parsehub 2.0.29__tar.gz → 2.0.30__tar.gz

{parsehub-2.0.29/src/parsehub.egg-info → parsehub-2.0.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.29
+Version: 2.0.30
 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-2.0.29 → parsehub-2.0.30}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.0.29"
+version = "2.0.30"
 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-2.0.29 → parsehub-2.0.30}/src/parsehub/parsers/base/ytdlp.py

@@ -185,7 +185,7 @@ class YtVideoParseResult(VideoParseResult):
     async def _do_download(
         self,
         *,
-        output_dir: str | Path,
+        output_dir: Path,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         callback_kwargs: dict | None = None,
@@ -200,7 +200,7 @@ class YtVideoParseResult(VideoParseResult):
         if self.dl.proxy:
             paramss["proxy"] = self.dl.proxy
 
-        paramss["outtmpl"] = f"{output_dir_path.joinpath('ytdlp_%(id)s')}.%(ext)s"
+        paramss["outtmpl"] = f"{output_dir_path.joinpath(self.name)}.%(ext)s"
 
         if callback:
             loop = asyncio.get_running_loop()

{parsehub-2.0.29 → parsehub-2.0.30}/src/parsehub/parsers/parser/bilibili.py

@@ -168,7 +168,7 @@ class BiliVideoParseResult(VideoParseResult):
     async def _do_download(
         self,
         *,
-        output_dir: str | Path,
+        output_dir: Path,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         callback_kwargs: dict | None = None,

{parsehub-2.0.29 → parsehub-2.0.30}/src/parsehub/parsers/parser/coolapk.py

@@ -63,7 +63,7 @@ class CoolapkParseResult(ParseResult):
     async def _do_download(
         self,
         *,
-        output_dir: str | Path,
+        output_dir: Path,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         callback_kwargs: dict | None = None,

{parsehub-2.0.29 → parsehub-2.0.30}/src/parsehub/parsers/parser/douyin.py

@@ -68,7 +68,7 @@ class DouyinParseResult(ParseResult):
     async def _do_download(
         self,
         *,
-        output_dir: str | Path,
+        output_dir: Path,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         callback_kwargs: dict | None = None,

{parsehub-2.0.29 → parsehub-2.0.30}/src/parsehub/parsers/parser/kuaishou.py

@@ -6,7 +6,7 @@ from ..base.base import BaseParser
 class KuaiShouParser(BaseParser):
     __platform__ = Platform.KUAISHOU
     __supported_type__ = ["视频"]
-    __match__ = r"^(http(s)?://)?(www|v)\.kuaishou.com/.+"
+    __match__ = r"^(http(s)?://)?(www|v|live)\.kuaishou.com/.+"
     __redirect_keywords__ = ["v.kuaishou", "/f/"]
 
     async def _do_parse(self, raw_url: str) -> VideoParseResult:

{parsehub-2.0.29 → parsehub-2.0.30}/src/parsehub/parsers/parser/tiktok.py

@@ -63,7 +63,7 @@ class TikTokVideoParseResult(VideoParseResult):
     async def _do_download(
         self,
         *,
-        output_dir: str | Path,
+        output_dir: Path,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         callback_kwargs: dict | None = None,

{parsehub-2.0.29 → parsehub-2.0.30}/src/parsehub/provider_api/weibo.py

@@ -99,6 +99,7 @@ class MediaType(Enum):
     PHOTO = "pic"
     LIVE_PHOTO = "livephoto"
     GIF = "gif"
+    ARTICLE = "article"
 
 
 class Info(abc.ABC):
@@ -123,7 +124,7 @@ class Playback:
     size: int = 0
 
     @classmethod
-    def parse(cls, playback: dict) -> "Playback":
+    def parse(cls, playback: dict) -> Self:
         pi = playback["play_info"]
         url = pi["url"]
         width = pi["width"]
@@ -143,8 +144,8 @@ class MediaInfo:
     prefetch_size: int | None = None
     playback: Playback | None = None
 
-    @staticmethod
-    def parse(media_dict: dict) -> "MediaInfo":
+    @classmethod
+    def parse(cls, media_dict: dict) -> Self:
         format_ = media_dict["format"]
         mp4_hd_url = media_dict.get("mp4_hd_url")
         mp4_sd_url = media_dict.get("mp4_sd_url")
@@ -152,7 +153,7 @@ class MediaInfo:
         prefetch_size = media_dict["prefetch_size"]
         playback_list = media_dict.get("playback_list", [])
         playback = Playback.parse(playback_list[0]) if playback_list else None
-        return MediaInfo(format_, mp4_hd_url, mp4_sd_url, duration, prefetch_size, playback)
+        return cls(format_, mp4_hd_url, mp4_sd_url, duration, prefetch_size, playback)
 
 
 @dataclass
@@ -162,13 +163,16 @@ class PageInfo(Info):
     page_pic: str | None = None
     short_url: str | None = None
 
-    @staticmethod
-    def parse(page_info_dict: dict) -> "PageInfo":
+    @classmethod
+    def parse(cls, page_info_dict: dict) -> Self:
         object_type = MediaType(page_info_dict["object_type"])
-        media_info = MediaInfo.parse(page_info_dict["media_info"])
+        if object_type != MediaType.ARTICLE:
+            media_info = MediaInfo.parse(page_info_dict["media_info"])
+        else:
+            media_info = None
         page_pic = page_info_dict.get("page_pic")
         short_url = page_info_dict.get("short_url")
-        return PageInfo(object_type, media_info, page_pic, short_url)
+        return cls(object_type, media_info, page_pic, short_url)
 
     @property
     def media_url(self) -> str | None:
@@ -220,9 +224,9 @@ class PicInfo(Info):
     largest: Pic | None = None
     video: str | None = None
 
-    @staticmethod
-    def parse(pic_dict: dict) -> "PicInfo":
-        return PicInfo(
+    @classmethod
+    def parse(cls, pic_dict: dict) -> Self:
+        return cls(
             pic_id=pic_dict["pic_id"],
             type=MediaType(pic_dict["type"]),
             thumbnail=Pic(**pic_dict["thumbnail"]),
@@ -281,8 +285,8 @@ class MixMediaInfoItem(Info):
 class MixMediaInfo:
     items: list[MixMediaInfoItem] | None = None
 
-    @staticmethod
-    def parse(mix_media_info_dict: dict) -> "MixMediaInfo":
+    @classmethod
+    def parse(cls, mix_media_info_dict: dict) -> Self:
         items: list[MixMediaInfoItem] = []
         for item_dict in mix_media_info_dict["items"]:
             type_ = MediaType(item_dict["type"])
@@ -294,7 +298,7 @@ class MixMediaInfo:
             else:
                 data = None
             items.append(MixMediaInfoItem(type_, data))
-        return MixMediaInfo(items)
+        return cls(items)
 
 
 @dataclass
@@ -308,8 +312,8 @@ class Data:
     mix_media_info: MixMediaInfo | None = None
     retweeted_status: "Data | None" = None
 
-    @staticmethod
-    def parse(data_dict: dict) -> "Data":
+    @classmethod
+    def parse(cls, data_dict: dict) -> Self:
         if page_info := data_dict.get("page_info"):
             data_dict["page_info"] = PageInfo.parse(page_info)
         if pic_infos := data_dict.get("pic_infos"):
@@ -318,10 +322,10 @@ class Data:
             data_dict["mix_media_info"] = MixMediaInfo.parse(mix_media_info)
         if retweeted_status := data_dict.get("retweeted_status"):
             data_dict["retweeted_status"] = Data.parse(retweeted_status)
-        return Data.from_kwargs(**data_dict)
+        return cls.from_kwargs(**data_dict)
 
     @classmethod
-    def from_kwargs(cls, **kwargs: Any) -> "Data":
+    def from_kwargs(cls, **kwargs: Any) -> Self:
         cls_fields = set(signature(cls).parameters)
 
         native_args, new_args = {}, {}
@@ -377,4 +381,4 @@ class WeiboTVContent:
 
 
 if __name__ == "__main__":
-    print(asyncio.run(WeiboAPI().parse("https://weibo.com/tv/show/1034:5306598453608528")))
+    print(asyncio.run(WeiboAPI().parse("https://weibo.com/ttarticle/p/show?id=2309405312350592041114")))

{parsehub-2.0.29 → parsehub-2.0.30}/src/parsehub/types/result.py

@@ -41,11 +41,15 @@ class ParseResult(ABC):  # noqa: B024
         :param content: 正文 (纯文本)
         :param platform: 平台
         """
-        self.raw_url: str | None = None
+        self.raw_url: str = ""
         self.title = (title or "").strip()
         self.content = (content or "").strip()
         self.media = media
         self.platform = platform
+        self.name = slugify(
+            self.title or self.content or str(time.time_ns()), allow_unicode=True, max_length=50, lowercase=False
+        )
+        """符合路径命名规范的名称, 可用于目录和文件名"""
 
     def __repr__(self) -> str:
         media_count = (
@@ -77,7 +81,7 @@ class ParseResult(ABC):  # noqa: B024
     async def _do_download(
         self,
         *,
-        output_dir: str | Path,
+        output_dir: Path,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         callback_kwargs: dict | None = None,
@@ -114,10 +118,17 @@ class ParseResult(ABC):  # noqa: B024
                 dl_progress_args = callback_args
                 dl_progress_kwargs = callback_kwargs or {}
 
+            index = i + 1
+
             try:
+                save_path = (
+                    output_dir.joinpath(f"{self.name}.{media.ext}")
+                    if is_single
+                    else output_dir.joinpath(f"{index:03d}_{self.name}.{media.ext}")
+                )
                 f = await download(
                     media.url,
-                    f"{output_dir}/{i}.{media.ext}",
+                    save_path,
                     headers=headers,
                     proxy=proxy,
                     progress=dl_progress,
@@ -140,9 +151,14 @@ class ParseResult(ABC):  # noqa: B024
                     mf = LivePhotoFile(path=f, width=media.width, height=media.height, duration=media.duration)
                     if media.video_url:
                         try:
+                            save_path = (
+                                output_dir.joinpath(f"{self.name}_video.{media.video_ext}")
+                                if is_single
+                                else output_dir.joinpath(f"{index:03d}_{self.name}_video.{media.video_ext}")
+                            )
                             vf = await download(
                                 media.video_url,
-                                f"{output_dir}/{i}_video.{media.video_ext}",
+                                save_path,
                                 headers=headers,
                                 proxy=proxy,
                             )
@@ -196,13 +212,10 @@ class ParseResult(ABC):  # noqa: B024
                 - ``count``: 计数进度，用于多文件下载时报告已完成/总文件数
         """
         save_dir = Path(path) if path else GlobalConfig.default_save_dir
-        r = slugify(
-            self.title or self.content or str(time.time_ns()), allow_unicode=True, max_length=20, lowercase=False
-        )
-        output_dir = save_dir.joinpath(r)
+        output_dir = save_dir.joinpath(self.name)
         counter = 2
         while output_dir.exists():
-            output_dir = save_dir.joinpath(f"{r}_{counter}")
+            output_dir = save_dir.joinpath(f"{self.name}_{counter}")
             counter += 1
         output_dir.mkdir(parents=True, exist_ok=True)
 

{parsehub-2.0.29 → parsehub-2.0.30/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.29
+Version: 2.0.30
 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-2.0.29 → parsehub-2.0.30}/test/test_core_offline.py

@@ -268,6 +268,7 @@ class TestPlatformUrlMatching(unittest.TestCase):
                 "https://www.kuaishou.com/short-video/3xexample",
                 "https://v.kuaishou.com/example",
                 "https://www.kuaishou.com/f/example",
+                "https://live.kuaishou.com/u/3xmdumq6gmzrr64/3xjsfb8u3d7gzyu",
             ],
             Platform.PIPIX: [
                 "https://h5.pipix.com/s/example/",