parsehub 2.3.13__tar.gz → 2.3.15__tar.gz

{parsehub-2.3.13/src/parsehub.egg-info → parsehub-2.3.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.3.13
+Version: 2.3.15
 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
@@ -22,7 +22,7 @@ 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]>=2026.10.10.233141.dev0
+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

{parsehub-2.3.13 → parsehub-2.3.15}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.3.13"
+version = "2.3.15"
 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"
@@ -25,7 +25,7 @@ dependencies = [
     "python-dotenv>=1.0.1",
     "tenacity>=8.5.0",
     "urlextract>=1.9.0",
-    "yt-dlp[default]>=2026.10.10.233141.dev0",
+    "yt-dlp[default]>=2026.10.26.220202.dev0",
     "lxml>=5.3.0",
     "pydantic>=1.10.19",
     "markdownify>=1.1.0",

{parsehub-2.3.13 → parsehub-2.3.15}/src/parsehub/parsers/parser/bilibili.py

@@ -112,17 +112,16 @@ class BiliParse(BaseParser):
             p = int(parse_qs(urlparse(url).query).get("p", ["1"])[0])
             view = data["View"]
 
-            cid = view["cid"]
-            duration = view["duration"]
-            dimension = view["dimension"]
+            pages = view.get("pages") or []
+            page_info = next((i for i in pages if i["page"] == p), None)
+            if page_info is None and pages:
+                page_info = pages[0]  # p 越界时回退默认P
+
+            cid = page_info["cid"] if page_info else view["cid"]
+            duration = page_info["duration"] if page_info else view["duration"]
+            dimension = page_info["dimension"] if page_info else view["dimension"]
             desc = view["desc"]
 
-            if p != 1 and (pages := view.get("pages")):
-                if page_info := next((i for i in pages if i["page"] == p), None):
-                    cid = page_info["cid"]
-                    duration = page_info["duration"]
-                    dimension = page_info["dimension"]
-
             b3, b4 = await bili.get_buvid()
             video_playurl = await bili.get_video_playurl(url, cid, b3, b4)
 

{parsehub-2.3.13 → parsehub-2.3.15}/src/parsehub/parsers/parser/xhs.py

@@ -1,8 +1,6 @@
 import re
 from typing import Union
 
-import httpx
-
 from ...provider_api.xhs import MOBILE_HEADERS, PC_HEADERS, XHSAPI, XHSMedia, XHSMediaType, XHSPost, XHSPostType
 from ...types import (
     ContentUnavailableError,
@@ -81,12 +79,8 @@ class XHSParser(BaseParser):
                             LivePhotoRef(url=i.thumb_url or "", video_url=i.url, width=i.width, height=i.height)
                         )
                     else:
-                        # 小红书图片格式: "png" | "webp" | "jpeg" | "heic" | "avif"
-                        ext = await self.get_ext_by_url(i.url)
-                        if ext not in ["png", "webp", "jpeg", "heic", "avif"]:
-                            ext = "jpeg"
                         photos.append(
-                            ImageRef(url=i.url, ext=ext, thumb_url=i.thumb_url, width=i.width, height=i.height)
+                            ImageRef(url=i.url, ext="jpg", thumb_url=i.thumb_url, width=i.width, height=i.height)
                         )
 
                 return ImageParseResult(
@@ -97,21 +91,6 @@ class XHSParser(BaseParser):
             case _:
                 raise ParseError("不支持的类型")
 
-    async def get_ext_by_url(self, url: str) -> str:
-        async with httpx.AsyncClient(proxy=self.proxy) as client:
-            try:
-                response = await client.head(url, follow_redirects=True)
-            except Exception:
-                return ""
-
-            if content_type := response.headers.get("content-type"):
-                media_type = content_type.split(";")[0].strip()
-                if "/" in media_type:
-                    extension = media_type.split("/")[-1]
-                    return str(extension)
-
-            return ""
-
     @staticmethod
     def hashtag_handler(desc: str | None) -> str:
         if not desc:

{parsehub-2.3.13 → parsehub-2.3.15}/src/parsehub/parsers/parser/zuiyou.py

@@ -6,7 +6,8 @@ from ..base.base import BaseParser
 class ZuiYouParser(BaseParser):
     __platform__ = Platform.ZUIYOU
     __supported_type__ = ["视频", "图文"]
-    __match__ = r"^(http(s)?://)share.xiaochuankeji.cn/hybrid/share/post\?pid=\d+"
+    __match__ = r"^(http(s)?://)(share.xiaochuankeji.cn/hybrid/share/post\?pid=\d+|s.izuiyou.com/s/\w+)"
+    __redirect_keywords__ = ["s.izuiyou.com/s/"]
     __reserved_parameters__ = ["pid"]
 
     async def _do_parse(self, raw_url: str) -> MultimediaParseResult:

{parsehub-2.3.13 → parsehub-2.3.15}/src/parsehub/provider_api/xhs.py

@@ -8,6 +8,7 @@ import re
 from dataclasses import dataclass
 from enum import Enum
 from typing import Any, cast
+from urllib.parse import urlsplit
 
 import httpx
 from bs4 import BeautifulSoup
@@ -87,6 +88,7 @@ class XHSAPI:
         script = scripts[0].text
         json_data = script.replace("window.__INITIAL_STATE__=", "")
         json_data = re.sub(r"\bundefined\b", "null", json_data)  # 清理js对象
+        json_data = re.sub(r"new Set\((\[[^\]]*\])\)", r"\1", json_data)
         data = json.loads(json_data)
         return cast(dict[str, Any], data)
 
@@ -192,18 +194,13 @@ class XHSAPI:
 
     @staticmethod
     def get_trace_id(img_url: str) -> str:
-        match = re.search(r"/[a-f0-9]{32}/(.*)/([^/!]+)(?:!.*)?", img_url)
-        if match:
-            return f"{match.group(1)}/{match.group(2)}"
-
-        match = re.search(r"/([^/!]+)(?:!.*)?$", img_url)
-        if match:
-            return match.group(1)
-        return img_url
+        path = urlsplit(img_url).path.split("!", 1)[0]
+        match = re.search(r"/[a-f0-9]{32}/(.+)", path)
+        return match.group(1) if match else path.lstrip("/")
 
     def get_raw_image_url(self, ime_url: str) -> str:
         """拼接无水印图片链接"""
-        return f"http://sns-img-hw.xhscdn.com/{self.get_trace_id(ime_url)}"
+        return f"https://sns-img-hw.xhscdn.com/{self.get_trace_id(ime_url)}?imageView2/format/jpg"
 
 
 class XHSMediaType(Enum):

{parsehub-2.3.13 → parsehub-2.3.15/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.3.13
+Version: 2.3.15
 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
@@ -22,7 +22,7 @@ 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]>=2026.10.10.233141.dev0
+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

{parsehub-2.3.13 → parsehub-2.3.15}/src/parsehub.egg-info/SOURCES.txt

@@ -76,6 +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_offline.py
 test/test_cli.py
 test/test_cli_config.py
 test/test_core_offline.py

{parsehub-2.3.13 → parsehub-2.3.15}/src/parsehub.egg-info/requires.txt

@@ -5,7 +5,7 @@ pydub>=0.25.1
 python-dotenv>=1.0.1
 tenacity>=8.5.0
 urlextract>=1.9.0
-yt-dlp[default]>=2026.10.10.233141.dev0
+yt-dlp[default]>=2026.10.26.220202.dev0
 lxml>=5.3.0
 pydantic>=1.10.19
 markdownify>=1.1.0

parsehub-2.3.15/test/test_bilibili_offline.py

@@ -0,0 +1,63 @@
+import unittest
+from unittest.mock import patch
+
+from parsehub.parsers.parser.bilibili import BiliParse
+
+VIEW = {
+    "cid": 111,
+    "duration": 769,
+    "dimension": {"width": 1920, "height": 1080},
+    "desc": "",
+    "title": "test",
+    "pic": "https://cdn.example/cover.jpg",
+    "pages": [
+        {"page": 1, "cid": 111, "duration": 190, "dimension": {"width": 1920, "height": 1080}},
+        {"page": 2, "cid": 222, "duration": 193, "dimension": {"width": 1920, "height": 1080}},
+    ],
+}
+
+
+class FakeBiliAPI:
+    last_cid = None
+
+    def __init__(self, proxy=None):
+        self.proxy = proxy
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, *args):
+        return None
+
+    async def get_video_info(self, url):
+        return {"data": {"View": VIEW}}
+
+    async def get_buvid(self):
+        return "b3", "b4"
+
+    async def get_video_playurl(self, url, cid, b3, b4):
+        FakeBiliAPI.last_cid = cid
+        return {"data": {"durl": [{"url": "https://cdn.example/video.mp4"}]}}
+
+
+class TestBilibiliParts(unittest.IsolatedAsyncioTestCase):
+    async def test_default_part_uses_first_page_duration(self):
+        with patch("parsehub.parsers.parser.bilibili.BiliAPI", FakeBiliAPI):
+            result = await BiliParse().bili_api_parse("https://www.bilibili.com/video/BV1zLap6VEz1/")
+
+        self.assertEqual(result.media.duration, 190)
+        self.assertEqual(FakeBiliAPI.last_cid, 111)
+
+    async def test_requested_part_uses_page_duration(self):
+        with patch("parsehub.parsers.parser.bilibili.BiliAPI", FakeBiliAPI):
+            result = await BiliParse().bili_api_parse("https://www.bilibili.com/video/BV1zLap6VEz1/?p=2")
+
+        self.assertEqual(result.media.duration, 193)
+        self.assertEqual(FakeBiliAPI.last_cid, 222)
+
+    async def test_out_of_range_falls_back_to_default_part(self):
+        with patch("parsehub.parsers.parser.bilibili.BiliAPI", FakeBiliAPI):
+            result = await BiliParse().bili_api_parse("https://www.bilibili.com/video/BV1zLap6VEz1/?p=99")
+
+        self.assertEqual(result.media.duration, 190)
+        self.assertEqual(FakeBiliAPI.last_cid, 111)

{parsehub-2.3.13 → parsehub-2.3.15}/test/test_core_offline.py

@@ -640,8 +640,7 @@ class TestPlatformUrlMatching(unittest.TestCase):
             ],
             Platform.XIAOHEIHE: [
                 "https://www.xiaoheihe.cn/app/bbs/link/174972336",
-                "https://www.xiaoheihe.cn/v3/bbs/app/api/web/share?link_id=174972336",
-                "https://api.xiaoheihe.cn/v3/bbs/app/link?link_id=174972336",
+                "https://api.xiaoheihe.cn/v3/bbs/app/api/web/share?h_camp=link&h_src=YXBwX3NoYXJl&link_id=57b172affdbc",
             ],
             Platform.YOUTUBE: [
                 "https://www.youtube.com/watch?v=1h_uc3K4Cpg",