parsehub 2.0.31__tar.gz → 2.0.32__tar.gz

{parsehub-2.0.31/src/parsehub.egg-info → parsehub-2.0.32}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.0.31
+Version: 2.0.32
 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-2.0.31 → parsehub-2.0.32}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.0.31"
+version = "2.0.32"
 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-2.0.31 → parsehub-2.0.32}/src/parsehub/__init__.py

@@ -7,7 +7,7 @@ from .parsers.base import BaseParser
 from .types import Platform
 from .types.callback import ProgressCallback
 from .types.result import AnyParseResult, DownloadResult
-from .utils.utils import run_sync
+from .utils.helpers import SecretCookie, run_sync
 
 logger.disable(__name__)
 
@@ -27,7 +27,7 @@ class ParseHub:
         if not parser:
             raise UnknownPlatform(url)
         try:
-            p = parser(proxy=proxy, cookie=cookie)
+            p = parser(proxy=proxy, cookie=SecretCookie(cookie))
             return await p.parse(url)
         except ParseError:
             raise
@@ -56,6 +56,7 @@ class ParseHub:
         parse_proxy: str | None = None,
         parse_cookie: str | dict | None = None,
         save_metadata: bool = False,
+        connections: int = 4,
     ) -> DownloadResult:
         """下载
         :param url: 分享文案 / 分享链接
@@ -67,6 +68,7 @@ class ParseHub:
         :param parse_proxy: 解析代理
         :param parse_cookie: 解析 cookie
         :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
+        :param connections: 多线程下载连接数, 默认为 4
         :return: DownloadResult
 
         Note:
@@ -88,6 +90,7 @@ class ParseHub:
             callback_kwargs=callback_kwargs,
             proxy=proxy,
             save_metadata=save_metadata,
+            connections=connections,
         )
 
     def download_sync(
@@ -101,6 +104,7 @@ class ParseHub:
         parse_proxy: str | None = None,
         parse_cookie: str | dict | None = None,
         save_metadata: bool = False,
+        connections: int = 4,
     ) -> DownloadResult:
         """
         同步下载
@@ -113,6 +117,7 @@ class ParseHub:
         :param parse_proxy: 解析代理
         :param parse_cookie: 解析 cookie
         :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
+        :param connections: 多线程下载连接数, 默认为 4
         :return: DownloadResult
 
         Note:
@@ -137,6 +142,7 @@ class ParseHub:
                 parse_proxy=parse_proxy,
                 parse_cookie=parse_cookie,
                 save_metadata=save_metadata,
+                connections=connections,
             )
         )
 

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/cli.py

@@ -116,6 +116,7 @@ def _build_parser(prog: str) -> argparse.ArgumentParser:
     )
     download_parser.add_argument("-q", "--quiet", action="store_true", help="不输出状态和进度信息")
     download_parser.add_argument("--no-progress", action="store_true", help="不显示下载进度")
+    download_parser.add_argument("--connections", type=int, default=4, help="单文件分片下载连接数，设为 1 可禁用分片")
     _add_json_options(download_parser)
     download_parser.set_defaults(func=_cmd_download)
 
@@ -256,6 +257,7 @@ def _cmd_download(args: argparse.Namespace) -> int:
         parse_proxy=parse_proxy,
         parse_cookie=parse_cookie,
         save_metadata=args.save_metadata,
+        connections=args.connections,
     )
     reporter.finish()
 

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/base/base.py

@@ -11,7 +11,7 @@ from ... import parsers
 from ...config.config import GlobalConfig
 from ...types import AnyParseResult, ParseError
 from ...types.platform import Platform
-from ...utils.utils import match_url, normalize_cookie
+from ...utils.helpers import SecretCookie, match_url
 
 
 class BaseParser(ABC):
@@ -31,9 +31,9 @@ class BaseParser(ABC):
     __redirect_keywords__: list[str] = []
     """如果链接包含其中之一, 则遵循重定向规则"""
 
-    def __init__(self, *, proxy: str | None = None, cookie: str | dict | None = None):
+    def __init__(self, *, proxy: str | None = None, cookie: SecretCookie = SecretCookie()):
         self.proxy = proxy
-        self.cookie = normalize_cookie(cookie)
+        self.cookie = cookie
 
     def __init_subclass__(cls, /, register: bool = True, **kwargs: Any) -> None:
         super().__init_subclass__(**kwargs)

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/base/ytdlp.py

@@ -155,7 +155,6 @@ class YtParser(BaseParser, register=False):
     @property
     def params(self) -> dict[str, Any]:
         params = {
-            "format": "mp4+bestvideo[height<=1080]+bestaudio",
             "quiet": True,  # 不输出日志
             "noprogress": True,  # 不输出下载进度
             # "writethumbnail": True, # 下载缩略图
@@ -191,6 +190,7 @@ class YtVideoParseResult(VideoParseResult):
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         headers: dict | None = None,
+        connections: int = 4,
     ) -> "DownloadResult":
         if callback_kwargs is None:
             callback_kwargs = {}
@@ -201,6 +201,7 @@ class YtVideoParseResult(VideoParseResult):
             paramss["proxy"] = self.dl.proxy
 
         paramss["outtmpl"] = f"{output_dir_path.joinpath(self.name)}.%(ext)s"
+        paramss["concurrent_fragment_downloads"] = connections  # 多线程下载
 
         if callback:
             loop = asyncio.get_running_loop()

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/bilibili.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import re
 from pathlib import Path
-from typing import cast
+from typing import Any, cast
 from urllib.parse import parse_qs, urlparse
 
 from loguru import logger
@@ -20,7 +20,6 @@ from ...types import (
     VideoParseResult,
     VideoRef,
 )
-from ...utils.utils import cookie_ellipsis
 from ..base.ytdlp import YtParser, YtVideoParseResult
 
 
@@ -88,10 +87,10 @@ class BiliParse(YtParser):
     async def get_dynamic_info(self, url: str) -> BiliDynamic:
         async with BiliAPI(proxy=self.proxy) as bili:
             try:
-                dynamic_info = await bili.get_dynamic_info(url, cookie=self.cookie)
+                dynamic_info = await bili.get_dynamic_info(url, cookie=self.cookie.get_value())
             except Exception as e:
                 if "风控" in str(e):
-                    raise ParseError(f"账号风控\n使用的cookie: {cookie_ellipsis(self.cookie)}") from e
+                    raise ParseError(f"账号风控\n使用的cookie: {self.cookie}") from e
                 raise ParseError(str(e)) from e
         return cast(BiliDynamic, dynamic_info)
 
@@ -163,6 +162,14 @@ class BiliParse(YtParser):
             desc = desc.replace(hashtag, f" {hashtag.strip().removesuffix('#')} ")
         return desc.strip()
 
+    @property
+    def params(self) -> dict[str, Any]:
+        sub: dict[str, Any] = {
+            "format": "mp4+bestvideo[height<=1080]+bestaudio",
+        }
+        p = sub | super().params
+        return p
+
 
 class BiliVideoParseResult(VideoParseResult):
     async def _do_download(
@@ -174,6 +181,7 @@ class BiliVideoParseResult(VideoParseResult):
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         headers: dict | None = None,
+        connections: int = 4,
     ) -> DownloadResult:
         headers = {"referer": "https://www.bilibili.com", "User-Agent": GlobalConfig.ua}
         return await super()._do_download(
@@ -183,6 +191,7 @@ class BiliVideoParseResult(VideoParseResult):
             callback_kwargs=callback_kwargs,
             proxy=proxy,
             headers=headers,
+            connections=connections,
         )
 
 

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/coolapk.py

@@ -69,6 +69,7 @@ class CoolapkParseResult(ParseResult):
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         headers: dict | None = None,
+        connections: int = 4,
     ) -> "DownloadResult":
         headers = {
             "Accept": (
@@ -83,6 +84,7 @@ class CoolapkParseResult(ParseResult):
             callback_kwargs=callback_kwargs,
             proxy=proxy,
             headers=headers,
+            connections=connections,
         )
 
 

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/douyin.py

@@ -38,10 +38,10 @@ class DouyinParser(BaseParser):
 
     async def _fetch_api_result(self, url: str) -> "DouyinApiResult":
         """获取并解析抖音 API 结果"""
-        if not self.cookie:
+        if not (cookie := self.cookie.get_value()):
             raise ParseError("抖音 Cookie 未配置")
 
-        crawler = DouyinWebCrawler(proxy=self.proxy, cookie=self.cookie)
+        crawler = DouyinWebCrawler(proxy=self.proxy, cookie=cookie)
         response = await crawler.parse(url)
         return DouyinApiResult.parse(response)
 
@@ -74,6 +74,7 @@ class DouyinParseResult(ParseResult):
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         headers: dict | None = None,
+        connections: int = 4,
     ) -> "DownloadResult":
         headers = {
             "Referer": "https://www.douyin.com/",
@@ -85,6 +86,7 @@ class DouyinParseResult(ParseResult):
             callback_kwargs=callback_kwargs,
             proxy=proxy,
             headers=headers,
+            connections=connections,
         )
 
 

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/instagram.py

@@ -1,12 +1,12 @@
 import asyncio
 import re
-from typing import Any, cast
+from typing import cast
 
 from instaloader import BadResponseException
 
 from ...provider_api.instagram import MyInstaloaderContext, MyPost
 from ...types import ImageParseResult, ImageRef, MultimediaParseResult, ParseError, Platform, VideoParseResult, VideoRef
-from ...utils.utils import cookie_ellipsis
+from ...utils.helpers import SecretCookie
 from ..base.base import BaseParser
 
 
@@ -57,12 +57,12 @@ class InstagramParser(BaseParser):
             case _:
                 raise ParseError("不支持的类型")
 
-    async def _parse(self, url: str, shortcode: str, cookie: dict[str, Any] | None = None) -> MyPost:
+    async def _parse(self, url: str, shortcode: str, cookie: SecretCookie | None = None) -> MyPost:
         try:
             post = await asyncio.wait_for(
                 asyncio.to_thread(
                     MyPost.from_shortcode,
-                    MyInstaloaderContext(self.proxy, cookie),
+                    MyInstaloaderContext(self.proxy, cookie.get_value() if cookie else None),
                     shortcode,
                 ),
                 30,
@@ -80,7 +80,7 @@ class InstagramParser(BaseParser):
                     raise ParseError("无法获取帖子内容") from e
         except Exception as e:
             if cookie:
-                text = f"Instagram 账号可能已被封禁\n\n使用的Cookie: {cookie_ellipsis(cookie)}"
+                text = f"Instagram 账号可能已被封禁\n\n使用的Cookie: {cookie}"
             else:
                 text = str(e)
             raise ParseError(f"无法获取帖子内容: {text}") from e

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/kuaishou.py

@@ -10,7 +10,7 @@ class KuaiShouParser(BaseParser):
     __redirect_keywords__ = ["v.kuaishou", "/f/"]
 
     async def _do_parse(self, raw_url: str) -> VideoParseResult:
-        ks = KuaiShouAPI(self.cookie, self.proxy)
+        ks = KuaiShouAPI(self.cookie.get_value(), self.proxy)
         try:
             result = await ks.get_video_info(raw_url)
         except Exception as e:

parsehub-2.0.32/src/parsehub/parsers/parser/snapchat.py

@@ -0,0 +1,11 @@
+from ...types.platform import Platform
+from ..base.ytdlp import YtParser
+
+
+class Snapchatarse(YtParser):
+    __platform__ = Platform.SNAPCHAT
+    __supported_type__ = ["视频"]
+    __match__ = r"^(http(s)?://)?(?:www\.)?snapchat\.com/@([a-zA-Z0-9._-]+)(?:/spotlight)?/([a-zA-Z0-9_-]+)"
+
+
+__all__ = ["Snapchatarse"]

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/tiktok.py

@@ -33,7 +33,7 @@ class TikTokParser(BaseParser):
                 return self._build_image_result(result)
 
     async def _fetch_api_result(self, url: str) -> "TikTokApiResult":
-        crawler = TikTokWebCrawler(proxy=self.proxy, cookie=self.cookie)
+        crawler = TikTokWebCrawler(proxy=self.proxy, cookie=self.cookie.get_value())
         try:
             response = await crawler.parse(url)
             return TikTokApiResult.parse(response)
@@ -69,6 +69,7 @@ class TikTokVideoParseResult(VideoParseResult):
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         headers: dict | None = None,
+        connections: int = 4,
     ) -> "DownloadResult":
         headers = {
             "Referer": "https://www.tiktok.com/",
@@ -80,6 +81,7 @@ class TikTokVideoParseResult(VideoParseResult):
             callback_kwargs=callback_kwargs,
             proxy=proxy,
             headers=headers,
+            connections=connections,
         )
 
 

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/twitter.py

@@ -17,7 +17,6 @@ from ...types import (
     RichTextParseResult,
     VideoRef,
 )
-from ...utils.utils import cookie_ellipsis
 from ..base.base import BaseParser
 
 
@@ -40,14 +39,12 @@ class TwitterParser(BaseParser):
             tweet = await x.fetch_tweet(url)
         except Exception as e:
             if any(s in str(e) for s in ("error -2",)):
-                if self.cookie:
-                    x2 = Twitter(self.proxy, cookie=self.cookie)
+                if cookie := self.cookie.get_value():
+                    x2 = Twitter(self.proxy, cookie=cookie)
                     try:
                         tweet = await x2.fetch_tweet(url)
                     except Exception as e2:
-                        raise ParseError(
-                            f"Twitter 账号可能已被封禁\n\n使用的Cookie: {cookie_ellipsis(self.cookie)}"
-                        ) from e2
+                        raise ParseError(f"Twitter 账号可能已被封禁\n\n使用的Cookie: {self.cookie}") from e2
                 else:
                     raise ParseError(str(e)) from e
             else:

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/xhs.py

@@ -25,7 +25,7 @@ class XHSParser(BaseParser):
     __after_clean_parameters__ = ["xsec_token"]
 
     async def _do_parse(self, raw_url: str) -> Union["VideoParseResult", "ImageParseResult", "MultimediaParseResult"]:
-        xhs = XHSAPI(proxy=self.proxy, cookie=self.cookie)
+        xhs = XHSAPI(proxy=self.proxy, cookie=self.cookie.get_value())
         result = await xhs.extract(raw_url)
 
         desc = self.hashtag_handler(result.desc)

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/parsers/parser/youtube.py

@@ -15,18 +15,19 @@ class YtbParse(YtParser):
     @property
     def params(self) -> dict[str, Any]:
         sub: dict[str, Any] = {
+            "format": "mp4+bestvideo[height<=1080]+bestaudio",
             # "writesubtitles": True, # 下载字幕
             # "writeautomaticsub": True, # 下载自动生成的字幕
             # "subtitlesformat": "ttml", # 字幕格式
             # "subtitleslangs": ["en", "ja", "zh-CN"], # 字幕语言
         }
-        if self.cookie:
-            sub["cookiefile"] = io.StringIO(self.to_netscape_cookie(self.cookie, "youtube.com"))
+        if cookie := self.cookie.get_value():
+            sub["cookiefile"] = io.StringIO(self.to_netscape_cookie(cookie, "youtube.com"))
         p = sub | super().params
         return p
 
     @staticmethod
-    def to_netscape_cookie(cookie: dict, domain: str) -> str | None:
+    def to_netscape_cookie(cookie: dict | None, domain: str) -> str | None:
         """将字典格式 cookie 转为 Netscape 格式字符串
         :param cookie: 字典格式 cookie
         :param domain: cookie 所属域名, 例如 "youtube.com"

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/types/platform.py

@@ -21,6 +21,7 @@ class Platform(Enum):
     XIAOHEIHE = ("xiaoheihe", "小黑盒")
     YOUTUBE = ("youtube", "Youtube")
     ZUIYOU = ("zuiyou", "最右")
+    SNAPCHAT = ("snapchat", "Snapchat")
 
     def __init__(self, platform_id: str, platform_name: str) -> None:
         self.id = platform_id

{parsehub-2.0.31 → parsehub-2.0.32}/src/parsehub/types/result.py

@@ -15,7 +15,7 @@ from slugify import slugify
 from ..config import GlobalConfig
 from ..errors import DeleteError, DownloadError
 from ..utils.downloader import download
-from ..utils.utils import run_sync
+from ..utils.helpers import run_sync
 from .callback import ProgressCallback
 from .media_file import AniFile, AnyMediaFile, ImageFile, LivePhotoFile, VideoFile
 from .media_ref import AniRef, AnyMediaRef, ImageRef, LivePhotoRef, VideoRef
@@ -87,6 +87,7 @@ class ParseResult(ABC):  # noqa: B024
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         headers: dict | None = None,
+        connections: int = 4,
     ) -> "DownloadResult":
         """
         执行下载
@@ -96,6 +97,7 @@ class ParseResult(ABC):  # noqa: B024
         :param callback_kwargs: 回调函数的关键字参数
         :param proxy: 代理
         :param headers: 请求头
+        :param connections: 多线程下载连接数, 默认为 4
         :return: DownloadResult
         """
         if self.media is None:
@@ -134,6 +136,7 @@ class ParseResult(ABC):  # noqa: B024
                     progress=dl_progress,
                     progress_args=dl_progress_args,
                     progress_kwargs=dl_progress_kwargs,
+                    connections=connections,
                 )
             except Exception as e:
                 shutil.rmtree(output_dir, ignore_errors=True)
@@ -161,6 +164,7 @@ class ParseResult(ABC):  # noqa: B024
                                 save_path,
                                 headers=headers,
                                 proxy=proxy,
+                                connections=connections,
                             )
                         except Exception as e:
                             shutil.rmtree(output_dir, ignore_errors=True)
@@ -190,6 +194,7 @@ class ParseResult(ABC):  # noqa: B024
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         save_metadata: bool = False,
+        connections: int = 4,
     ) -> "DownloadResult":
         """
         :param path: 保存路径
@@ -198,6 +203,7 @@ class ParseResult(ABC):  # noqa: B024
         :param callback_kwargs: 回调函数的关键字参数
         :param proxy: 代理
         :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
+        :param connections: 多线程下载连接数, 默认为 4
         :return: DownloadResult
 
         Note:
@@ -230,6 +236,7 @@ class ParseResult(ABC):  # noqa: B024
                 callback_args=callback_args,
                 callback_kwargs=callback_kwargs,
                 proxy=proxy,
+                connections=connections,
             )
         except Exception as e:
             shutil.rmtree(output_dir, ignore_errors=True)
@@ -244,6 +251,7 @@ class ParseResult(ABC):  # noqa: B024
         callback_kwargs: dict | None = None,
         proxy: str | None = None,
         save_metadata: bool = False,
+        connections: int = 4,
     ) -> "DownloadResult":
         """
         :param path: 保存路径
@@ -252,6 +260,7 @@ class ParseResult(ABC):  # noqa: B024
         :param callback_kwargs: 回调函数的关键字参数
         :param proxy: 代理
         :param save_metadata: 保存解析结果为 metadata.json, 默认为 False
+        :param connections: 多线程下载连接数, 默认为 4
         :return: DownloadResult
 
         Note:
@@ -273,6 +282,7 @@ class ParseResult(ABC):  # noqa: B024
                 callback_kwargs=callback_kwargs,
                 proxy=proxy,
                 save_metadata=save_metadata,
+                connections=connections,
             )
         )