parsehub 2.4.0__tar.gz → 2.4.1__tar.gz

{parsehub-2.4.0/src/parsehub.egg-info → parsehub-2.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.4.0
+Version: 2.4.1
 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
@@ -15,32 +15,32 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.12.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: aiofiles>=23.2
-Requires-Dist: beautifulsoup4>=4.12.3
-Requires-Dist: loguru>=0.6.0
+Requires-Dist: aiofiles>=25.1.0
+Requires-Dist: beautifulsoup4>=4.15.0
+Requires-Dist: loguru>=0.7.3
 Requires-Dist: pydub>=0.25.1
-Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: tenacity>=8.5.0
-Requires-Dist: urlextract>=1.9.0
-Requires-Dist: yt-dlp[default]>=2026.10.26.220202.dev0
-Requires-Dist: lxml>=5.3.0
-Requires-Dist: pydantic>=1.10.19
-Requires-Dist: markdownify>=1.1.0
-Requires-Dist: markdown>=3.7
-Requires-Dist: json5>=0.12
-Requires-Dist: requests
-Requires-Dist: httpx[socks]>=0.24.1
-Requires-Dist: pillow>=12.1.0
-Requires-Dist: python-slugify[unidecode]>=8.0.4
-Requires-Dist: opencv-python-headless>=4.13.0.92
-Requires-Dist: cryptography>=49.0.0
+Requires-Dist: python-dotenv>=1.2.4
+Requires-Dist: tenacity>=9.2.1
+Requires-Dist: urlextract>=1.10.0
+Requires-Dist: yt-dlp[default]>=2026.11.4.232659.dev0
+Requires-Dist: lxml>=6.1.3
+Requires-Dist: pydantic>=2.14.3
+Requires-Dist: markdownify>=1.2.3
+Requires-Dist: markdown>=3.11.3
+Requires-Dist: json5>=0.17.3
+Requires-Dist: requests>=2.34.2
+Requires-Dist: httpx[socks]>=0.28.1
+Requires-Dist: pillow>=13.0.0
+Requires-Dist: python-slugify[unidecode]>=9.1.3
+Requires-Dist: opencv-python-headless>=5.0.0.93
+Requires-Dist: cryptography>=50.0.2
 Requires-Dist: gmssl>=3.2.2
 Requires-Dist: signerpy>=0.12.0
-Requires-Dist: curl-cffi>=0.13
+Requires-Dist: curl-cffi>=0.17.0
 Requires-Dist: xhshow>=0.2.0
 Provides-Extra: cli
-Requires-Dist: argcomplete>=3.6.3; extra == "cli"
-Requires-Dist: platformdirs>=4.5.1; extra == "cli"
+Requires-Dist: argcomplete>=3.7.2; extra == "cli"
+Requires-Dist: platformdirs>=4.14.5; extra == "cli"
 Dynamic: license-file
 
 <div align="center">

{parsehub-2.4.0 → parsehub-2.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.4.0"
+version = "2.4.1"
 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"
@@ -18,28 +18,28 @@ classifiers = [
 ]
 
 dependencies = [
-    "aiofiles>=23.2",
-    "beautifulsoup4>=4.12.3",
-    "loguru>=0.6.0",
+    "aiofiles>=25.1.0",
+    "beautifulsoup4>=4.15.0",
+    "loguru>=0.7.3",
     "pydub>=0.25.1",
-    "python-dotenv>=1.0.1",
-    "tenacity>=8.5.0",
-    "urlextract>=1.9.0",
-    "yt-dlp[default]>=2026.10.26.220202.dev0",
-    "lxml>=5.3.0",
-    "pydantic>=1.10.19",
-    "markdownify>=1.1.0",
-    "markdown>=3.7",
-    "json5>=0.12",
-    "requests",
-    "httpx[socks]>=0.24.1",
-    "pillow>=12.1.0",
-    "python-slugify[unidecode]>=8.0.4",
-    "opencv-python-headless>=4.13.0.92",
-    "cryptography>=49.0.0",
+    "python-dotenv>=1.2.4",
+    "tenacity>=9.2.1",
+    "urlextract>=1.10.0",
+    "yt-dlp[default]>=2026.11.4.232659.dev0",
+    "lxml>=6.1.3",
+    "pydantic>=2.14.3",
+    "markdownify>=1.2.3",
+    "markdown>=3.11.3",
+    "json5>=0.17.3",
+    "requests>=2.34.2",
+    "httpx[socks]>=0.28.1",
+    "pillow>=13.0.0",
+    "python-slugify[unidecode]>=9.1.3",
+    "opencv-python-headless>=5.0.0.93",
+    "cryptography>=50.0.2",
     "gmssl>=3.2.2",
     "signerpy>=0.12.0",
-    "curl-cffi>=0.13",
+    "curl-cffi>=0.17.0",
     "xhshow>=0.2.0",
 ]
 
@@ -49,15 +49,15 @@ ph = "parsehub.cli:main"
 
 [project.optional-dependencies]
 cli = [
-    "argcomplete>=3.6.3",
-    "platformdirs>=4.5.1",
+    "argcomplete>=3.7.2",
+    "platformdirs>=4.14.5",
 ]
 
 [dependency-groups]
 dev = [
-    "mypy>=2.1.0",
-    "pytest>=9.0.3",
-    "ruff>=0.14.14",
+    "mypy>=2.4.1",
+    "pytest>=9.2.0",
+    "ruff>=0.17.4",
 ]
 
 [tool.hatch.build.targets.wheel]

{parsehub-2.4.0 → parsehub-2.4.1}/src/parsehub/parsers/parser/instagram.py

@@ -66,7 +66,7 @@ class InstagramParser(BaseParser):
                 except ParseError as e:
                     logger.warning(f"Instagram yt-dlp 解析失败, 使用直链视频: {e}")
                 else:
-                    return YtVideoParseResult(
+                    return InstagramYtVideoParseResult(
                         dl=info,
                         title=post.title,
                         content=post.caption,
@@ -98,12 +98,8 @@ class InstagramParser(BaseParser):
     async def _parse(self, shortcode: str) -> InstagramPost:
         stages: list[FallbackStage[InstagramPost]] = [FallbackStage("匿名", lambda: self._fetch(shortcode))]
         if self.cookie.get_value():
-            stages.append(
-                FallbackStage("cookie", lambda: self._fetch(shortcode, self.cookie), cookie=True)
-            )
-        return await self._fallback(
-            *stages, stop=lambda e: not isinstance(e.__cause__, InstagramRestrictedError)
-        )
+            stages.append(FallbackStage("cookie", lambda: self._fetch(shortcode, self.cookie), cookie=True))
+        return await self._fallback(*stages, stop=lambda e: not isinstance(e.__cause__, InstagramRestrictedError))
 
     async def _fetch(self, shortcode: str, cookie: SecretCookie | None = None) -> InstagramPost:
         api = InstagramAPI(proxy=self.proxy, cookie=cookie.get_value() if cookie else None, timeout=30)
@@ -127,4 +123,10 @@ class InstagramYtParse(YtParser, register=False):
     pass
 
 
+class InstagramYtVideoParseResult(YtVideoParseResult):
+    @property
+    def cli_args(self) -> list[str]:
+        return [*super().cli_args, "-S", "vcodec:h264"]
+
+
 __all__ = ["InstagramParser"]

{parsehub-2.4.0 → parsehub-2.4.1}/src/parsehub/parsers/parser/kuaishou.py

@@ -46,6 +46,7 @@ class KuaiShouParser(BaseParser):
         if (
             ksp.page_type == "VIDEO" or "/short-video/" in raw_url
         ):  # 地区风控导致获取到的 page_type 可能为 ATLAS 但实际为视频
+
             async def parse_html() -> VideoParseResult:
                 content = ksp.get_title_content()
                 video = ksp.get_real_video_url()

{parsehub-2.4.0 → parsehub-2.4.1}/src/parsehub/provider_api/instagram.py

@@ -131,8 +131,7 @@ class InstagramAPI:
     ) -> InstagramPost:
         """用 embed 补齐 v1 / GraphQL 缺失的视频直链和时长。"""
         if not any(
-            (post.type is InstagramMediaType.VIDEO or item.is_video)
-            and (not item.video_url or item.duration <= 0)
+            (post.type is InstagramMediaType.VIDEO or item.is_video) and (not item.video_url or item.duration <= 0)
             for item in post.media
         ):
             return post

{parsehub-2.4.0 → parsehub-2.4.1}/src/parsehub/provider_api/wxchannels.py

@@ -95,9 +95,7 @@ class WXChannels:
 
         feed_data = feed_result.get("data") or {}
         feed_error = feed_data.get("errMsg") or {}
-        error_text = " ".join(
-            _strip_html(str(feed_error.get(key) or "")) for key in ("title", "content")
-        ).strip()
+        error_text = " ".join(_strip_html(str(feed_error.get(key) or "")) for key in ("title", "content")).strip()
         if feed_result.get("errCode") != 0:
             message = feed_result.get("errMsg") or "微信视频号解析失败"
             raise WXChannelsError(str(message))

{parsehub-2.4.0 → parsehub-2.4.1/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.4.0
+Version: 2.4.1
 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
@@ -15,32 +15,32 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.12.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: aiofiles>=23.2
-Requires-Dist: beautifulsoup4>=4.12.3
-Requires-Dist: loguru>=0.6.0
+Requires-Dist: aiofiles>=25.1.0
+Requires-Dist: beautifulsoup4>=4.15.0
+Requires-Dist: loguru>=0.7.3
 Requires-Dist: pydub>=0.25.1
-Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: tenacity>=8.5.0
-Requires-Dist: urlextract>=1.9.0
-Requires-Dist: yt-dlp[default]>=2026.10.26.220202.dev0
-Requires-Dist: lxml>=5.3.0
-Requires-Dist: pydantic>=1.10.19
-Requires-Dist: markdownify>=1.1.0
-Requires-Dist: markdown>=3.7
-Requires-Dist: json5>=0.12
-Requires-Dist: requests
-Requires-Dist: httpx[socks]>=0.24.1
-Requires-Dist: pillow>=12.1.0
-Requires-Dist: python-slugify[unidecode]>=8.0.4
-Requires-Dist: opencv-python-headless>=4.13.0.92
-Requires-Dist: cryptography>=49.0.0
+Requires-Dist: python-dotenv>=1.2.4
+Requires-Dist: tenacity>=9.2.1
+Requires-Dist: urlextract>=1.10.0
+Requires-Dist: yt-dlp[default]>=2026.11.4.232659.dev0
+Requires-Dist: lxml>=6.1.3
+Requires-Dist: pydantic>=2.14.3
+Requires-Dist: markdownify>=1.2.3
+Requires-Dist: markdown>=3.11.3
+Requires-Dist: json5>=0.17.3
+Requires-Dist: requests>=2.34.2
+Requires-Dist: httpx[socks]>=0.28.1
+Requires-Dist: pillow>=13.0.0
+Requires-Dist: python-slugify[unidecode]>=9.1.3
+Requires-Dist: opencv-python-headless>=5.0.0.93
+Requires-Dist: cryptography>=50.0.2
 Requires-Dist: gmssl>=3.2.2
 Requires-Dist: signerpy>=0.12.0
-Requires-Dist: curl-cffi>=0.13
+Requires-Dist: curl-cffi>=0.17.0
 Requires-Dist: xhshow>=0.2.0
 Provides-Extra: cli
-Requires-Dist: argcomplete>=3.6.3; extra == "cli"
-Requires-Dist: platformdirs>=4.5.1; extra == "cli"
+Requires-Dist: argcomplete>=3.7.2; extra == "cli"
+Requires-Dist: platformdirs>=4.14.5; extra == "cli"
 Dynamic: license-file
 
 <div align="center">

{parsehub-2.4.0 → parsehub-2.4.1}/src/parsehub.egg-info/SOURCES.txt

@@ -76,11 +76,7 @@ src/parsehub/utils/downloader.py
 src/parsehub/utils/fallback.py
 src/parsehub/utils/helpers.py
 src/parsehub/utils/media_info.py
-test/test_bilibili_music_offline.py
-test/test_bilibili_offline.py
 test/test_cli.py
 test/test_cli_config.py
 test/test_core_offline.py
-test/test_downloader.py
-test/test_instagram_duration_offline.py
-test/test_zuiyou_duration_offline.py
+test/test_downloader.py

parsehub-2.4.1/src/parsehub.egg-info/requires.txt

@@ -0,0 +1,27 @@
+aiofiles>=25.1.0
+beautifulsoup4>=4.15.0
+loguru>=0.7.3
+pydub>=0.25.1
+python-dotenv>=1.2.4
+tenacity>=9.2.1
+urlextract>=1.10.0
+yt-dlp[default]>=2026.11.4.232659.dev0
+lxml>=6.1.3
+pydantic>=2.14.3
+markdownify>=1.2.3
+markdown>=3.11.3
+json5>=0.17.3
+requests>=2.34.2
+httpx[socks]>=0.28.1
+pillow>=13.0.0
+python-slugify[unidecode]>=9.1.3
+opencv-python-headless>=5.0.0.93
+cryptography>=50.0.2
+gmssl>=3.2.2
+signerpy>=0.12.0
+curl-cffi>=0.17.0
+xhshow>=0.2.0
+
+[cli]
+argcomplete>=3.7.2
+platformdirs>=4.14.5

{parsehub-2.4.0 → parsehub-2.4.1}/test/test_core_offline.py

@@ -1,25 +1,10 @@
 import unittest
-from pathlib import Path
-from unittest.mock import AsyncMock, patch
 from urllib.parse import parse_qs, urlparse
 
-import httpx
-
 from parsehub import ParseHub
 from parsehub.errors import ParseError, UnknownPlatform
 from parsehub.parsers.base import BaseParser
-from parsehub.parsers.parser.douban import DoubanParser, DoubanRichTextParseResult
-from parsehub.parsers.parser.douyin import parse_video_info
-from parsehub.provider_api.douban import (
-    IMAGE_REFERER,
-    Douban,
-    DoubanError,
-    DoubanPhoto,
-    DoubanTopic,
-    DoubanVideo,
-)
-from parsehub.provider_api.douyin import DouyinMobileCrawler, DouyinMobileDevice
-from parsehub.types import AniRef, ImageParseResult, ImageRef, ParseResult, Platform, VideoParseResult, VideoRef
+from parsehub.types import ImageParseResult, ImageRef, Platform, VideoParseResult, VideoRef
 from parsehub.utils.helpers import SecretCookie, match_url, run_sync
 
 
@@ -225,325 +210,6 @@ class TestParseResultToDict(unittest.TestCase):
         )
 
 
-class TestDouyinStorySupport(unittest.TestCase):
-    def test_mobile_device_can_be_loaded_from_env(self):
-        with patch.dict(
-            "os.environ",
-            {
-                "PARSEHUB_DOUYIN_DEVICE_ID": "1325343490970016",
-                "PARSEHUB_DOUYIN_IID": "1325343490974112",
-            },
-            clear=True,
-        ):
-            device = DouyinMobileDevice.from_env()
-
-        self.assertIsNotNone(device)
-        assert device is not None
-        self.assertEqual(device.device_id, "1325343490970016")
-        self.assertEqual(device.iid, "1325343490974112")
-
-    def test_mobile_device_can_be_loaded_from_register_response(self):
-        device = DouyinMobileDevice.from_register_response(
-            {
-                "device_id": 1219790537803243,
-                "install_id": 1219790537807339,
-                "device_id_str": "1219790537803243",
-                "install_id_str": "1219790537807339",
-            },
-            cdid="demo-cdid",
-            openudid="demo-openudid",
-        )
-
-        self.assertIsNotNone(device)
-        assert device is not None
-        self.assertEqual(device.device_id, "1219790537803243")
-        self.assertEqual(device.iid, "1219790537807339")
-        self.assertEqual(device.cdid, "demo-cdid")
-        self.assertEqual(device.openudid, "demo-openudid")
-
-    def test_mobile_device_pool_round_robin(self):
-        old_pool = DouyinMobileCrawler._device_pool
-        old_index = DouyinMobileCrawler._device_pool_index
-        try:
-            DouyinMobileCrawler._device_pool = [
-                DouyinMobileDevice(device_id="1", iid="11"),
-                DouyinMobileDevice(device_id="2", iid="22"),
-                DouyinMobileDevice(device_id="3", iid="33"),
-            ]
-            DouyinMobileCrawler._device_pool_index = 0
-
-            picked = [DouyinMobileCrawler._next_pooled_device().device_id for _ in range(5)]
-
-            self.assertEqual(picked, ["1", "2", "3", "1", "2"])
-        finally:
-            DouyinMobileCrawler._device_pool = old_pool
-            DouyinMobileCrawler._device_pool_index = old_index
-
-    def test_parse_video_info_prefers_story_default_play_url_by_data_size(self):
-        video_data = {
-            "duration": 9682,
-            "cover": {"url_list": ["https://cdn.example/thumb.jpg"]},
-            "bit_rate": [
-                {
-                    "bit_rate": 0,
-                    "play_addr": {
-                        "url_list": ["https://cdn.example/story-default.mp4"],
-                        "width": 720,
-                        "height": 1280,
-                        "data_size": 7567631,
-                    },
-                },
-                {
-                    "bit_rate": 632,
-                    "play_addr": {
-                        "url_list": ["https://cdn.example/720p.mp4"],
-                        "width": 720,
-                        "height": 1280,
-                        "data_size": 783567,
-                    },
-                },
-            ],
-        }
-
-        info = parse_video_info(video_data)
-
-        self.assertEqual(info["video_url"], "https://cdn.example/story-default.mp4")
-        self.assertEqual(info["thumb_url"], "https://cdn.example/thumb.jpg")
-        self.assertEqual(info["duration"], 9682)
-
-
-class TestDoubanTopicParsing(unittest.TestCase):
-    @staticmethod
-    def _photo(image: dict, width: int = 500, height: int = 400) -> dict:
-        return {"id": "1", "image": image, "size": {"width": width, "height": height}}
-
-    def test_error_messages_prefer_chinese_and_contextualise_raw_codes(self):
-        cases = [
-            # 豆瓣给了中文提示时直接透出
-            ({"localized_message": "这篇内容不存在了", "msg": "topic not found"}, "这篇内容不存在了"),
-            # 只有英文错误码时补上中文上下文, 避免用户只看到 need_permission
-            ({"msg": "need_permission"}, "获取话题内容失败: need_permission"),
-            ({}, "获取话题内容失败: HTTP 403"),
-        ]
-        for payload, expected in cases:
-            with self.subTest(payload=payload):
-                response = httpx.Response(403, json=payload)
-                with patch.object(httpx.AsyncClient, "get", new=AsyncMock(return_value=response)):
-                    with self.assertRaises(DoubanError) as ctx:
-                        run_sync(Douban().fetch_topic_data("https://www.douban.com/group/topic/1/"))
-                self.assertEqual(ctx.exception.msg, expected)
-
-    def test_get_topic_id_accepts_both_topic_url_forms(self):
-        # /group/topic/<id> 与 /topic/<id> 共用同一套 ID 与接口
-        self.assertEqual(Douban.get_topic_id("https://www.douban.com/group/topic/495373106/"), "495373106")
-        self.assertEqual(Douban.get_topic_id("https://www.douban.com/topic/492821052/"), "492821052")
-
-    def test_get_topic_id_rejects_non_topic_url(self):
-        for url in (
-            "https://movie.douban.com/subject/1292052/",
-            # 话题广场是另一套 ID, 不能被 /topic/ 规则误匹配
-            "https://www.douban.com/gallery/topic/125573/",
-            # 广播是另一种内容类型, 接口与数据结构均不同
-            "https://m.douban.com/people/182691094/status/9372433345/",
-        ):
-            with self.subTest(url=url), self.assertRaises(DoubanError):
-                Douban.get_topic_id(url)
-
-    def test_photo_topic_prefers_large_and_keeps_inline_markdown(self):
-        large = "https://img3.doubanio.com/view/group_topic/l/public/p1.jpg"
-        small = "https://img3.doubanio.com/view/group_topic/m/public/p1.jpg"
-        topic = DoubanTopic.parse(
-            {
-                "title": "标题",
-                "content": f"<div id='content'><p>正文</p><img src=\"{large}\"/></div>",
-                "photos": [
-                    self._photo(
-                        {
-                            "is_animated": False,
-                            "large": {"url": large, "width": 500, "height": 482},
-                            "normal": {"url": small, "width": 200, "height": 193},
-                        }
-                    )
-                ],
-            }
-        )
-
-        self.assertEqual(topic.text_content, "正文")
-        self.assertIn(large, topic.markdown_content)
-        # 取 large 作正片, normal 退为缩略图
-        self.assertEqual(topic.photos, [DoubanPhoto(url=large, ext="jpg", thumb_url=small, width=500, height=482)])
-
-    def test_animated_photo_uses_mp4_variant(self):
-        topic = DoubanTopic.parse(
-            {
-                "title": "动图",
-                "content": "",
-                "photos": [
-                    self._photo(
-                        {
-                            "is_animated": True,
-                            # large 是体积极大的原始 GIF, 应优先取 video
-                            "large": {"url": "https://img3.doubanio.com/view/group_topic/raw/public/p2.jpg"},
-                            "normal": {"url": "https://img3.doubanio.com/view/group_topic/l/public/p2.jpg"},
-                            "video": {
-                                "url": "https://img3.doubanio.com/view/group_topic/l/public/p2.mp4",
-                                "width": 500,
-                                "height": 291,
-                            },
-                        }
-                    )
-                ],
-            }
-        )
-
-        self.assertEqual(
-            topic.photos,
-            [
-                DoubanPhoto(
-                    url="https://img3.doubanio.com/view/group_topic/l/public/p2.mp4",
-                    ext="mp4",
-                    thumb_url="https://img3.doubanio.com/view/group_topic/l/public/p2.jpg",
-                    width=500,
-                    height=291,
-                    is_animated=True,
-                )
-            ],
-        )
-
-    def test_video_topic_converts_duration_to_seconds(self):
-        topic = DoubanTopic.parse(
-            {
-                "title": "视频",
-                "content": "<div id='content'><p>说明</p></div>",
-                "photos": [],
-                "video_info": {
-                    "video_url": "https://sv1.doubanio.com/example.mp4",
-                    "cover_url": "https://sv1.doubanio.com/example_cover.png",
-                    "duration": "01:05",
-                    "video_width": 720,
-                    "video_height": 1280,
-                },
-            }
-        )
-
-        self.assertEqual(
-            topic.video,
-            DoubanVideo(
-                url="https://sv1.doubanio.com/example.mp4",
-                thumb_url="https://sv1.doubanio.com/example_cover.png",
-                width=720,
-                height=1280,
-                duration=65,
-            ),
-        )
-
-    def test_video_info_without_url_is_ignored(self):
-        """video_info 缺 video_url 时不该当成视频话题"""
-        topic = DoubanTopic.parse({"title": "t", "content": "", "photos": [], "video_info": {"duration": "00:12"}})
-
-        self.assertEqual(topic.photos, [])
-
-
-class TestDoubanParserResultTypes(unittest.IsolatedAsyncioTestCase):
-    @staticmethod
-    def _topic(**kwargs) -> DoubanTopic:
-        defaults: dict = {
-            "title": "标题",
-            "markdown_content": "",
-            "text_content": "",
-            "image_layout": "vertical",  # 默认图文混排, 走 RichText 分支
-            "video": None,
-            "photos": [],
-        }
-        return DoubanTopic(**{**defaults, **kwargs})
-
-    @staticmethod
-    async def _parse(topic: DoubanTopic):
-        with patch.object(Douban, "parse", new=AsyncMock(return_value=topic)):
-            return await DoubanParser()._do_parse("https://www.douban.com/group/topic/1/")
-
-    async def test_topic_always_returns_richtext(self):
-        """图 / 视频 / 纯文字 任意组合都走 RichText, 不再区分纯图"""
-        photo = DoubanPhoto(url="https://img3.doubanio.com/p1.jpg", width=500, height=482)
-        video = DoubanVideo(url="https://sv1.doubanio.com/a.mp4", duration=39)
-        img_md = "正文\n\n![](https://img3.doubanio.com/p1.jpg)"
-        cases = {
-            # markdown 必须原样带过去: 图片内嵌的位置信息只存在于 markdown 里
-            "图 + 正文": (self._topic(markdown_content=img_md, text_content="正文", photos=[photo]), 1, img_md),
-            "纯图无正文": (self._topic(markdown_content="![](x)", photos=[photo]), 1, "![](x)"),
-            "纯文字": (self._topic(markdown_content="只有文字", text_content="只有文字"), 0, "只有文字"),
-            "纯视频": (self._topic(video=video), 1, ""),
-        }
-        for label, (topic, media_count, expected_md) in cases.items():
-            with self.subTest(case=label):
-                result = await self._parse(topic)
-                self.assertIsInstance(result, DoubanRichTextParseResult)
-                self.assertEqual(len(result.media or []), media_count)
-                self.assertEqual(result.markdown_content, expected_md)
-
-    async def test_video_with_photos_keeps_video_first(self):
-        result = await self._parse(
-            self._topic(
-                text_content="说明",
-                markdown_content="说明",
-                video=DoubanVideo(url="https://sv1.doubanio.com/a.mp4", duration=39),
-                photos=[DoubanPhoto(url="https://img3.doubanio.com/p1.jpg", width=500, height=482)],
-            )
-        )
-
-        self.assertIsInstance(result, DoubanRichTextParseResult)
-        self.assertEqual(
-            result.media,
-            [
-                VideoRef(url="https://sv1.doubanio.com/a.mp4", duration=39),
-                ImageRef(url="https://img3.doubanio.com/p1.jpg", width=500, height=482),
-            ],
-        )
-
-    async def test_animated_photo_becomes_ani_ref(self):
-        result = await self._parse(
-            self._topic(
-                photos=[
-                    DoubanPhoto(
-                        url="https://img3.doubanio.com/p2.mp4",
-                        ext="mp4",
-                        thumb_url="https://img3.doubanio.com/p2.jpg",
-                        width=500,
-                        height=291,
-                        is_animated=True,
-                    )
-                ]
-            )
-        )
-
-        self.assertEqual(
-            result.media,
-            [
-                AniRef(
-                    url="https://img3.doubanio.com/p2.mp4",
-                    ext="mp4",
-                    thumb_url="https://img3.doubanio.com/p2.jpg",
-                    width=500,
-                    height=291,
-                )
-            ],
-        )
-
-    async def test_provider_error_is_wrapped_in_parse_error(self):
-        with patch.object(Douban, "parse", new=AsyncMock(side_effect=DoubanError("这篇内容不存在了"))):
-            with self.assertRaisesRegex(ParseError, "豆瓣解析失败: 这篇内容不存在了"):
-                await DoubanParser()._do_parse("https://www.douban.com/group/topic/1/")
-
-    async def test_download_injects_douban_referer(self):
-        result = DoubanRichTextParseResult(title="标题", media=[ImageRef(url="https://img3.doubanio.com/p1.jpg")])
-
-        with patch.object(ParseResult, "_do_download", new=AsyncMock()) as mocked:
-            await result._do_download(output_dir=Path("/tmp/does-not-matter"))
-
-        # 豆瓣图床无 Referer 时返回 418
-        self.assertEqual(mocked.await_args.kwargs["headers"]["Referer"], IMAGE_REFERER)
-
-
 class TestPlatformUrlMatching(unittest.TestCase):
     def test_supported_platform_url_formats(self):
         parsehub = ParseHub()