+        # 从匹配对象中获取原始URL
+        url = matched.group(0)
+        resp = await self._req_xdown_api(url)
+        if resp.get("status") != "ok":
+            raise ParseException("解析失败")
+
+        html_content = resp.get("data")
+
+        if html_content is None:
+            raise ParseException("解析失败, 数据为空")
+
+        data = self.parse_twitter_html(html_content)
+
+        return self.build_result(data)
+
+    @classmethod
+    def parse_twitter_html(cls, html_content: str):
+        """解析 Twitter HTML 内容
+
+        Args:
+            html_content (str): Twitter HTML 内容
+
+        Returns:
+            ParseData: 解析数据
+        """
+        from bs4 import BeautifulSoup, Tag
+
+        from .data import ParseData
+
+        soup = BeautifulSoup(html_content, "html.parser")
+        data = ParseData()
+
+        # 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
+
+        # 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:
+                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
+                data.video_url = href
+                break
+
+        # 3. 提取标题
+        title_tag = soup.find("h3")
+        if title_tag:
+            data.title = title_tag.get_text(strip=True)
+
+        # # 4. 提取Twitter ID
+        # twitter_id_input = soup.find("input", {"id": "TwitterId"})
+        # if (
+        #     twitter_id_input
+        #     and isinstance(twitter_id_input, Tag)
+        #     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-2.0.0 → nonebot_plugin_parser-2.0.1}/src/nonebot_plugin_parser/parsers/weibo.py

@@ -175,7 +175,6 @@ class WeiBoParser(BaseParser):
 
         # 用 bytes 更稳，避免编码歧义
         weibo_data = msgspec.json.decode(response.content, type=WeiboResponse).data
-        url = f"https://weibo.com/{weibo_data.user.id}/{weibo_data.bid}"
         return self.build_result(weibo_data.parse_data)
 
     def _base62_encode(self, number: int) -> str:
@@ -269,7 +268,7 @@ class WeiboData(Struct):
 
     @property
     def title(self) -> str:
-        return self.status_title or self.page_info.title if self.page_info else ""
+        return self.page_info.title if self.page_info else ""
 
     @property
     def display_name(self) -> str:
@@ -303,6 +302,14 @@ class WeiboData(Struct):
             return [x.large.url for x in self.pics]
         return []
 
+    @property
+    def url(self) -> str:
+        return f"https://weibo.com/{self.user.id}/{self.bid}"
+
+    @property
+    def timestamp(self) -> int:
+        return int(time.mktime(time.strptime(self.created_at, "%a %b %d %H:%M:%S %z %Y")))
+
     @property
     def parse_data(self) -> ParseData:
         return ParseData(
@@ -310,10 +317,11 @@ class WeiboData(Struct):
             name=self.display_name,
             avatar_url=self.user.profile_image_url,
             text=self.text_content,
-            timestamp=int(time.mktime(time.strptime(self.created_at, "%a %b %d %H:%M:%S %z %Y"))),
+            timestamp=self.timestamp,
             video_url=self.video_url,
             cover_url=self.cover_url,
             images_urls=self.pic_urls,
+            url=self.url,
             repost=self.retweeted_status.parse_data if self.retweeted_status else None,
         )