parsehub 2.0.24__tar.gz → 2.0.26__tar.gz

{parsehub-2.0.24/src/parsehub.egg-info → parsehub-2.0.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.24
+Version: 2.0.26
 Summary: 轻量、异步、开箱即用的社交媒体聚合解析库
 Author-email: 梓澪 <zilingmio@gmail.com>
 License: MIT
@@ -95,7 +95,7 @@ Dynamic: license-file
 ### CLI 安装
 
 ```bash
-pipx install "parsehub[cli]"
+uv tool install "parsehub[cli]"
 ph -v
 ```
 
@@ -105,12 +105,8 @@ ph -v
 # uv
 uv add parsehub
 
-# pip
-pip install parsehub
-
 # 需要完整 CLI 能力时，可安装 `cli` 扩展
 uv add "parsehub[cli]"
-pip install "parsehub[cli]"
 ```
 
 ## 🚀 快速开始

{parsehub-2.0.24 → parsehub-2.0.26}/README.md

@@ -53,7 +53,7 @@
 ### CLI 安装
 
 ```bash
-pipx install "parsehub[cli]"
+uv tool install "parsehub[cli]"
 ph -v
 ```
 
@@ -63,12 +63,8 @@ ph -v
 # uv
 uv add parsehub
 
-# pip
-pip install parsehub
-
 # 需要完整 CLI 能力时，可安装 `cli` 扩展
 uv add "parsehub[cli]"
-pip install "parsehub[cli]"
 ```
 
 ## 🚀 快速开始

{parsehub-2.0.24 → parsehub-2.0.26}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.0.24"
+version = "2.0.26"
 description = "轻量、异步、开箱即用的社交媒体聚合解析库"
 readme = "README.md"
 requires-python = ">=3.12.0"

{parsehub-2.0.24 → parsehub-2.0.26}/src/parsehub/parsers/parser/weibo.py

@@ -1,6 +1,6 @@
 import re
 
-from ...provider_api.weibo import MediaType, MixMediaInfoItem, PicInfo, WeiboAPI
+from ...provider_api.weibo import MediaType, MixMediaInfoItem, PicInfo, WeiboAPI, WeiboTVContent
 from ...types import (
     AniRef,
     ImageParseResult,
@@ -17,10 +17,21 @@ from ..base.base import BaseParser
 class WeiboParser(BaseParser):
     __platform__ = Platform.WEIBO
     __supported_type__ = ["视频", "图文"]
-    __match__ = r"^(http(s)?://)((m\.|)weibo\.(com|cn)/(?!(u/)).+|mapp\.api\.weibo\.cn/fx/.+)"
+    __match__ = r"^(http(s)?://)((m\.|video\.|)weibo\.(com|cn)/(?!(u/)).+|mapp\.api\.weibo\.cn/fx/.+)"
+    __reserved_parameters__ = ["fid"]
 
     async def _do_parse(self, raw_url: str) -> MultimediaParseResult | VideoParseResult | ImageParseResult:
         weibo = await WeiboAPI(self.proxy).parse(raw_url)
+        if isinstance(weibo, WeiboTVContent):
+            return VideoParseResult(
+                content=self.f_text(weibo.text),
+                video=VideoRef(
+                    url=weibo.video_url,
+                    thumb_url=weibo.cover_image,
+                    duration=int(weibo.video_duration),
+                ),
+            )
+
         data = weibo.data
         text = self.f_text(data.content)
         media: list[VideoRef | ImageRef | LivePhotoRef | AniRef] = []

{parsehub-2.0.24 → parsehub-2.0.26}/src/parsehub/provider_api/coolapk.py

@@ -32,9 +32,9 @@ class Coolapk:
             return cls(title, markdown_content, text_content, imgs)
 
         feed_element = soup.find(class_="feed-message")
-        if feed_element and (content := feed_element.text.strip()):
+        if feed_element and (feed_content := feed_element.text.strip()):
             message_image_group = soup.find(class_="message-image-group")
             imgs = [f"https:{i['src']}" for i in message_image_group.find_all("img")] if message_image_group else []
-            return cls(None, None, content, imgs)
+            return cls(None, None, feed_content, imgs)
 
         raise ValueError("获取内容失败, 分享时请保留 shareKey 或 s 参数")

{parsehub-2.0.24 → parsehub-2.0.26}/src/parsehub/provider_api/weibo.py

@@ -5,59 +5,92 @@ from abc import abstractmethod
 from dataclasses import dataclass
 from enum import Enum
 from inspect import signature
-from typing import Any
+from typing import Any, Self, Union
 from urllib.parse import urlparse
 
 import httpx
 
 
 class WeiboAPI:
-    _MAPP_FX_NETLOC = "mapp.api.weibo.cn"
-    _STATUS_PATH_PATTERN = re.compile(r"^/status/([^/?#]+)")
-
     def __init__(self, proxy: str | None = None):
         self.proxy = proxy
+        self._cookies = {
+            "SUB": "_2AkMR47Mlf8NxqwFRmfocxG_lbox2wg7EieKnv0L-JRMxHRl-yT9yqhFdtRB6OmOdyoia9pKPkqoHRRmSBA_WNPaHuybH",
+        }
 
     @staticmethod
-    def get_id_by_url(url: str) -> str | None:
-        bid = url.split("/")[-1]
-        if bid.isdigit() or len(bid) == 9:
-            return bid
-        return None
+    def is_tv(url: str) -> bool:
+        if "/tv/show" in url:
+            return True
+        return False
 
     async def resolve_url(self, url: str) -> str:
         parsed = urlparse(url)
-        if parsed.hostname != self._MAPP_FX_NETLOC or not parsed.path.startswith("/fx/"):
-            return url
 
-        async with httpx.AsyncClient(proxy=self.proxy, follow_redirects=False, timeout=30) as client:
-            response = await client.get(url)
-            if response.is_error:
-                response.raise_for_status()
-        return response.headers.get("location") or url
+        async def fn() -> str:
+            async with httpx.AsyncClient(proxy=self.proxy, follow_redirects=False, timeout=30) as client:
+                response = await client.get(url)
+                if response.is_error:
+                    response.raise_for_status()
+            return response.headers.get("location") or url
 
-    async def get_id_by_url_async(self, url: str) -> str | None:
-        url = await self.resolve_url(url)
+        if parsed.hostname == "mapp.api.weibo.cn" and parsed.path.startswith("/fx/"):
+            return await fn()
+        if parsed.hostname == "video.weibo.com" and parsed.path.startswith("/show"):
+            return await fn()
+        return url
+
+    async def get_id_by_url(self, url: str) -> str | None:
         parsed = urlparse(url)
-        if match := self._STATUS_PATH_PATTERN.match(parsed.path):
-            return match.group(1)
-        return self.get_id_by_url(url)
+        if match := re.compile(r"^/status/([^/?#]+)").match(parsed.path):
+            return match[1]
 
-    async def parse(self, url: str) -> "WeiboContent":
-        bid = await self.get_id_by_url_async(url)
-        if not bid:
-            raise ValueError("Invalid URL")
+        id_ = parsed.path.split("/")[-1]
+
+        if self.is_tv(url) and len(id_) == 21:
+            return id_
+
+        if id_.isdigit() or len(id_) == 9:
+            return id_
+        return None
+
+    async def statuses_show(self, bid: str) -> dict:
         headers = {
             "referer": "https://weibo.com",
         }
-        cookies = {
-            "SUB": "_2AkMR47Mlf8NxqwFRmfocxG_lbox2wg7EieKnv0L-JRMxHRl-yT9yqhFdtRB6OmOdyoia9pKPkqoHRRmSBA_WNPaHuybH",
-        }
         api = f"https://weibo.com/ajax/statuses/show?id={bid}&isGetLongText=true"
         async with httpx.AsyncClient(proxy=self.proxy) as client:
-            response = await client.get(api, cookies=cookies, headers=headers)
+            response = await client.get(api, cookies=self._cookies, headers=headers)
+            response.raise_for_status()
+            result: dict = response.json()
+            return result
+
+    async def tv_show(self, oid: str) -> dict:
+        headers = {
+            "content-type": "application/x-www-form-urlencoded",
+            "referer": "https://weibo.com/tv/home",
+        }
+        params = {
+            "page": f"/tv/show/{oid}",
+        }
+        data = {"data": f'{{"Component_Play_Playinfo":{{"oid":"{oid}"}}}}'}
+        async with httpx.AsyncClient(proxy=self.proxy) as client:
+            response = await client.post(
+                "https://weibo.com/tv/api/component", cookies=self._cookies, headers=headers, data=data, params=params
+            )
             response.raise_for_status()
-            result = response.json()
+            result: dict = response.json()
+            return result
+
+    async def parse(self, url: str) -> Union["WeiboContent", "WeiboTVContent"]:
+        resolve_url = await self.resolve_url(url)
+        id_ = await self.get_id_by_url(resolve_url)
+        if not id_:
+            raise ValueError("Invalid URL")
+        if self.is_tv(resolve_url):
+            result = await self.tv_show(id_)
+            return WeiboTVContent.parse(result)
+        result = await self.statuses_show(id_)
         return WeiboContent.parse(result)
 
 
@@ -317,11 +350,31 @@ class Data:
 class WeiboContent:
     data: Data
 
-    @staticmethod
-    def parse(json_dict: dict) -> "WeiboContent":
+    @classmethod
+    def parse(cls, json_dict: dict) -> Self:
         data = Data.parse(json_dict)
-        return WeiboContent(data=data)
+        return cls(data=data)
+
+
+@dataclass
+class WeiboTVContent:
+    text: str
+    video_url: str
+    video_duration: float
+    cover_image: str
+
+    @classmethod
+    def parse(cls, json_dict: dict) -> Self:
+        data = json_dict["data"]
+        cpp = data["Component_Play_Playinfo"]
+
+        cover_image = f"https:{cpp['cover_image']}"
+        duration_time = cpp["duration_time"]
+        text = cpp["text"]
+        urls: dict[str, str] = cpp["urls"]
+        video_url = f"https:{list(urls.values())[0]}"
+        return cls(text=text, video_url=video_url, video_duration=duration_time, cover_image=cover_image)
 
 
 if __name__ == "__main__":
-    print(asyncio.run(WeiboAPI().parse("https://weibo.com/6576374129/Qv0n8sXum")))
+    print(asyncio.run(WeiboAPI().parse("https://weibo.com/tv/show/1034:5306598453608528")))

{parsehub-2.0.24 → parsehub-2.0.26}/src/parsehub/types/result.py

@@ -48,8 +48,9 @@ class ParseResult(ABC):  # noqa: B024
         self.platform = platform
 
     def __repr__(self) -> str:
-        media_items = self.media if isinstance(self.media, Sequence) else [self.media]
-        media_count = f"[{len(media_items)}]" if self.media else None
+        media_count = (
+            f"[{len(self.media if isinstance(self.media, Sequence) else [self.media])}]" if self.media else None
+        )
         return (
             f"{self.__class__.__name__}(platform={self.platform}, title={self.title or ''},"
             f" content={self.content or ''}, media={media_count}, "
@@ -356,7 +357,7 @@ class RichTextParseResult(ParseResult):
 
 
 class DownloadResult:
-    def __init__(self, media: AnyMediaFile | list[AnyMediaFile], output_dir: str | Path):
+    def __init__(self, media: AnyMediaFile | Sequence[AnyMediaFile], output_dir: str | Path):
         """
         下载结果
         :param media: 本地媒体路径
@@ -372,7 +373,10 @@ class DownloadResult:
             raise DeleteError(f"目录删除失败: {self.output_dir}") from e
 
     def __repr__(self) -> str:
-        return f"{self.__class__.__name__}(media={self.media}, output_dir={self.output_dir})"
+        media_count = (
+            f"[{len(self.media if isinstance(self.media, Sequence) else [self.media])}]" if self.media else None
+        )
+        return f"{self.__class__.__name__}(media={media_count}, output_dir={self.output_dir})"
 
 
 AnyParseResult = VideoParseResult | ImageParseResult | MultimediaParseResult | RichTextParseResult

{parsehub-2.0.24 → parsehub-2.0.26/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.24
+Version: 2.0.26
 Summary: 轻量、异步、开箱即用的社交媒体聚合解析库
 Author-email: 梓澪 <zilingmio@gmail.com>
 License: MIT
@@ -95,7 +95,7 @@ Dynamic: license-file
 ### CLI 安装
 
 ```bash
-pipx install "parsehub[cli]"
+uv tool install "parsehub[cli]"
 ph -v
 ```
 
@@ -105,12 +105,8 @@ ph -v
 # uv
 uv add parsehub
 
-# pip
-pip install parsehub
-
 # 需要完整 CLI 能力时，可安装 `cli` 扩展
 uv add "parsehub[cli]"
-pip install "parsehub[cli]"
 ```
 
 ## 🚀 快速开始

{parsehub-2.0.24 → parsehub-2.0.26}/test/test_core_offline.py

@@ -297,7 +297,8 @@ class TestPlatformUrlMatching(unittest.TestCase):
                 "https://weibo.com/1234567890/Nexample",
                 "https://weibo.com/detail/1234567890123456",
                 "https://m.weibo.cn/status/Nexample",
-                "https://weibo.cn/status/Nexample",
+                "https://video.weibo.com/show?fid=1034:5307969483767845",
+                "https://weibo.com/tv/show/1034:5307969483767845",
             ],
             Platform.WEIXIN: [
                 "https://mp.weixin.qq.com/s/example",