parsehub 2.0.5__tar.gz → 2.0.7__tar.gz

{parsehub-2.0.5/src/parsehub.egg-info → parsehub-2.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.5
+Version: 2.0.7
 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

{parsehub-2.0.5 → parsehub-2.0.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.0.5"
+version = "2.0.7"
 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-2.0.5 → parsehub-2.0.7}/src/parsehub/__init__.py

@@ -125,15 +125,37 @@ class ParseHub:
             )
         )
 
-    async def get_raw_url(self, url: str, proxy: str | None = None) -> str:
+    async def get_raw_url(self, url: str, proxy: str | None = None, clean_all: bool = True) -> str:
         """获取原始链接
         :param url: 分享文案 / 分享链接
         :param proxy: 代理
+        :param clean_all: 是否清除全部可清除的参数 (包括解析后才需清除的参数)
+
+        Example:
+            以小红书为例，其解析器配置如下::
+
+                __reserved_parameters__ = []
+                __after_clean_parameters__ = ["xsec_token"]
+
+            原始链接::
+
+                https://www.xiaohongshu.com/explore/abc123?xsec_token=xxx&tracking=yyy
+
+            ``clean_all=False`` (解析阶段，保留解析所需的参数)::
+
+                https://www.xiaohongshu.com/explore/abc123?xsec_token=xxx
+                # tracking 被清除，xsec_token 保留（解析时需要它）
+
+            ``clean_all=True`` (最终输出，清除所有非必要参数)::
+
+                https://www.xiaohongshu.com/explore/abc123
+                # xsec_token 也被清除，返回干净的链接
+
         :return: 原始链接
         """
         parser = self.get_parser(url)
         try:
-            return await parser(proxy=proxy).get_raw_url(url, after_clean_parameters=True)
+            return await parser(proxy=proxy).get_raw_url(url, clean_all=clean_all)
         except Exception as e:
             raise ParseError from e
 

{parsehub-2.0.5 → parsehub-2.0.7}/src/parsehub/parsers/base/base.py

@@ -63,7 +63,7 @@ class BaseParser(ABC):
         :param url: 分享文案 / 分享链接
         :return: 解析结果
         """
-        raw_url = await self.get_raw_url(url, after_clean_parameters=False)
+        raw_url = await self.get_raw_url(url, clean_all=False)
         result = await self._do_parse(raw_url)
         result.platform = self.__platform__
         result.raw_url = self._clean_params(raw_url, self.__after_clean_parameters__)
@@ -76,11 +76,32 @@ class BaseParser(ABC):
         """
         raise NotImplementedError
 
-    async def get_raw_url(self, url: str, after_clean_parameters: bool = False) -> str:
+    async def get_raw_url(self, url: str, clean_all: bool = False) -> str:
         """
         清除链接中的参数
         :param url: 链接
-        :param after_clean_parameters: 是否执行后清理参数
+        :param clean_all: 是否清除全部可清除的参数 (包括解析后才需清除的参数)
+
+        Example:
+            以小红书为例，其解析器配置如下::
+
+                __reserved_parameters__ = []
+                __after_clean_parameters__ = ["xsec_token"]
+
+            原始链接::
+
+                https://www.xiaohongshu.com/explore/abc123?xsec_token=xxx&tracking=yyy
+
+            ``clean_all=False`` (解析阶段，保留解析所需的参数)::
+
+                https://www.xiaohongshu.com/explore/abc123?xsec_token=xxx
+                # tracking 被清除，xsec_token 保留（解析时需要它）
+
+            ``clean_all=True`` (最终输出，清除所有非必要参数)::
+
+                https://www.xiaohongshu.com/explore/abc123
+                # xsec_token 也被清除，返回干净的链接
+
         :return:
         """
         url = match_url(url)
@@ -107,9 +128,7 @@ class BaseParser(ABC):
         for i in query_params.copy().keys():
             is_reserved = i in self.__reserved_parameters__
             is_after_clean = i in self.__after_clean_parameters__
-            keep = (is_reserved and not (after_clean_parameters and is_after_clean)) or (
-                is_after_clean and not after_clean_parameters
-            )
+            keep = (is_reserved and not (clean_all and is_after_clean)) or (is_after_clean and not clean_all)
             if not keep:
                 query_params.pop(i, None)
 

{parsehub-2.0.5 → parsehub-2.0.7}/src/parsehub/parsers/parser/bilibili.py

@@ -66,12 +66,12 @@ class BiliParse(YtParser):
         else:
             return super().match(url)
 
-    async def get_raw_url(self, url: str, after_clean_parameters: bool = False) -> str:
+    async def get_raw_url(self, url: str, clean_all: bool = False) -> str:
         """获取原始链接"""
         if self._is_bvid(url):
             return f"https://www.bilibili.com/video/{url}"
         else:
-            return await super().get_raw_url(url, after_clean_parameters=after_clean_parameters)
+            return await super().get_raw_url(url, clean_all=clean_all)
 
     @staticmethod
     async def is_dynamic(url) -> str | None:

{parsehub-2.0.5 → parsehub-2.0.7}/src/parsehub/parsers/parser/instagram.py

@@ -28,7 +28,6 @@ class InstagramParser(BaseParser):
             dimensions = {}
         width, height = dimensions.get("width", 0) or 0, dimensions.get("height", 0) or 0
 
-        k = {"title": post.title, "content": post.caption, "raw_url": raw_url}
         match post.typename:
             case "GraphSidecar":
                 media = [
@@ -37,9 +36,11 @@ class InstagramParser(BaseParser):
                     else ImageRef(url=i.display_url, width=i.width, height=i.height)
                     for i in post.get_sidecar_nodes()
                 ]
-                return MultimediaParseResult(media=media, **k)
+                return MultimediaParseResult(media=media, title=post.title, content=post.caption)
             case "GraphImage":
-                return ImageParseResult(photo=[ImageRef(url=post.url, width=width, height=height)], **k)
+                return ImageParseResult(
+                    photo=[ImageRef(url=post.url, width=width, height=height)], title=post.title, content=post.caption
+                )
             case "GraphVideo":
                 return VideoParseResult(
                     video=VideoRef(
@@ -49,7 +50,8 @@ class InstagramParser(BaseParser):
                         width=width,
                         height=height,
                     ),
-                    **k,
+                    title=post.title,
+                    content=post.caption,
                 )
             case _:
                 raise ParseError("不支持的类型")

{parsehub-2.0.5 → parsehub-2.0.7}/src/parsehub/parsers/parser/twitter.py

@@ -19,10 +19,10 @@ class TwitterParser(BaseParser):
 
     async def _do_parse(self, raw_url: str) -> "MultimediaParseResult":
         tweet = await self._parse(raw_url)
-        return await self.media_parse(raw_url, tweet)
+        return await self.media_parse(tweet)
 
-    async def get_raw_url(self, url: str, after_clean_parameters: bool = False) -> str:
-        url = await super().get_raw_url(url, after_clean_parameters=after_clean_parameters)
+    async def get_raw_url(self, url: str, clean_all: bool = False) -> str:
+        url = await super().get_raw_url(url, clean_all=clean_all)
         return str(urlunparse(urlparse(url)._replace(netloc="x.com")))
 
     async def _parse(self, url: str):
@@ -46,7 +46,7 @@ class TwitterParser(BaseParser):
         return tweet
 
     @staticmethod
-    async def media_parse(url, tweet: TwitterTweet):
+    async def media_parse(tweet: TwitterTweet):
         media = []
         for m in tweet.media:
             match m:

{parsehub-2.0.5 → parsehub-2.0.7}/src/parsehub/parsers/parser/xhs.py

@@ -29,7 +29,6 @@ class XHSParser(BaseParser):
         result = await xhs.extract(raw_url)
 
         desc = self.hashtag_handler(result.desc)
-        k = {"title": result.title, "content": desc, "raw_url": raw_url}
         match result.type:
             case XHSPostType.VIDEO:
                 v: XHSMedia = result.media[0]
@@ -37,7 +36,8 @@ class XHSParser(BaseParser):
                     video=VideoRef(
                         url=v.url, thumb_url=v.thumb_url, duration=v.duration, height=v.height, width=v.width
                     ),
-                    **k,
+                    title=result.title,
+                    content=desc,
                 )
             case XHSPostType.IMAGE:
                 photos: list[ImageRef | LivePhotoRef] = []
@@ -55,7 +55,8 @@ class XHSParser(BaseParser):
 
                 return ImageParseResult(
                     photo=photos,
-                    **k,
+                    title=result.title,
+                    content=desc,
                 )
             case _:
                 raise ParseError("不支持的类型")

{parsehub-2.0.5 → parsehub-2.0.7}/src/parsehub/parsers/parser/xiaoheihe.py

@@ -22,14 +22,13 @@ class XiaoHeiHeParser(BaseParser):
     async def _do_parse(self, raw_url: str) -> AnyParseResult:
         xhh: XiaoHeiHePost = await XiaoHeiHeAPI(proxy=self.proxy).parse(raw_url)
         media = self.__parse_media(xhh)
-        v = {"title": xhh.title, "content": xhh.content, "raw_url": raw_url}
         match xhh.type:
             case XiaoHeiHePostType.VIDEO:
-                return VideoParseResult(video=media, **v)
+                return VideoParseResult(video=media, title=xhh.title, content=xhh.content)
             case XiaoHeiHePostType.IMAGE:
                 if not media or all(isinstance(m, ImageRef) for m in media):
-                    return ImageParseResult(photo=media, **v)
-                return MultimediaParseResult(media=media, **v)
+                    return ImageParseResult(photo=media, title=xhh.title, content=xhh.content)
+                return MultimediaParseResult(media=media, title=xhh.title, content=xhh.content)
             case XiaoHeiHePostType.ARTICLE:
                 return RichTextParseResult(title=xhh.title, media=media, markdown_content=xhh.content)
 

{parsehub-2.0.5 → parsehub-2.0.7/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.5
+Version: 2.0.7
 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