parsehub 2.2.0__tar.gz → 2.2.1__tar.gz

{parsehub-2.2.0/src/parsehub.egg-info → parsehub-2.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.2.0
+Version: 2.2.1
 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
@@ -28,7 +28,7 @@ Requires-Dist: pydantic>=1.10.19
 Requires-Dist: markdownify>=1.1.0
 Requires-Dist: markdown>=3.7
 Requires-Dist: requests
-Requires-Dist: httpx>=0.24.1
+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

{parsehub-2.2.0 → parsehub-2.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.2.0"
+version = "2.2.1"
 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"
@@ -31,7 +31,7 @@ dependencies = [
     "markdownify>=1.1.0",
     "markdown>=3.7",
     "requests",
-    "httpx>=0.24.1",
+    "httpx[socks]>=0.24.1",
     "pillow>=12.1.0",
     "python-slugify[unidecode]>=8.0.4",
     "opencv-python-headless>=4.13.0.92",

{parsehub-2.2.0 → parsehub-2.2.1}/src/parsehub/parsers/parser/douban.py

@@ -1,12 +1,15 @@
 from pathlib import Path
+from typing import Union
 
 from ...provider_api.douban import IMAGE_REFERER, Douban, DoubanError, DoubanPhoto, DoubanVideo
 from ...types import (
     AniRef,
     AnyMediaRef,
     DownloadResult,
+    ImageParseResult,
     ImageRef,
     ParseError,
+    ParseResult,
     Platform,
     ProgressCallback,
     RichTextParseResult,
@@ -22,7 +25,7 @@ class DoubanParser(BaseParser):
     __match__ = r"^(http(s)?://)?(((www|m)\.)?douban\.com/((group/)?topic/\d+|doubanapp/dispatch)|douc\.cc/.+)"
     __redirect_keywords__ = ["douc.cc", "doubanapp/dispatch"]
 
-    async def _do_parse(self, raw_url: str) -> "DoubanRichTextParseResult":
+    async def _do_parse(self, raw_url: str) -> Union["DoubanRichTextParseResult", "DoubanImageParseResult"]:
         try:
             topic = await Douban(proxy=self.proxy, cookie=self.cookie.get_value()).parse(raw_url)
         except DoubanError as e:
@@ -30,11 +33,16 @@ class DoubanParser(BaseParser):
         except Exception as e:
             raise ParseError("豆瓣解析失败: 未知错误") from e
 
+        photos = [self.to_media_ref(p) for p in topic.photos]
+
+        if topic.image_layout == "horizontal":
+            return DoubanImageParseResult(title=topic.title, photo=photos, content=topic.text_content)
+
         # 图片和视频在正文里有位置关系, 交给 RichText 由 markdown 保留顺序
-        media: list[AnyMediaRef] = [
-            *([self.to_video_ref(topic.video)] if topic.video else []),
-            *(self.to_media_ref(p) for p in topic.photos),
-        ]
+        media: list[AnyMediaRef] = []
+        if topic.video:
+            media.append(self.to_video_ref(topic.video))
+        media.extend(photos)
         return DoubanRichTextParseResult(title=topic.title, media=media, markdown_content=topic.markdown_content)
 
     @staticmethod
@@ -59,7 +67,7 @@ class DoubanParser(BaseParser):
         )
 
 
-class DoubanRichTextParseResult(RichTextParseResult):
+class DoubanParseResult(ParseResult):
     async def _do_download(
         self,
         *,
@@ -83,4 +91,10 @@ class DoubanRichTextParseResult(RichTextParseResult):
         )
 
 
+class DoubanImageParseResult(ImageParseResult, DoubanParseResult): ...
+
+
+class DoubanRichTextParseResult(RichTextParseResult, DoubanParseResult): ...
+
+
 __all__ = ["DoubanParser", "DoubanRichTextParseResult"]

{parsehub-2.2.0 → parsehub-2.2.1}/src/parsehub/provider_api/douban.py

@@ -1,6 +1,6 @@
 import re
 from dataclasses import dataclass, field
-from typing import Any, cast
+from typing import Any, Literal, cast
 
 import httpx
 from bs4 import BeautifulSoup
@@ -80,6 +80,7 @@ class DoubanTopic:
     title: str
     markdown_content: str
     text_content: str
+    image_layout: Literal["horizontal", "vertical"]  # vertical 图文混排, horizontal 图集
     video: DoubanVideo | None = None
     photos: list[DoubanPhoto] = field(default_factory=list)
 
@@ -95,7 +96,8 @@ class DoubanTopic:
             markdown_content=markdown_content,
             text_content=text_content,
             video=parse_video(video_info) if video_info else None,
-            photos=[p for photo in data.get("photos") or [] if (p := parse_photo(photo))],
+            photos=[p for photo in data.get("photos", []) if (p := parse_photo(photo))],
+            image_layout=data.get("image_layout", "horizontal"),
         )
 
 

{parsehub-2.2.0 → parsehub-2.2.1}/src/parsehub/provider_api/xhs.py

@@ -10,6 +10,8 @@ from typing import Any, cast
 import httpx
 from bs4 import BeautifulSoup
 
+from ..errors import ParseError
+
 
 class XHSAPI:
     def __init__(self, proxy: str | None = None, cookie: dict | None = None):
@@ -17,8 +19,13 @@ class XHSAPI:
         self.cookie = cookie
 
     async def __fetch_html(self, url: str) -> str:
-        async with httpx.AsyncClient(proxy=self.proxy, cookies=self.cookie) as client:
-            return (await client.get(url, timeout=30)).text
+        async with httpx.AsyncClient(proxy=self.proxy, cookies=self.cookie, follow_redirects=True) as client:
+            result = await client.get(url, timeout=30)
+            if "/login" in str(result.url):
+                raise ParseError("该帖子需要登录后查看")
+            elif "/404" in str(result.url):
+                raise ParseError("帖子不存在")
+            return result.text
 
     @staticmethod
     async def __extract_data(html: str) -> dict[str, Any]:
@@ -27,7 +34,7 @@ class XHSAPI:
             script for script in soup.find_all("script") if script.text.lstrip().startswith("window.__INITIAL_STATE__")
         ]
         if not scripts:
-            raise ValueError("No data found")
+            raise ParseError("No data found")
         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
@@ -36,11 +43,11 @@ class XHSAPI:
 
     def __parse(self, data: dict[str, Any]) -> XHSPost:
         if not data.get("note"):
-            raise ValueError("该帖子需要登录后查看")
+            raise ParseError("该帖子需要登录后查看")
         first_note_id = data["note"]["firstNoteId"]
         note = data["note"]["noteDetailMap"][first_note_id]["note"]
         if not note:
-            raise ValueError("未获取到内容, 该帖子可能需要登录后查看")
+            raise ParseError("未获取到内容, 该帖子可能需要登录后查看")
 
         title = note["title"]
         desc = note["desc"]
@@ -79,7 +86,7 @@ class XHSAPI:
             stream = media["stream"]
             selected_stream = self.__select_stream(stream)
             if not selected_stream:
-                raise ValueError("未获取到视频流")
+                raise ParseError("未获取到视频流")
             stream = selected_stream[0]
             media_list.append(
                 XHSMedia(

{parsehub-2.2.0 → parsehub-2.2.1/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.2.0
+Version: 2.2.1
 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
@@ -28,7 +28,7 @@ Requires-Dist: pydantic>=1.10.19
 Requires-Dist: markdownify>=1.1.0
 Requires-Dist: markdown>=3.7
 Requires-Dist: requests
-Requires-Dist: httpx>=0.24.1
+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

{parsehub-2.2.0 → parsehub-2.2.1}/src/parsehub.egg-info/requires.txt

@@ -11,7 +11,7 @@ pydantic>=1.10.19
 markdownify>=1.1.0
 markdown>=3.7
 requests
-httpx>=0.24.1
+httpx[socks]>=0.24.1
 pillow>=12.1.0
 python-slugify[unidecode]>=8.0.4
 opencv-python-headless>=4.13.0.92