parsehub 2.0.2__tar.gz → 2.0.4__tar.gz

{parsehub-2.0.2/src/parsehub.egg-info → parsehub-2.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.2
+Version: 2.0.4
 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
@@ -125,26 +125,21 @@ print(result)
 
 ```python
 from parsehub import ParseHub
-from parsehub.config import ParseConfig
 
-config = ParseConfig(
-    cookie="key1=value1; key2=value2",  # 从浏览器中获取
-    proxy="http://127.0.0.1:7890",  # 可选
-)
-ph = ParseHub(config=config)
+ph = ParseHub(cookie="key1=value1; key2=value2", proxy="http://127.0.0.1:7890",)
 ```
 
 Cookie 支持多种格式传入：
 
 ```python
 # 字符串
-ParseConfig(cookie="key1=value1; key2=value2")
+ParseHub(cookie="key1=value1; key2=value2")
 
 # JSON 字符串
-ParseConfig(cookie='{"key1": "value1", "key2": "value2"}')
+ParseHub(cookie='{"key1": "value1", "key2": "value2"}')
 
 # 字典
-ParseConfig(cookie={"key1": "value1", "key2": "value2"})
+ParseHub(cookie={"key1": "value1", "key2": "value2"})
 ```
 
 目前支持 Cookie 登录的平台:
@@ -158,9 +153,6 @@ from parsehub.config import GlobalConfig
 
 # 自定义默认下载目录
 GlobalConfig.default_save_dir = "./my_downloads"
-
-# 视频时长限制 (超过此时长将下载最低画质，0 为不限制)
-GlobalConfig.duration_limit = 600  # 秒
 ```
 
 ## 🤝 参考项目

{parsehub-2.0.2 → parsehub-2.0.4}/README.md

@@ -88,26 +88,21 @@ print(result)
 
 ```python
 from parsehub import ParseHub
-from parsehub.config import ParseConfig
 
-config = ParseConfig(
-    cookie="key1=value1; key2=value2",  # 从浏览器中获取
-    proxy="http://127.0.0.1:7890",  # 可选
-)
-ph = ParseHub(config=config)
+ph = ParseHub(cookie="key1=value1; key2=value2", proxy="http://127.0.0.1:7890",)
 ```
 
 Cookie 支持多种格式传入：
 
 ```python
 # 字符串
-ParseConfig(cookie="key1=value1; key2=value2")
+ParseHub(cookie="key1=value1; key2=value2")
 
 # JSON 字符串
-ParseConfig(cookie='{"key1": "value1", "key2": "value2"}')
+ParseHub(cookie='{"key1": "value1", "key2": "value2"}')
 
 # 字典
-ParseConfig(cookie={"key1": "value1", "key2": "value2"})
+ParseHub(cookie={"key1": "value1", "key2": "value2"})
 ```
 
 目前支持 Cookie 登录的平台:
@@ -121,9 +116,6 @@ from parsehub.config import GlobalConfig
 
 # 自定义默认下载目录
 GlobalConfig.default_save_dir = "./my_downloads"
-
-# 视频时长限制 (超过此时长将下载最低画质，0 为不限制)
-GlobalConfig.duration_limit = 600  # 秒
 ```
 
 ## 🤝 参考项目

{parsehub-2.0.2 → parsehub-2.0.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.0.2"
+version = "2.0.4"
 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-2.0.2 → parsehub-2.0.4}/src/parsehub/__init__.py

@@ -43,9 +43,11 @@ class ParseHub:
         self,
         url: str,
         path: str | Path = None,
+        *,
         callback: ProgressCallback = None,
         callback_args: tuple = (),
         proxy: str | None = None,
+        save_metadata: bool = False,
     ) -> DownloadResult:
         """下载
         :param url: 分享文案 / 分享链接
@@ -53,6 +55,7 @@ class ParseHub:
         :param callback: 下载进度回调函数
         :param callback_args: 下载进度回调函数参数
         :param proxy: 代理
+        :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
         :return: DownloadResult
 
         Note:
@@ -67,7 +70,9 @@ class ParseHub:
                 - ``count``: 计数进度，用于多文件下载时报告已完成/总文件数
         """
         result = await self.parse(url)
-        return await result.download(path, callback, callback_args, proxy)
+        return await result.download(
+            path, callback=callback, callback_args=callback_args, proxy=proxy, save_metadata=save_metadata
+        )
 
     def download_sync(
         self,
@@ -76,6 +81,7 @@ class ParseHub:
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         proxy: str | None = None,
+        save_metadata: bool = False,
     ) -> DownloadResult:
         """
         同步下载
@@ -84,6 +90,7 @@ class ParseHub:
         :param callback: 进度回调函数
         :param callback_args: 进度回调函数参数
         :param proxy: 代理
+        :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
         :return: DownloadResult
 
         Note:
@@ -97,7 +104,11 @@ class ParseHub:
                 - ``bytes``: 字节进度，用于单文件下载时报告已下载/总字节数
                 - ``count``: 计数进度，用于多文件下载时报告已完成/总文件数
         """
-        return get_event_loop().run_until_complete(self.download(url, path, callback, callback_args, proxy))
+        return get_event_loop().run_until_complete(
+            self.download(
+                url, path, callback=callback, callback_args=callback_args, proxy=proxy, save_metadata=save_metadata
+            )
+        )
 
     async def get_raw_url(self, url: str, proxy: str | None = None) -> str:
         """获取原始链接

{parsehub-2.0.2 → parsehub-2.0.4}/src/parsehub/config/config.py

@@ -12,10 +12,9 @@ class _GlobalConfig(BaseModel):
         "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36"
     )
     douyin_api: HttpUrl = "https://douyin.wtf/"
-    """建议自行部署: https://github.com/Evil0ctal/Douyin_TikTok_Download_API"""
-    duration_limit: int = 0
-    """部分平台下载超过指定时长的视频时, 下载最低画质, 单位秒, 0为不限制"""
+    """抖音解析API, 建议自行部署: https://github.com/Evil0ctal/Douyin_TikTok_Download_API"""
     default_save_dir: Path = Path(sys.argv[0]).parent / "downloads"
+    """默认下载目录"""
 
 
 GlobalConfig = _GlobalConfig()

{parsehub-2.0.2 → parsehub-2.0.4}/src/parsehub/parsers/base/ytdlp.py

@@ -6,7 +6,6 @@ from typing import Union
 
 from yt_dlp import YoutubeDL
 
-from ...config.config import GlobalConfig
 from ...types import (
     DownloadError,
     DownloadResult,
@@ -137,9 +136,9 @@ class YtVideoParseResult(VideoParseResult):
 
         paramss["outtmpl"] = f"{output_dir.joinpath('ytdlp_%(id)s')}.%(ext)s"
 
-        if GlobalConfig.duration_limit and self.dl.duration > GlobalConfig.duration_limit:
-            # 视频超过限制时长，获取最低画质
-            paramss["format"] = "worstvideo* + worstaudio / worst"
+        # if GlobalConfig.duration_limit and self.dl.duration > GlobalConfig.duration_limit:
+        #     # 视频超过限制时长，获取最低画质
+        #     paramss["format"] = "worstvideo* + worstaudio / worst"
 
         if callback:
             await callback(0, 1, "count", *callback_args)

{parsehub-2.0.2 → parsehub-2.0.4}/src/parsehub/parsers/parser/bilibili.py

@@ -118,10 +118,11 @@ class BiliParse(YtParser):
                     dimension = page_info["dimension"]
 
             b3, b4 = await bili.get_buvid()
-            if GlobalConfig.duration_limit and duration > GlobalConfig.duration_limit:
-                video_playurl = await bili.get_video_playurl(url, cid, b3, b4, False)
-            else:
-                video_playurl = await bili.get_video_playurl(url, cid, b3, b4)
+            video_playurl = await bili.get_video_playurl(url, cid, b3, b4)
+            # if GlobalConfig.duration_limit and duration > GlobalConfig.duration_limit:
+            #     video_playurl = await bili.get_video_playurl(url, cid, b3, b4, False)
+            # else:
+            #     video_playurl = await bili.get_video_playurl(url, cid, b3, b4)
 
         durl = video_playurl["data"]["durl"][0]
         video_url = self.change_source(durl["backup_url"][0]) if durl.get("backup_url") else durl["url"]

{parsehub-2.0.2 → parsehub-2.0.4}/src/parsehub/provider_api/xiaoheihe.py

@@ -182,8 +182,8 @@ class XiaoHeiHeAPI:
                             type=media_type,
                             url=image["url"],
                             thumb_url=image["url"],
-                            height=int(image.get("height", 0)),
-                            width=int(image.get("width", 0)),
+                            height=int(float(image.get("height", 0))),
+                            width=int(float(image.get("width", 0))),
                         )
                     )
             return XiaoHeiHePost(type=post_type, title=title, content=content, media=images)

{parsehub-2.0.2 → parsehub-2.0.4}/src/parsehub/types/__init__.py

@@ -3,6 +3,7 @@ from .callback import ProgressCallback, ProgressUnit
 from .media_file import AniFile, AnyMediaFile, ImageFile, LivePhotoFile, MediaFile, VideoFile
 from .media_ref import AniRef, AnyMediaRef, ImageRef, LivePhotoRef, MediaRef, VideoRef
 from .platform import Platform
+from .post import PostType
 from .result import (
     AnyParseResult,
     DownloadResult,
@@ -38,4 +39,5 @@ __all__ = [
     "AnyMediaFile",
     "ProgressCallback",
     "ProgressUnit",
+    "PostType",
 ]

parsehub-2.0.4/src/parsehub/types/post.py

@@ -0,0 +1,11 @@
+from enum import StrEnum
+
+
+class PostType(StrEnum):
+    """帖子类型"""
+
+    UNKNOWN = "unknown"
+    IMAGE = "image"
+    VIDEO = "video"
+    MULTIMEDIA = "multimedia"
+    RICHTEXT = "richtext"

{parsehub-2.0.2 → parsehub-2.0.4}/src/parsehub/types/result.py

@@ -1,8 +1,12 @@
+import json
 import shutil
 import time
 from abc import ABC
+from dataclasses import asdict
 from pathlib import Path
+from typing import ClassVar
 
+import aiofiles
 from bs4 import BeautifulSoup
 from markdown import markdown as md_to_html
 from slugify import slugify
@@ -15,11 +19,14 @@ from .callback import ProgressCallback
 from .media_file import AniFile, AnyMediaFile, ImageFile, LivePhotoFile, VideoFile
 from .media_ref import AniRef, AnyMediaRef, ImageRef, LivePhotoRef, VideoRef
 from .platform import Platform
+from .post import PostType
 
 
 class ParseResult(ABC):  # noqa: B024
     """解析结果基类"""
 
+    type: ClassVar[PostType] = PostType.UNKNOWN
+
     def __init__(
         self,
         raw_url: str,
@@ -31,7 +38,7 @@ class ParseResult(ABC):  # noqa: B024
         """
         :param title: 标题
         :param media: 媒体下载链接
-        :param content: 正文
+        :param content: 正文 (纯文本)
         :param raw_url: 原始帖子链接
         :param platform: 平台
         """
@@ -49,6 +56,23 @@ class ParseResult(ABC):  # noqa: B024
             f"raw_url={self.raw_url})"
         )
 
+    def to_dict(self) -> dict:
+        """转换为字典"""
+        media = None
+        if isinstance(self.media, list):
+            media = [asdict(m) for m in self.media]
+        elif self.media:
+            media = asdict(self.media)
+
+        return {
+            "platform": self.platform.id if self.platform else None,
+            "type": self.type.value,
+            "title": self.title,
+            "content": self.content,
+            "raw_url": self.raw_url,
+            "media": media,
+        }
+
     async def _do_download(
         self,
         *,
@@ -135,15 +159,18 @@ class ParseResult(ABC):  # noqa: B024
     async def download(
         self,
         path: str | Path | None = None,
+        *,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         proxy: str | None = None,
+        save_metadata: bool = False,
     ) -> "DownloadResult":
         """
         :param path: 保存路径
         :param callback: 下载进度回调函数
         :param callback_args: 下载进度回调函数参数
         :param proxy: 代理
+        :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
         :return: DownloadResult
 
         Note:
@@ -168,22 +195,33 @@ class ParseResult(ABC):  # noqa: B024
             counter += 1
         output_dir.mkdir(parents=True, exist_ok=True)
 
-        return await self._do_download(
-            output_dir=output_dir, callback=callback, callback_args=callback_args, proxy=proxy
-        )
+        if save_metadata:
+            async with aiofiles.open(output_dir.joinpath("metadata.json"), "w", encoding="utf-8") as f:
+                await f.write(json.dumps(self.to_dict(), ensure_ascii=False, indent=4))
+
+        try:
+            return await self._do_download(
+                output_dir=output_dir, callback=callback, callback_args=callback_args, proxy=proxy
+            )
+        except Exception as e:
+            shutil.rmtree(output_dir, ignore_errors=True)
+            raise e
 
     def download_sync(
         self,
         path: str | Path | None = None,
+        *,
         callback: ProgressCallback | None = None,
         callback_args: tuple = (),
         proxy: str | None = None,
+        save_metadata: bool = False,
     ) -> "DownloadResult":
         """
         :param path: 保存路径
         :param callback: 下载进度回调函数
         :param callback_args: 下载进度回调函数参数
         :param proxy: 代理
+        :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
         :return: DownloadResult
 
         Note:
@@ -197,12 +235,18 @@ class ParseResult(ABC):  # noqa: B024
                 - ``bytes``: 字节进度，用于单文件下载时报告已下载/总字节数
                 - ``count``: 计数进度，用于多文件下载时报告已完成/总文件数
         """
-        return get_event_loop().run_until_complete(self.download(path, callback, callback_args, proxy))
+        return get_event_loop().run_until_complete(
+            self.download(
+                path, callback=callback, callback_args=callback_args, proxy=proxy, save_metadata=save_metadata
+            )
+        )
 
 
 class VideoParseResult(ParseResult):
     """单个视频"""
 
+    type = PostType.VIDEO
+
     def __init__(
         self,
         raw_url: str,
@@ -222,6 +266,8 @@ class VideoParseResult(ParseResult):
 class ImageParseResult(ParseResult):
     """单图 / 多图 / 图集 / 实况照片"""
 
+    type = PostType.IMAGE
+
     def __init__(
         self,
         raw_url: str,
@@ -237,6 +283,8 @@ class ImageParseResult(ParseResult):
 class MultimediaParseResult(ParseResult):
     """多视频 / 视频 + 图片 / GIF / 实况照片"""
 
+    type = PostType.MULTIMEDIA
+
     def __init__(
         self,
         raw_url: str,
@@ -250,6 +298,8 @@ class MultimediaParseResult(ParseResult):
 class RichTextParseResult(ParseResult):
     """图文混排的文章"""
 
+    type = PostType.RICHTEXT
+
     def __init__(
         self,
         raw_url: str,
@@ -274,6 +324,17 @@ class RichTextParseResult(ParseResult):
             f" markdown_content={self.markdown_content or ''}, media={media_count} raw_url={self.raw_url})"
         )
 
+    def to_dict(self) -> dict:
+        """转换为字典"""
+        data = super().to_dict()
+        # 在 "content" 后面插入 "markdown_content"
+        result = {}
+        for key, value in data.items():
+            result[key] = value
+            if key == "content":
+                result["markdown_content"] = self.markdown_content
+        return result
+
     @property
     def plaintext_content(self) -> str:
         """从 markdown 转换为纯文本"""

{parsehub-2.0.2 → parsehub-2.0.4/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.2
+Version: 2.0.4
 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
@@ -125,26 +125,21 @@ print(result)
 
 ```python
 from parsehub import ParseHub
-from parsehub.config import ParseConfig
 
-config = ParseConfig(
-    cookie="key1=value1; key2=value2",  # 从浏览器中获取
-    proxy="http://127.0.0.1:7890",  # 可选
-)
-ph = ParseHub(config=config)
+ph = ParseHub(cookie="key1=value1; key2=value2", proxy="http://127.0.0.1:7890",)
 ```
 
 Cookie 支持多种格式传入：
 
 ```python
 # 字符串
-ParseConfig(cookie="key1=value1; key2=value2")
+ParseHub(cookie="key1=value1; key2=value2")
 
 # JSON 字符串
-ParseConfig(cookie='{"key1": "value1", "key2": "value2"}')
+ParseHub(cookie='{"key1": "value1", "key2": "value2"}')
 
 # 字典
-ParseConfig(cookie={"key1": "value1", "key2": "value2"})
+ParseHub(cookie={"key1": "value1", "key2": "value2"})
 ```
 
 目前支持 Cookie 登录的平台:
@@ -158,9 +153,6 @@ from parsehub.config import GlobalConfig
 
 # 自定义默认下载目录
 GlobalConfig.default_save_dir = "./my_downloads"
-
-# 视频时长限制 (超过此时长将下载最低画质，0 为不限制)
-GlobalConfig.duration_limit = 600  # 秒
 ```
 
 ## 🤝 参考项目

{parsehub-2.0.2 → parsehub-2.0.4}/src/parsehub.egg-info/SOURCES.txt

@@ -51,6 +51,7 @@ src/parsehub/types/callback.py
 src/parsehub/types/media_file.py
 src/parsehub/types/media_ref.py
 src/parsehub/types/platform.py
+src/parsehub/types/post.py
 src/parsehub/types/result.py
 src/parsehub/utils/downloader.py
 src/parsehub/utils/media_info.py