feat: fallback to another http client

pyproject.toml

@@ -3,7 +3,7 @@ name = "nonebot-plugin-parser"
 version = "2.6.0"
 description = "NoneBot2 链接分享解析 Alconna 版, 现支持B站|抖音|快手|微博|小红书|YouTube|TikTok|Twitter|AcFun|NGA"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 authors = [{ "name" = "fllesser", "email" = "fllessive@gmail.com" }]
 keywords = [
   "acfun",
@@ -53,6 +53,7 @@ dependencies = [
   "nonebot-plugin-apscheduler>=0.5.0,<1.0.0",
   "nonebot-plugin-localstore>=0.7.4,<1.0.0",
   "nonebot-plugin-uninfo>=0.10.1,<1.0.0",
+  "pyreqwest>=0.11.6",
 ]
 
 [project.urls]
@@ -150,8 +151,8 @@ test-render = "pytest tests/renders --cov=src --cov-report=xml --junitxml=junit.
 bump = "bump-my-version bump"
 show-bump = "bump-my-version show-bump"
 
-[tool.pyright]
-pythonVersion = "3.10"
+[tool.basedpyright]
+pythonVersion = "3.11"
 pythonPlatform = "All"
 defineConstant = { PYDANTIC_V2 = true }
 executionEnvironments = [

src/nonebot_plugin_parser/constants.py

@@ -1,4 +1,4 @@
-from enum import Enum
+from enum import StrEnum
 from typing import Final
 
 from httpx import Timeout
@@ -29,7 +29,7 @@
 DOWNLOAD_TIMEOUT: Final[Timeout] = Timeout(connect=15.0, read=240.0, write=10.0, pool=10.0)
 
 
-class PlatformEnum(str, Enum):
+class PlatformEnum(StrEnum):
     ACFUN = "acfun"
     BILIBILI = "bilibili"
     DOUYIN = "douyin"
@@ -45,7 +45,7 @@ def __str__(self) -> str:
         return self.value
 
 
-class RenderType(str, Enum):
+class RenderType(StrEnum):
     default = "default"
     common = "common"
     htmlkit = "htmlkit"

src/nonebot_plugin_parser/download/__init__.py

@@ -7,6 +7,7 @@
 import aiofiles
 from httpx import HTTPError, AsyncClient
 from nonebot import logger
+from curl_cffi import CurlError
 from rich.progress import (
     Progress,
     BarColumn,
@@ -59,33 +60,87 @@
 
         headers = {**self.headers, **(ext_headers or {})}
 
-        try:
-            async with self.client.stream("GET", url, headers=headers, follow_redirects=True) as response:
-                response.raise_for_status()
-                content_length = response.headers.get("Content-Length")
-                content_length = int(content_length) if content_length else 0
+        async with self.client.stream("GET", url, headers=headers, follow_redirects=True) as response:
+            response.raise_for_status()
+            content_length = response.headers.get("Content-Length")
+            content_length = int(content_length) if content_length else 0
 
-                if content_length == 0:
-                    logger.warning(f"媒体 url: {url}, 大小为 0, 取消下载")
-                    raise IgnoreException
+            if content_length == 0:
+                logger.warning(f"媒体 url: {url}, 大小为 0, 取消下载")
+                raise IgnoreException
 
-                if (file_size := content_length / 1024 / 1024) > pconfig.max_size:
-                    logger.warning(f"媒体 url: {url} 大小 {file_size:.2f} MB, 超过 {pconfig.max_size} MB, 取消下载")
-                    raise IgnoreException
+            if (file_size := content_length / 1024 / 1024) > pconfig.max_size:
+                logger.warning(f"媒体 url: {url} 大小 {file_size:.2f} MB, 超过 {pconfig.max_size} MB, 取消下载")
+                raise IgnoreException
 
-                with self.rich_progress(file_name, content_length) as update_progress:
-                    async with aiofiles.open(file_path, "wb") as file:
-                        async for chunk in response.aiter_bytes(chunk_size):
-                            await file.write(chunk)
-                            update_progress(advance=len(chunk))
+            with self.rich_progress(file_name, content_length) as update_progress:
+                async with aiofiles.open(file_path, "wb") as file:
+                    async for chunk in response.aiter_bytes(chunk_size):
+                        await file.write(chunk)
+                        update_progress(advance=len(chunk))
 
-        except HTTPError:
+        return file_path
+
+    async def _download_file_with_curl_cffi(
+        self,
+        url: str,
+        *,
+        file_name: str | None = None,
+        ext_headers: dict[str, str] | None = None,
+    ) -> Path:
+        from curl_cffi import Response, CurlError, AsyncSession
+
+        if not file_name:
+            file_name = generate_file_name(url)
+        file_path = self.cache_dir / file_name
+        # 如果文件存在，则直接返回
+        if file_path.exists():
+            return file_path
+
+        headers = {**self.headers, **(ext_headers or {})}
+        try:
+            async with AsyncSession() as session:
+                response: Response = await session.get(
+                    url,
+                    headers=headers,
+                    timeout=DOWNLOAD_TIMEOUT,
+                )
+                async with aiofiles.open(file_path, "wb") as file:
+                    await file.write(response.content)
+        except CurlError:
             await safe_unlink(file_path)
             logger.exception(f"下载失败 | url: {url}, file_path: {file_path}")
             raise DownloadException("媒体下载失败")
 
         return file_path
 
+    async def _download_file_with_reqwest(
+        self,
+        url: str,
+        *,
+        file_name: str | None = None,
+        ext_headers: dict[str, str] | None = None,
+    ):
+        """download file by url with reqwest"""
+        from pyreqwest.simple.request import pyreqwest_get
+
+        if not file_name:
+            file_name = generate_file_name(url)
+
+        file_path = self.cache_dir / file_name
+        # 如果文件存在，则直接返回
+        if file_path.exists():
+            return file_path
+
+        headers = {**self.headers, **(ext_headers or {})}
+
+        reponse = await pyreqwest_get(url).headers(headers).send()
+
+        async with aiofiles.open(file_path, "wb") as file:
+            await file.write(await reponse.bytes())
+
+        return file_path
+
     @auto_task
     async def download_file(
         self,
@@ -96,12 +151,17 @@
         chunk_size: int = 64 * 1024,
     ) -> Path:
         """download file by url with stream"""
-        return await self._download_file(
-            url,
-            file_name=file_name,
-            ext_headers=ext_headers,
-            chunk_size=chunk_size,
-        )
+        try:
+            path = await self._download_file(url, file_name=file_name, ext_headers=ext_headers, chunk_size=chunk_size)
+        except HTTPError:
+            logger.opt(exception=True).warning(f"下载失败(httpx) | url: {url}")
+            try:
+                path = await self._download_file_with_reqwest(url, file_name=file_name, ext_headers=ext_headers)
+            except CurlError:
+                logger.opt(exception=True).warning(f"下载失败(curl_cffi) | url: {url}")
+                raise DownloadException("媒体下载失败")
+
+        return path
 
     @auto_task
     async def download_video(

src/nonebot_plugin_parser/parsers/base.py

@@ -1,10 +1,10 @@
 from re import Match, Pattern, compile
 from abc import ABC
-from typing import TYPE_CHECKING, Any, TypeVar, ClassVar, cast
+from typing import TYPE_CHECKING, Any, TypeVar, ClassVar, cast, final
 from asyncio import Task
 from pathlib import Path
 from collections.abc import Callable, Coroutine
-from typing_extensions import Unpack, final
+from typing_extensions import Unpack
 
 from .data import Platform, ParseResult, ImageContent, ParseResultKwargs
 from .task import PathTask