parsehub 2.1.1__tar.gz → 2.1.3__tar.gz

{parsehub-2.1.1/src/parsehub.egg-info → parsehub-2.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.1.1
+Version: 2.1.3
 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
@@ -34,7 +34,7 @@ Requires-Dist: python-slugify[unidecode]>=8.0.4
 Requires-Dist: opencv-python-headless>=4.13.0.92
 Requires-Dist: cryptography>=49.0.0
 Requires-Dist: gmssl>=3.2.2
-Requires-Dist: SignerPy>=0.12.0
+Requires-Dist: signerpy>=0.12.0
 Provides-Extra: cli
 Requires-Dist: argcomplete>=3.6.3; extra == "cli"
 Requires-Dist: platformdirs>=4.5.1; extra == "cli"
@@ -310,6 +310,21 @@ except ParseError as exc:
 
 ---
 
+## 🤝 参与贡献
+
+欢迎提交 Pull Request 或 Issue!
+
+- Bug 反馈请附上相关 URL 和日志信息
+
+### 开发规范
+
+提交代码前请至少执行:
+
+```bash
+ruff format && ruff check --fix && uv run mypy
+uv run pytest
+```
+
 ## 🤝 参考项目
 
 - [Evil0ctal/Douyin_TikTok_Download_API](https://github.com/Evil0ctal/Douyin_TikTok_Download_API)
@@ -321,7 +336,7 @@ except ParseError as exc:
 
 ## 📜 开源协议
 
-本项目基于 [MIT License](LICENSE) 开源。
+本项目基于 [MIT License](LICENSE) 开源
 
 ---
 

{parsehub-2.1.1 → parsehub-2.1.3}/README.md

@@ -268,6 +268,21 @@ except ParseError as exc:
 
 ---
 
+## 🤝 参与贡献
+
+欢迎提交 Pull Request 或 Issue!
+
+- Bug 反馈请附上相关 URL 和日志信息
+
+### 开发规范
+
+提交代码前请至少执行:
+
+```bash
+ruff format && ruff check --fix && uv run mypy
+uv run pytest
+```
+
 ## 🤝 参考项目
 
 - [Evil0ctal/Douyin_TikTok_Download_API](https://github.com/Evil0ctal/Douyin_TikTok_Download_API)
@@ -279,7 +294,7 @@ except ParseError as exc:
 
 ## 📜 开源协议
 
-本项目基于 [MIT License](LICENSE) 开源。
+本项目基于 [MIT License](LICENSE) 开源
 
 ---
 

{parsehub-2.1.1 → parsehub-2.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.1.1"
+version = "2.1.3"
 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"
@@ -37,7 +37,7 @@ dependencies = [
     "opencv-python-headless>=4.13.0.92",
     "cryptography>=49.0.0",
     "gmssl>=3.2.2",
-    "SignerPy>=0.12.0",
+    "signerpy>=0.12.0",
 ]
 
 [project.scripts]
@@ -66,6 +66,7 @@ Issues = "https://github.com/z-mio/parsehub/issues"
 
 [tool.ruff]
 line-length = 120
+exclude = ["test/_*.py"]
 
 [tool.ruff.lint]
 select = [

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/parsers/base/ytdlp.py

@@ -445,9 +445,9 @@ class YtVideoParseResult(VideoParseResult):
     def __init__(
         self,
         dl: "YtVideoInfo",
-        title: str | None,
+        title: str = "",
         video: VideoRef | None = None,
-        content: str | None = None,
+        content: str = "",
     ):
         """dl: yt-dlp解析结果"""
         self.dl = dl

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/parsers/parser/bilibili.py

@@ -106,7 +106,6 @@ class BiliParse(BaseParser):
             view = data["View"]
 
             cid = view["cid"]
-            part = ""
             duration = view["duration"]
             dimension = view["dimension"]
             desc = view["desc"]
@@ -114,7 +113,6 @@ class BiliParse(BaseParser):
             if p != 1 and (pages := view.get("pages")):
                 if page_info := next((i for i in pages if i["page"] == p), None):
                     cid = page_info["cid"]
-                    part = page_info["part"]
                     duration = page_info["duration"]
                     dimension = page_info["dimension"]
 
@@ -123,9 +121,12 @@ class BiliParse(BaseParser):
 
         durl = video_playurl["data"]["durl"][0]
         video_url = self.change_source(durl["backup_url"][0]) if durl.get("backup_url") else durl["url"]
+        content = desc.strip()
+        if content == "-":
+            content = ""
         return BiliVideoParseResult(
             title=data["View"]["title"],
-            content=f"P{p}: {part}" if part else (desc.strip() or ""),
+            content=content,
             video=VideoRef(
                 url=video_url,
                 thumb_url=data["View"]["pic"],
@@ -147,9 +148,9 @@ class BiliParse(BaseParser):
         )
 
     @staticmethod
-    def hashtag_handler(desc: str | None) -> str | None:
+    def hashtag_handler(desc: str) -> str:
         if not desc:
-            return None
+            return ""
         hashtags = re.findall(r" ?#[^#]+# ?", desc)
         for hashtag in hashtags:
             desc = desc.replace(hashtag, f" {hashtag.strip().removesuffix('#')} ")

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/parsers/parser/douyin.py

@@ -117,13 +117,17 @@ def remove_video_watermark(url: str) -> str:
     return url.replace("playwm", "play")
 
 
-def parse_video_info(video_data: dict) -> dict:
-    bit_rates = video_data.get("bit_rate")
-    if not bit_rates:
-        raise ParseError("抖音解析失败: 未获取到视频下载地址")
+def _p_play_addr(video_data: dict) -> tuple[str | None, int, int]:
+    play_addr = video_data["play_addr"]
+    url_list = play_addr["url_list"]
+    if not url_list:
+        return None, 0, 0
+    return url_list[0], play_addr.get("width", 0), play_addr.get("height", 0)
+
 
-    # 按分辨率、文件大小、码率降序排列，选择最高质量。
-    # Story/日常的移动端 default 播放地址通常没有 br 参数，但 data_size 最大。
+def _p_bit_rates(video_data: dict) -> tuple[str, int, int]:
+    bit_rates: list = video_data.get("bit_rate", [])
+    bit_rates = list(filter(lambda i: i.get("is_bytevc1", 0) == 0, bit_rates))
     bit_rates.sort(
         key=lambda x: (
             x.get("play_addr", {}).get("width", 0) * x.get("play_addr", {}).get("height", 0),
@@ -135,11 +139,20 @@ def parse_video_info(video_data: dict) -> dict:
     best_quality = bit_rates[0]
 
     play_addr = best_quality.get("play_addr", {})
-    video_url_list = play_addr.get("url_list", [])
-    if not video_url_list:
-        raise ParseError("抖音解析失败: 视频下载地址为空")
+    url_list = play_addr.get("url_list", [])
+    return url_list[0], play_addr.get("width", 0), play_addr.get("height", 0)
+
+
+def parse_video_info(video_data: dict) -> dict:
+    u, w, h = None, 0, 0
+    is_bytevc1 = video_data.get("is_bytevc1")
+    # is_bytevc1 = 1 | 2 为字节自研视频编码 bytevc1 | bytevc2
+    if is_bytevc1 == 0:
+        u, w, h = _p_play_addr(video_data)
+    if not u:
+        u, w, h = _p_bit_rates(video_data)
 
-    video_url = remove_video_watermark(video_url_list[0])
+    video_url = remove_video_watermark(u)
 
     cover = video_data.get("cover", {})
     thumb_url_list = cover.get("url_list", [])
@@ -148,9 +161,9 @@ def parse_video_info(video_data: dict) -> dict:
     return {
         "video_url": video_url,
         "thumb_url": thumb_url,
-        "duration": best_quality.get("duration", 0),
-        "width": play_addr.get("width", 0),
-        "height": play_addr.get("height", 0),
+        "duration": video_data.get("duration", 0),
+        "width": w,
+        "height": h,
     }
 
 

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/provider_api/bilibili.py

@@ -245,8 +245,8 @@ class BiliImage:
 
 @dataclass(kw_only=True)
 class BiliDynamic:
-    title: str | None = None
-    content: str | None = None
+    title: str = ""
+    content: str = ""
     images: list[BiliImage] | None = None
 
     @classmethod
@@ -361,10 +361,10 @@ class BiliDynamic:
         return cls(title=title)
 
     @staticmethod
-    def _get_desc_text(module_dynamic: dict) -> str | None:
+    def _get_desc_text(module_dynamic: dict) -> str:
         if desc := module_dynamic["desc"]:
             return str(desc["text"]).strip()
-        return None
+        return ""
 
     @staticmethod
     def _get_major_cover(major_content: dict) -> list[BiliImage] | None:

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/provider_api/coolapk.py

@@ -10,9 +10,9 @@ from ..utils.helpers import UA
 
 @dataclass
 class Coolapk:
-    title: str | None = None
-    markdown_content: str | None = None
-    text_content: str | None = None
+    title: str = ""
+    markdown_content: str = ""
+    text_content: str = ""
     imgs: list[str] | None = None
 
     @classmethod
@@ -25,6 +25,8 @@ class Coolapk:
         if title_element and (title := title_element.text.strip()):
             content = soup.find(class_="feed-article-message")
             if content is None:
+                if "s=" in url or "shareKey=" in url:
+                    raise ValueError("获取内容失败")
                 raise ValueError("获取内容失败, 分享时请保留 shareKey 或 s 参数")
             markdown_content = MarkdownConverter(heading_style="ATX").convert(str(content))
             text_content = "".join(BeautifulSoup(markdown(markdown_content), "lxml").find_all(string=True))
@@ -35,6 +37,6 @@ class Coolapk:
         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, feed_content, imgs)
+            return cls("", "", feed_content, imgs)
 
         raise ValueError("获取内容失败, 分享时请保留 shareKey 或 s 参数")

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/provider_api/douyin.py

@@ -1147,7 +1147,7 @@ class DouyinMobileCrawler:
                             return cast(dict[str, Any], payload)
                         last_error = f"{host} missing aweme_detail: {payload.get('status_msg') or payload}"
                 await asyncio.sleep(0.15)
-        raise ParseError(f"获取抖音 Story/日常失败: {last_error}")
+        raise ParseError(f"获取抖音作品失败: {last_error}")
 
     async def parse(self, raw_url: str) -> dict:
         aweme_id = await self.get_aweme_id(raw_url)

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/provider_api/instagram.py

@@ -65,17 +65,17 @@ class InstagramPost:
         return bool(self._field("is_video"))
 
     @property
-    def title(self) -> str | None:
-        return self._node.get("title")
+    def title(self) -> str:
+        return str(self._node.get("title", ""))
 
     @property
-    def caption(self) -> str | None:
+    def caption(self) -> str:
         caption_edges = self._node.get("edge_media_to_caption", {}).get("edges") or []
         if caption_edges:
             if text := caption_edges[0].get("node", {}).get("text"):
                 return str(text)
-            return None
-        return self._node.get("caption")
+            return ""
+        return str(self._node.get("caption", ""))
 
     @property
     def url(self) -> str:

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/provider_api/twitter.py

@@ -173,7 +173,7 @@ class TwitterTweet:
     def __init__(
         self,
         tweet_id: str,
-        full_text: str | None = None,
+        full_text: str = "",
         media: list[TwitterVideo | TwitterPhoto | TwitterAni] | None = None,
         article: TwitterArticle | None = None,
     ):

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/provider_api/xhs.py

@@ -122,7 +122,7 @@ class XHSAPI:
 
     @staticmethod
     def get_trace_id(img_url: str) -> str:
-        match = re.search(r"/(spectrum|note_pre_post_uhdr|notes_pre_post|notes_uhdr)/([^/!]+)(?:!.*)?$", img_url)
+        match = re.search(r"/[a-f0-9]{32}/(.*)/([^/!]+)(?:!.*)?", img_url)
         if match:
             return f"{match.group(1)}/{match.group(2)}"
 
@@ -169,7 +169,7 @@ class XHSPost:
 if __name__ == "__main__":
 
     async def main() -> None:
-        url = "https://www.xiaohongshu.com/explore/68fe2018000000000303a844?xsec_token=ABgAb-5vt3L-aTqeEjdxJP_ylf02hY5n2f-y75yMQWrUo=&xsec_source=pc_search&source=web_explore_feed"
+        url = ""
         xhs = XHSAPI()
         print(await xhs.extract(url))
 

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/provider_api/zhihu.py

@@ -91,8 +91,8 @@ class ZhihuQA:
 class ZhihuZhuanLan:
     title: str
     imgs: list[str]
-    markdown_content: str | None = None
-    plaintext_content: str | None = None
+    markdown_content: str = ""
+    plaintext_content: str = ""
 
     @classmethod
     def parse(cls, data: dict) -> Self:
@@ -122,8 +122,8 @@ class ZhihuPin:
     type: ZhihuPinType
     title: str
     media: list[ZhihuMedia]
-    markdown_content: str | None = None
-    plaintext_content: str | None = None
+    markdown_content: str = ""
+    plaintext_content: str = ""
 
     @classmethod
     def parse(cls, result: dict) -> "ZhihuPin":

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub/types/result.py

@@ -30,8 +30,8 @@ class ParseResult(ABC):  # noqa: B024
 
     def __init__(
         self,
-        title: str | None = "",
-        content: str | None = "",
+        title: str = "",
+        content: str = "",
         media: Sequence[AnyMediaRef] | AnyMediaRef | None = None,
         platform: Platform | None = None,
     ):
@@ -42,8 +42,8 @@ class ParseResult(ABC):  # noqa: B024
         :param platform: 平台
         """
         self.raw_url: str = ""
-        self.title = (title or "").strip()
-        self.content = (content or "").strip()
+        self.title = title.strip()
+        self.content = content.strip()
         self.media = media
         self.platform = platform
         self.name = slugify(
@@ -294,9 +294,9 @@ class VideoParseResult(ParseResult):
 
     def __init__(
         self,
-        title: str | None = "",
+        title: str = "",
         video: str | VideoRef | None = None,
-        content: str | None = "",
+        content: str = "",
     ):
         video = VideoRef(url=video) if isinstance(video, str) else video
         super().__init__(
@@ -313,9 +313,9 @@ class ImageParseResult(ParseResult):
 
     def __init__(
         self,
-        title: str | None = "",
+        title: str = "",
         photo: Sequence[str | ImageRef | AniRef | LivePhotoRef] | None = None,
-        content: str | None = "",
+        content: str = "",
     ):
         media = [ImageRef(url=p) if isinstance(p, str) else p for p in photo] if photo else None
         super().__init__(title=title, media=media, content=content)
@@ -328,9 +328,9 @@ class MultimediaParseResult(ParseResult):
 
     def __init__(
         self,
-        title: str | None = "",
+        title: str = "",
         media: Sequence[AnyMediaRef] | None = None,
-        content: str | None = "",
+        content: str = "",
     ):
         super().__init__(title=title, media=media, content=content)
 
@@ -342,16 +342,16 @@ class RichTextParseResult(ParseResult):
 
     def __init__(
         self,
-        title: str | None = "",
+        title: str = "",
         media: Sequence[AnyMediaRef] | None = None,
-        markdown_content: str | None = "",
+        markdown_content: str = "",
     ):
         """
         :param title: 标题
         :param media: 文章中的媒体
         :param markdown_content: markdown 格式正文
         """
-        self.markdown_content = markdown_content or ""
+        self.markdown_content = markdown_content
         super().__init__(title=title, media=media, content=self.plaintext_content)
 
     def __repr__(self) -> str:

{parsehub-2.1.1 → parsehub-2.1.3/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.1.1
+Version: 2.1.3
 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
@@ -34,7 +34,7 @@ Requires-Dist: python-slugify[unidecode]>=8.0.4
 Requires-Dist: opencv-python-headless>=4.13.0.92
 Requires-Dist: cryptography>=49.0.0
 Requires-Dist: gmssl>=3.2.2
-Requires-Dist: SignerPy>=0.12.0
+Requires-Dist: signerpy>=0.12.0
 Provides-Extra: cli
 Requires-Dist: argcomplete>=3.6.3; extra == "cli"
 Requires-Dist: platformdirs>=4.5.1; extra == "cli"
@@ -310,6 +310,21 @@ except ParseError as exc:
 
 ---
 
+## 🤝 参与贡献
+
+欢迎提交 Pull Request 或 Issue!
+
+- Bug 反馈请附上相关 URL 和日志信息
+
+### 开发规范
+
+提交代码前请至少执行:
+
+```bash
+ruff format && ruff check --fix && uv run mypy
+uv run pytest
+```
+
 ## 🤝 参考项目
 
 - [Evil0ctal/Douyin_TikTok_Download_API](https://github.com/Evil0ctal/Douyin_TikTok_Download_API)
@@ -321,7 +336,7 @@ except ParseError as exc:
 
 ## 📜 开源协议
 
-本项目基于 [MIT License](LICENSE) 开源。
+本项目基于 [MIT License](LICENSE) 开源
 
 ---
 

{parsehub-2.1.1 → parsehub-2.1.3}/src/parsehub.egg-info/requires.txt

@@ -17,7 +17,7 @@ python-slugify[unidecode]>=8.0.4
 opencv-python-headless>=4.13.0.92
 cryptography>=49.0.0
 gmssl>=3.2.2
-SignerPy>=0.12.0
+signerpy>=0.12.0
 
 [cli]
 argcomplete>=3.6.3