parsehub 2.1.6__tar.gz → 2.1.7__tar.gz

{parsehub-2.1.6/src/parsehub.egg-info → parsehub-2.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.1.6
+Version: 2.1.7
 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-2.1.6 → parsehub-2.1.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.1.6"
+version = "2.1.7"
 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-2.1.6 → parsehub-2.1.7}/src/parsehub/parsers/base/base.py

@@ -77,11 +77,12 @@ class BaseParser(ABC):
         """
         raise NotImplementedError
 
-    async def get_raw_url(self, url: str, clean_all: bool = False) -> str:
+    async def get_raw_url(self, url: str, *, clean_all: bool = False, headers: dict | None = None) -> str:
         """
         清除链接中的参数
         :param url: 链接
         :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)
+        :param headers: 请求头, 默认为 {"User-Agent": UA}, 不需要请求头需传入空字典
 
         Example:
             以小红书为例，其解析器配置如下::
@@ -109,13 +110,14 @@ class BaseParser(ABC):
         url = matched_url or url
         if not url.startswith("http"):
             url = f"https://{url}"
+
         if any(x in url for x in self.__redirect_keywords__):
             async with httpx.AsyncClient(proxy=self.proxy, timeout=30) as client:
                 try:
                     r = await client.get(
                         url,
                         follow_redirects=True,
-                        headers={"User-Agent": UA},
+                        headers={"User-Agent": UA} if headers is None else headers,
                     )
                 except (httpx.ReadTimeout, httpx.ConnectTimeout) as e:
                     raise ParseError("获取原始链接超时") from e

{parsehub-2.1.6 → parsehub-2.1.7}/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
@@ -34,7 +34,7 @@ class BiliParse(BaseParser):
     async def _do_parse(self, raw_url: str) -> YtVideoParseResult | BiliVideoParseResult | ImageParseResult:
         if await self.is_dynamic(raw_url):
             dynamic = await self.get_dynamic_info(raw_url)
-            content = self.hashtag_handler(dynamic.content)
+            content = self.hashtag_handler(dynamic.content or "")
             photos: list[LivePhotoRef | ImageRef] = []
             if dynamic.images:
                 for i in dynamic.images:
@@ -43,7 +43,7 @@ class BiliParse(BaseParser):
                     else:
                         photos.append(ImageRef(url=i.url, width=i.width, height=i.height))
             return ImageParseResult(
-                title=dynamic.title,
+                title=dynamic.title or "",
                 content=content,
                 photo=photos,
             )
@@ -65,18 +65,18 @@ class BiliParse(BaseParser):
             return False
 
     @classmethod
-    def match(cls, url: str) -> bool:
-        if cls._is_bvid(url):
+    def match(cls, text: str) -> bool:
+        if cls._is_bvid(text):
             return True
         else:
-            return super().match(url)
+            return super().match(text)
 
-    async def get_raw_url(self, url: str, clean_all: bool = False) -> str:
+    async def get_raw_url(self, url: str, **kwargs: Any) -> 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, clean_all=clean_all)
+            return await super().get_raw_url(url, **kwargs)
 
     @staticmethod
     async def is_dynamic(url: str) -> str | None:
@@ -86,14 +86,15 @@ class BiliParse(BaseParser):
         return None
 
     async def get_dynamic_info(self, url: str) -> BiliDynamic:
-        async with BiliAPI(proxy=self.proxy) as bili:
-            try:
+        try:
+            async with BiliAPI(proxy=self.proxy) as bili:
                 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: {self.cookie}") from e
-                raise ParseError(str(e)) from e
-        return cast(BiliDynamic, dynamic_info)
+        except Exception as e:
+            if "风控" in str(e):
+                raise ParseError(f"账号风控\n使用的cookie: {self.cookie}") from e
+            raise ParseError(str(e)) from e
+        else:
+            return cast(BiliDynamic, dynamic_info)
 
     async def bili_api_parse(self, url: str) -> BiliVideoParseResult | ImageParseResult:
         async with BiliAPI(proxy=self.proxy) as bili:

{parsehub-2.1.6 → parsehub-2.1.7}/src/parsehub/parsers/parser/instagram.py

@@ -61,7 +61,7 @@ class InstagramParser(BaseParser):
                     else:
                         raise ParseError("受限视频无法解析: 你必须年满 18 周岁才能观看这个视频") from e
                 case _:
-                    raise ParseError("无法获取帖子内容(可能为私人内容)") from e
+                    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}"

{parsehub-2.1.6 → parsehub-2.1.7}/src/parsehub/parsers/parser/threads.py

@@ -6,7 +6,11 @@ from ..base.base import BaseParser
 class ThreadsParser(BaseParser):
     __platform__ = Platform.THREADS
     __supported_type__ = ["视频", "图文"]
-    __match__ = r"^(http(s)?://)?.+threads.com/@[\w.]+/post/.*"
+    __match__ = r"^(http(s)?://)?.+threads.com/(@[\w.]+/post|share)/.*"
+    __redirect_keywords__ = ["/share/"]
+
+    async def get_raw_url(self, url: str, *, clean_all: bool = False, headers: dict | None = None) -> str:
+        return await super().get_raw_url(url, clean_all=clean_all, headers={})
 
     async def _do_parse(self, raw_url: str) -> "MultimediaParseResult":
         post = await self._parse(raw_url)

{parsehub-2.1.6 → parsehub-2.1.7}/src/parsehub/parsers/parser/twitter.py

@@ -1,3 +1,4 @@
+from typing import Any
 from urllib.parse import urlparse, urlunparse
 
 from ...provider_api.twitter import (
@@ -29,8 +30,8 @@ class TwitterParser(BaseParser):
         tweet = await self._parse(raw_url)
         return await self.media_parse(tweet)
 
-    async def get_raw_url(self, url: str, clean_all: bool = False) -> str:
-        url = await super().get_raw_url(url, clean_all=clean_all)
+    async def get_raw_url(self, url: str, **kwargs: Any) -> str:
+        url = await super().get_raw_url(url, **kwargs)
         return str(urlunparse(urlparse(url)._replace(netloc="x.com")))
 
     async def _parse(self, url: str) -> TwitterTweet:

{parsehub-2.1.6 → parsehub-2.1.7}/src/parsehub/provider_api/bilibili.py

@@ -8,7 +8,7 @@ from dataclasses import dataclass
 from enum import Enum
 from functools import reduce
 from hashlib import md5
-from typing import Any, cast
+from typing import Any, Self, cast
 
 import httpx
 
@@ -245,12 +245,12 @@ class BiliImage:
 
 @dataclass(kw_only=True)
 class BiliDynamic:
-    title: str = ""
-    content: str = ""
+    title: str | None = ""
+    content: str | None = ""
     images: list[BiliImage] | None = None
 
     @classmethod
-    def parse(cls, data: dict) -> "BiliDynamic":
+    def parse(cls, data: dict) -> Self:
         module_dynamic: dict = data["item"]["modules"]["module_dynamic"]
         major: dict | None = module_dynamic.get("major", None)
         if not major:
@@ -259,9 +259,9 @@ class BiliDynamic:
             return cls._parse_major(module_dynamic, major)
 
     @classmethod
-    def _parse_major(cls, module_dynamic: dict, major: dict) -> "BiliDynamic":
+    def _parse_major(cls, module_dynamic: dict, major: dict) -> Self:
         major_type = major["type"]
-        major_parsers: dict[MajorType, Callable[[dict, dict], BiliDynamic]] = {
+        major_parsers: dict[MajorType, Callable[[dict, dict], Self]] = {
             MajorType.MAJOR_TYPE_MEDIALIST: cls._parse_medialist,
             MajorType.MAJOR_TYPE_UPOWER_COMMON: cls._parse_upower_common,
             MajorType.MAJOR_TYPE_COMMON: cls._parse_common,
@@ -279,30 +279,30 @@ class BiliDynamic:
         return major_parser(module_dynamic, major)
 
     @classmethod
-    def _parse_pgc_union(cls, _: dict, major: dict) -> "BiliDynamic":
+    def _parse_pgc_union(cls, _: dict, major: dict) -> Self:
         pgc = major["pgc"]
         return cls(title=pgc["title"], images=[BiliImage(url=pgc["cover"])])
 
     @classmethod
-    def _parse_forward(cls, module_dynamic: dict) -> "BiliDynamic":
+    def _parse_forward(cls, module_dynamic: dict) -> Self:
         return cls(content=cls._get_desc_text(module_dynamic))
 
     @classmethod
-    def _parse_av(cls, module_dynamic: dict, major: dict):
+    def _parse_av(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         archive = major["archive"]
         return cls(title=archive["title"], content=archive["desc"], images=cls._get_major_cover(archive))
 
     @classmethod
-    def _parse_music(cls, module_dynamic: dict, major: dict):
+    def _parse_music(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         music = major["music"]
         return cls(title=music["title"], images=cls._get_major_cover(music))
 
     @classmethod
-    def _parse_opus(cls, _: dict, major: dict) -> "BiliDynamic":
+    def _parse_opus(cls, _: dict, major: dict) -> Self:
         opus = major["opus"]
         images = None
         if pics := opus["pics"]:
@@ -312,14 +312,14 @@ class BiliDynamic:
         return cls(title=opus["title"], content=opus["summary"]["text"], images=images)
 
     @classmethod
-    def _parse_common(cls, module_dynamic: dict, major: dict):
+    def _parse_common(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         common = major["common"]
         return cls(title=common["title"], content=common["desc"], images=cls._get_major_cover(common))
 
     @classmethod
-    def _parse_live(cls, module_dynamic: dict, major: dict):
+    def _parse_live(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         live = major["live"]
@@ -327,14 +327,14 @@ class BiliDynamic:
         return cls(title=live["title"], content=content, images=cls._get_major_cover(live))
 
     @classmethod
-    def _parse_medialist(cls, module_dynamic: dict, major: dict):
+    def _parse_medialist(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         medialist = major["medialist"]
         return cls(title=medialist["title"], content=medialist["sub_title"], images=cls._get_major_cover(medialist))
 
     @classmethod
-    def _parse_courses(cls, module_dynamic: dict, major: dict):
+    def _parse_courses(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         courses = major["courses"]
@@ -342,14 +342,14 @@ class BiliDynamic:
         return cls(title=courses["title"], content=content, images=cls._get_major_cover(courses))
 
     @classmethod
-    def _parse_ugc_season(cls, module_dynamic: dict, major: dict):
+    def _parse_ugc_season(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         ugc_season = major["ugc_season"]
         return cls(title=ugc_season["title"], content=ugc_season["desc"], images=cls._get_major_cover(ugc_season))
 
     @classmethod
-    def _parse_upower_common(cls, module_dynamic: dict, major: dict):
+    def _parse_upower_common(cls, module_dynamic: dict, major: dict) -> Self:
         if content := cls._get_desc_text(module_dynamic):
             return cls(content=content)
         upower_common = major["upower_common"]

{parsehub-2.1.6 → parsehub-2.1.7/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.1.6
+Version: 2.1.7
 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-2.1.6 → parsehub-2.1.7}/test/test_core_offline.py

@@ -348,6 +348,7 @@ class TestPlatformUrlMatching(unittest.TestCase):
             Platform.THREADS: [
                 "https://www.threads.com/@zaborona.magazine/post/DBuqMBwMfxW",
                 "https://www.threads.com/@user_name/post/DBuqMBwMfxW",
+                "https://www.threads.com/share/Dq6fjYWK-/",
             ],
             Platform.TIEBA: [
                 "https://tieba.baidu.com/p/9939510114",