nonebot-plugin-parser 2.4.1__tar.gz → 2.4.2__tar.gz

{nonebot_plugin_parser-2.4.1 → nonebot_plugin_parser-2.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: nonebot-plugin-parser
-Version: 2.4.1
+Version: 2.4.2
 Summary: NoneBot2 链接分享解析 Alconna 版, 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

{nonebot_plugin_parser-2.4.1 → nonebot_plugin_parser-2.4.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nonebot-plugin-parser"
-version = "2.4.1"
+version = "2.4.2"
 description = "NoneBot2 链接分享解析 Alconna 版, 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"
@@ -119,7 +119,7 @@ nonebug = { git = "https://github.com/nonebot/nonebug" }
 [tool.bumpversion]
 tag = true
 commit = true
-current_version = "2.4.1"
+current_version = "2.4.2"
 message = "release: bump vesion from {current_version} to {new_version}"
 
 [[tool.bumpversion.files]]

{nonebot_plugin_parser-2.4.1 → nonebot_plugin_parser-2.4.2}/src/nonebot_plugin_parser/parsers/base.py

@@ -199,6 +199,18 @@ class BaseParser:
             contents.append(ImageContent(task))
         return contents
 
+    def create_image_content(
+        self,
+        url_or_task: str | Task[Path],
+    ):
+        """创建图片内容"""
+        from .data import ImageContent
+
+        if isinstance(url_or_task, str):
+            url_or_task = DOWNLOADER.download_img(url_or_task, ext_headers=self.headers)
+
+        return ImageContent(url_or_task)
+
     def create_dynamic_contents(
         self,
         dynamic_urls: list[str],

{nonebot_plugin_parser-2.4.1 → nonebot_plugin_parser-2.4.2}/src/nonebot_plugin_parser/parsers/twitter.py

@@ -3,31 +3,82 @@ from typing import Any, ClassVar
 from itertools import chain
 
 from httpx import AsyncClient
+from msgspec import Struct, field
+from msgspec.json import Decoder
 
 from .base import BaseParser, PlatformEnum, handle
-from .data import Platform, ParseResult
+from .data import Platform, ParseResult, MediaContent
 from ..exception import ParseException
 
 
+class MediaElement(Struct):
+    type: str
+    """媒体类型 video/image/gif"""
+    url: str
+    altText: str | None = None
+    thumbnail_url: str | None = None
+    duration_millis: int | None = None
+
+
+class VxTwitterResponse(Struct):
+    article: str | None
+    date_epoch: int
+    fetched_on: int
+    likes: int
+    text: str
+    user_name: str
+    user_screen_name: str
+    user_profile_image_url: str
+    qrt: "VxTwitterResponse | None" = None
+    qrtURL: str | None = None
+    media_extended: list[MediaElement] = field(default_factory=list)
+
+
+decoder = Decoder(VxTwitterResponse)
+
+
 class TwitterParser(BaseParser):
     platform: ClassVar[Platform] = Platform(name=PlatformEnum.TWITTER, display_name="小蓝鸟")
 
-    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 AsyncClient(headers=headers, timeout=self.timeout) as client:
-            url = "https://xdown.app/api/ajaxSearch"
-            response = await client.post(url, data=data)
-            return response.json()
-
     @handle("x.com", r"x.com/[0-9-a-zA-Z_]{1,20}/status/([0-9]+)")
     async def _parse(self, searched: re.Match[str]) -> ParseResult:
+        url = f"https://{searched.group(0)}"
+        return await self.parse_by_vxapi(url)
+
+    async def parse_by_vxapi(self, url: str):
+        """使用 vxtwitter API 解析 Twitter 链接"""
+
+        api_url = url.replace("x.com", "api.vxtwitter.com")
+        async with AsyncClient(headers=self.headers, timeout=self.timeout) as client:
+            response = await client.get(api_url)
+            response.raise_for_status()
+
+        data = decoder.decode(response.content)
+        return self._collect_result(data)
+
+    def _collect_result(self, data: VxTwitterResponse) -> ParseResult:
+        author = self.create_author(data.user_screen_name, data.user_profile_image_url)
+
+        contents: list[MediaContent] = []
+
+        for media in data.media_extended:
+            if media.type in ("video", "gif"):
+                contents.append(self.create_video_content(media.url, media.thumbnail_url))
+            elif media.type == "image":
+                contents.append(self.create_image_content(media.url))
+
+        repost = self._collect_result(data.qrt) if data.qrt else None
+
+        return self.result(
+            author=author,
+            title=data.article,
+            text=data.text,
+            timestamp=data.date_epoch,
+            contents=contents,
+            repost=repost,
+        )
+
+    async def _parse_old(self, searched: re.Match[str]) -> ParseResult:
         # 从匹配对象中获取原始URL
         url = f"https://{searched.group(0)}"
 
@@ -40,9 +91,23 @@ class TwitterParser(BaseParser):
         if html_content is None:
             raise ParseException("解析失败, 数据为空")
 
-        return self.parse_twitter_html(html_content)
+        return self._parse_twitter_html(html_content)
+
+    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 AsyncClient(headers=headers, timeout=self.timeout) as client:
+            url = "https://xdown.app/api/ajaxSearch"
+            response = await client.post(url, data=data)
+            return response.json()
 
-    def parse_twitter_html(self, html_content: str) -> ParseResult:
+    def _parse_twitter_html(self, html_content: str) -> ParseResult:
         """解析 Twitter HTML 内容"""
         from bs4 import Tag, BeautifulSoup
 
@@ -106,11 +171,3 @@ class TwitterParser(BaseParser):
             author=self.create_author("无用户名"),
             contents=contents,
         )
-        # # 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)
-        # ):