parsehub 2.2.0__tar.gz → 2.2.2__tar.gz

{parsehub-2.2.0/src/parsehub.egg-info → parsehub-2.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.2.0
+Version: 2.2.2
 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
@@ -27,8 +27,9 @@ 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>=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
@@ -72,28 +73,28 @@ Dynamic: license-file
 
 ## 🌐 支持平台
 
-| 平台            | 视频 | 图文 | 其他                |
-|-----------------|:----:|:----:|---------------------|
-| **Twitter / X** |  ✅  |  ✅  | 📝 文章             |
-| **Instagram**   |  ✅  |  ✅  |                     |
-| **YouTube**     |  ✅  |      | 🎵 音乐             |
-| **Facebook**    |  ✅  |      |                     |
-| **Threads**     |  ✅  |  ✅  |                     |
-| **Bilibili**    |  ✅  |      | 📝 动态             |
-| **抖音**        |  ✅  |  ✅  | ☀️日常              |
-| **TikTok**      |  ✅  |  ✅  |                     |
-| **微博**        |  ✅  |  ✅  |                     |
-| **小红书**      |  ✅  |  ✅  |                     |
-| **贴吧**        |  ✅  |  ✅  |                     |
-| **微信公众号**  |      |  ✅  |                     |
-| **快手**        |  ✅  |  ✅  |                     |
-| **酷安**        |      |  ✅  |                     |
-| **皮皮虾**      |  ✅  |  ✅  |                     |
-| **最右**        |  ✅  |  ✅  |                     |
-| **小黑盒**      |  ✅  |  ✅  |                     |
-| **Snapchat**    |  ✅  |      |                     |
-| **知乎**        |  ✅  |  ✅  | 🐶 问答, 专栏, 圈子 |
-| **豆瓣**        |  ✅  |  ✅  | 👥 小组话题         |
+| 平台            | 视频 | 图文 | 其他                      |
+|-----------------|:----:|:----:|---------------------------|
+| **Twitter / X** |  ✅  |  ✅  | 📝 文章                   |
+| **Instagram**   |  ✅  |  ✅  |                           |
+| **YouTube**     |  ✅  |      | 🎵 音乐                   |
+| **Facebook**    |  ✅  |      |                           |
+| **Threads**     |  ✅  |  ✅  |                           |
+| **Bilibili**    |  ✅  |      | 📝 动态                   |
+| **抖音**        |  ✅  |  ✅  | ☀️日常                    |
+| **TikTok**      |  ✅  |  ✅  |                           |
+| **微博**        |  ✅  |  ✅  |                           |
+| **小红书**      |  ✅  |  ✅  |                           |
+| **贴吧**        |  ✅  |  ✅  |                           |
+| **微信公众号**  |      |  ✅  |                           |
+| **快手**        |  ✅  |  ✅  |                           |
+| **酷安**        |      |  ✅  |                           |
+| **皮皮虾**      |  ✅  |  ✅  |                           |
+| **最右**        |  ✅  |  ✅  |                           |
+| **小黑盒**      |  ✅  |  ✅  |                           |
+| **Snapchat**    |  ✅  |      |                           |
+| **知乎**        |  ✅  |  ✅  | 🐶 问答, 专栏, 圈子, 日报 |
+| **豆瓣**        |  ✅  |  ✅  | 👥 小组话题               |
 
 ## 📦 安装
 

{parsehub-2.2.0 → parsehub-2.2.2}/README.md

@@ -30,28 +30,28 @@
 
 ## 🌐 支持平台
 
-| 平台            | 视频 | 图文 | 其他                |
-|-----------------|:----:|:----:|---------------------|
-| **Twitter / X** |  ✅  |  ✅  | 📝 文章             |
-| **Instagram**   |  ✅  |  ✅  |                     |
-| **YouTube**     |  ✅  |      | 🎵 音乐             |
-| **Facebook**    |  ✅  |      |                     |
-| **Threads**     |  ✅  |  ✅  |                     |
-| **Bilibili**    |  ✅  |      | 📝 动态             |
-| **抖音**        |  ✅  |  ✅  | ☀️日常              |
-| **TikTok**      |  ✅  |  ✅  |                     |
-| **微博**        |  ✅  |  ✅  |                     |
-| **小红书**      |  ✅  |  ✅  |                     |
-| **贴吧**        |  ✅  |  ✅  |                     |
-| **微信公众号**  |      |  ✅  |                     |
-| **快手**        |  ✅  |  ✅  |                     |
-| **酷安**        |      |  ✅  |                     |
-| **皮皮虾**      |  ✅  |  ✅  |                     |
-| **最右**        |  ✅  |  ✅  |                     |
-| **小黑盒**      |  ✅  |  ✅  |                     |
-| **Snapchat**    |  ✅  |      |                     |
-| **知乎**        |  ✅  |  ✅  | 🐶 问答, 专栏, 圈子 |
-| **豆瓣**        |  ✅  |  ✅  | 👥 小组话题         |
+| 平台            | 视频 | 图文 | 其他                      |
+|-----------------|:----:|:----:|---------------------------|
+| **Twitter / X** |  ✅  |  ✅  | 📝 文章                   |
+| **Instagram**   |  ✅  |  ✅  |                           |
+| **YouTube**     |  ✅  |      | 🎵 音乐                   |
+| **Facebook**    |  ✅  |      |                           |
+| **Threads**     |  ✅  |  ✅  |                           |
+| **Bilibili**    |  ✅  |      | 📝 动态                   |
+| **抖音**        |  ✅  |  ✅  | ☀️日常                    |
+| **TikTok**      |  ✅  |  ✅  |                           |
+| **微博**        |  ✅  |  ✅  |                           |
+| **小红书**      |  ✅  |  ✅  |                           |
+| **贴吧**        |  ✅  |  ✅  |                           |
+| **微信公众号**  |      |  ✅  |                           |
+| **快手**        |  ✅  |  ✅  |                           |
+| **酷安**        |      |  ✅  |                           |
+| **皮皮虾**      |  ✅  |  ✅  |                           |
+| **最右**        |  ✅  |  ✅  |                           |
+| **小黑盒**      |  ✅  |  ✅  |                           |
+| **Snapchat**    |  ✅  |      |                           |
+| **知乎**        |  ✅  |  ✅  | 🐶 问答, 专栏, 圈子, 日报 |
+| **豆瓣**        |  ✅  |  ✅  | 👥 小组话题               |
 
 ## 📦 安装
 

{parsehub-2.2.0 → parsehub-2.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.2.0"
+version = "2.2.2"
 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"
@@ -30,8 +30,9 @@ dependencies = [
     "pydantic>=1.10.19",
     "markdownify>=1.1.0",
     "markdown>=3.7",
+    "json5>=0.12",
     "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-2.2.2}/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-2.2.2/src/parsehub/parsers/parser/weixin.py

@@ -0,0 +1,40 @@
+from ...provider_api.weixin import WX, WXItemShowType
+from ...types import AnyParseResult, ImageParseResult, ImageRef, ParseError, Platform, RichTextParseResult
+from ..base.base import BaseParser
+
+
+class WXParser(BaseParser):
+    __platform__ = Platform.WEIXIN
+    __supported_type__ = ["图文"]
+    __match__ = r"^(http(s)?://)mp.weixin.qq.com/s/.*"
+
+    @staticmethod
+    def _refs(urls: list[str]) -> list[ImageRef]:
+        """图片地址带 wx_fmt 参数标明实际格式, 缺失时才用默认的 jpg."""
+        refs = []
+        for url in urls:
+            fmt = url.partition("wx_fmt=")[2].partition("&")[0]
+            refs.append(ImageRef(url=url, ext=fmt or "jpg"))
+        return refs
+
+    async def _do_parse(self, raw_url: str) -> AnyParseResult:
+        wx = await WX.parse(raw_url, self.proxy)
+
+        match wx.item_show_type:
+            case WXItemShowType.ARTICLE:
+                return RichTextParseResult(
+                    title=wx.title,
+                    media=self._refs(wx.imgs),
+                    markdown_content=wx.markdown_content,
+                )
+            case WXItemShowType.IMAGE | WXItemShowType.TEXT:
+                return ImageParseResult(
+                    title=wx.title,
+                    photo=self._refs(wx.photos),
+                    content=wx.text_content,
+                )
+            case _:
+                raise ParseError(f"不支持的内容类型: {wx.item_show_type!r}")
+
+
+__all__ = ["WXParser"]

{parsehub-2.2.0 → parsehub-2.2.2}/src/parsehub/parsers/parser/zhihu.py

@@ -13,8 +13,8 @@ from ..base.base import BaseParser
 
 class ZhihuParser(BaseParser):
     __platform__ = Platform.ZHIHU
-    __supported_type__ = ["问答", "专栏", "圈子"]
-    __match__ = r"^(http(s)?://)?(www|zhuanlan).zhihu.com/(pin|question|p)/.*"
+    __supported_type__ = ["问答", "专栏", "圈子", "日报"]
+    __match__ = r"^(http(s)?://)?(www|zhuanlan|daily).zhihu.com/(pin|question|p|story)/.*"
 
     async def _do_parse(
         self, raw_url: str

{parsehub-2.2.0 → parsehub-2.2.2}/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-2.2.2}/src/parsehub/provider_api/weibo.py

@@ -206,6 +206,7 @@ class PageInfo(Info):
 @dataclass
 class Pic:
     url: str | None = None
+    hdr_url: str | None = None
     width: int | None = None
     height: int | None = None
     cut_type: int | None = None

parsehub-2.2.2/src/parsehub/provider_api/weixin.py

@@ -0,0 +1,153 @@
+import re
+from dataclasses import dataclass
+from enum import IntEnum
+from html import unescape
+from typing import Any, cast
+
+import httpx
+import json5
+from bs4 import BeautifulSoup
+from markdownify import MarkdownConverter
+
+from ..errors import ParseError
+from ..utils.helpers import UA
+
+
+class WXItemShowType(IntEnum):
+    """页面数据里的 ``item_show_type``, 决定正文与媒体的取值位置."""
+
+    ARTICLE = 0
+    """公众号文章"""
+    IMAGE = 8
+    """图文"""
+    TEXT = 10
+    """纯文本"""
+
+
+_TAG_RE = re.compile(r"</?[a-zA-Z][^>]*>")
+_BREAK_RE = re.compile(r"<br\s*/?>", re.IGNORECASE)
+_IMG_SRC_RE = re.compile(r"<img[^>]*?\bdata-src\s*=\s*[\"']([^\"']+)[\"']", re.IGNORECASE)
+#: 页面数据用 '0' * 1 这类写法做隐式类型转换, 不是合法的 JSON5 值
+_IMPLICIT_INT_RE = re.compile(r"('[^'\n]*'|\"[^\"\n]*\")\s*\*\s*1(?![.\d])")
+#: 对象以 "};" 结束后还跟着 try/catch 与 IIFE 收尾
+_OBJECT_END_RE = re.compile(r"}\s*;.*$", re.DOTALL)
+
+_PAYLOAD_NAME = "cgiDataNew"
+
+
+def _load_payload(html: str) -> dict[str, Any]:
+    """解析 ``window.cgiDataNew`` 为字典.
+
+    数据在 script 标签里, 是 JS 对象字面量 (键无引号、单引号字符串、尾随逗号),
+    用 json5 解析, 只需去掉两处 JS 语法.
+    """
+    scripts = [s.text for s in BeautifulSoup(html, "lxml").find_all("script") if _PAYLOAD_NAME in s.text]
+    if not scripts:
+        raise ParseError(f"未找到 {_PAYLOAD_NAME} 数据")
+
+    text = scripts[0].split(_PAYLOAD_NAME, 1)[1]
+    text = _IMPLICIT_INT_RE.sub(r"\1", text)
+    text = text[text.index("{") :]
+    return cast(dict[str, Any], json5.loads(_OBJECT_END_RE.sub("}", text, count=1)))
+
+
+def _to_text(source: Any) -> str:
+    """正文片段转纯文本, 兼容本身就是纯文本的情况."""
+    if not isinstance(source, str) or not source:
+        return ""
+    return unescape(_TAG_RE.sub("", _BREAK_RE.sub("\n", unescape(source)))).strip()
+
+
+def _collect_photos(data: dict[str, Any]) -> list[str]:
+    """图片消息的图片地址, 取原始图 ``watermark_info.cdn_url``, 缺失时退回 ``cdn_url``."""
+    entries = data.get("picture_page_info_list") or []
+    return [
+        url
+        for e in entries
+        if isinstance(e, dict)
+        for url in [(e.get("watermark_info") or {}).get("cdn_url") or e.get("cdn_url")]
+        if url
+    ]
+
+
+class WXConverter(MarkdownConverter):
+    """把正文 HTML 转为 markdown, 图片地址取自 ``data-src``."""
+
+    def convert_img(self, el: Any, text: Any, parent_tags: Any) -> str:
+        alt = el.attrs.get("alt", None) or ""
+        src = el.attrs.get("data-src", None) or el.attrs.get("src", None) or ""
+        title = el.attrs.get("title", None) or ""
+        title_part = ' "{}"'.format(title.replace('"', r"\"")) if title else ""
+        options = cast(dict[str, Any], getattr(self, "options"))  # noqa: B009
+        if "_inline" in parent_tags and el.parent.name not in options["keep_inline_images_in"]:
+            return alt
+
+        return f"![{alt}]({src}{title_part})"
+
+
+@dataclass
+class WX:
+    """微信文章的解析结果.
+
+    Attributes:
+        item_show_type: 内容形态
+        title: 标题
+        markdown_content: markdown 正文, 仅图文形态有值
+        imgs: 正文内的图片地址
+        text_content: 纯文本正文
+        photos: 图片消息的图片地址, 仅图片形态有值
+    """
+
+    item_show_type: WXItemShowType
+    title: str
+    markdown_content: str
+    imgs: list[str]
+    text_content: str
+    photos: list[str]
+
+    @staticmethod
+    async def parse(url: str, proxy: str | None = None) -> "WX":
+        async with httpx.AsyncClient(proxy=proxy) as client:
+            response = await client.get(url, headers={"User-Agent": UA})
+        return WX._parse_data(response.text)
+
+    @classmethod
+    def _parse_data(cls, html: str) -> "WX":
+        data = _load_payload(html)
+        try:
+            item_show_type = WXItemShowType(int(data["item_show_type"]))
+        except (KeyError, TypeError, ValueError) as e:
+            raise ParseError(f"不支持的内容类型: {data.get('item_show_type')!r}") from e
+
+        match item_show_type:
+            case WXItemShowType.ARTICLE:
+                source = data.get("content_noencode") or ""
+                return cls(
+                    item_show_type=item_show_type,
+                    title=data.get("title") or "",
+                    markdown_content=WXConverter(heading_style="ATX").convert(source),
+                    imgs=_IMG_SRC_RE.findall(source),
+                    text_content=_to_text(source),
+                    photos=[],
+                )
+            case WXItemShowType.TEXT:
+                return cls(
+                    item_show_type=item_show_type,
+                    title="",
+                    markdown_content="",
+                    imgs=[],
+                    text_content=_to_text((data.get("text_page_info") or {}).get("content_noencode")),
+                    photos=[],
+                )
+            case WXItemShowType.IMAGE:
+                return cls(
+                    item_show_type=item_show_type,
+                    title=data.get("title") or "",
+                    markdown_content="",
+                    imgs=[],
+                    text_content=_to_text(data.get("content_noencode")),
+                    photos=_collect_photos(data),
+                )
+
+
+__all__ = ["WX", "WXConverter", "WXItemShowType"]

{parsehub-2.2.0 → parsehub-2.2.2}/src/parsehub/provider_api/xhs.py

@@ -10,6 +10,10 @@ from typing import Any, cast
 import httpx
 from bs4 import BeautifulSoup
 
+from parsehub.utils.helpers import UA
+
+from ..errors import ParseError
+
 
 class XHSAPI:
     def __init__(self, proxy: str | None = None, cookie: dict | None = None):
@@ -17,8 +21,17 @@ 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,
+                headers={"User-Agent": UA},
+                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 +40,7 @@ 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 +49,11 @@ 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 +92,7 @@ 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-2.2.2}/src/parsehub/provider_api/zhihu.py

@@ -208,8 +208,24 @@ class ZhihuAPI:
             return await self.parse_zl(raw_url)
         if "/pin/" in raw_url:
             return await self.parse_pin(raw_url)
+        if "daily.zhihu.com" in raw_url or "/story/" in raw_url:
+            return await self.parse_daily(raw_url)
         raise ValueError("不支持的类型")
 
+    async def parse_daily(self, raw_url: str) -> ZhihuQA | ZhihuZhuanLan | ZhihuPin:
+        story_id = self._get_daily_id(raw_url)
+        result = await self._daily(story_id)
+        body = result.get("body", "")
+        soup = BeautifulSoup(body, "lxml")
+        origin_url: str | None = None
+        for a in soup.find_all("a"):
+            if "查看知乎原文" in a.get_text():
+                origin_url = str(a.get("href"))
+                break
+        if not origin_url:
+            raise ValueError("未在知乎日报中找到原文链接")
+        return await self.parse(origin_url)
+
     async def parse_qa(self, raw_url: str) -> ZhihuQA:
         qid, aid = self._get_qa_id(raw_url)
         if aid:
@@ -293,6 +309,12 @@ class ZhihuAPI:
             r = await client.get(url, headers=headers, params=query, cookies=self.cookie)
             return dict(r.json())
 
+    async def _daily(self, story_id: int | str) -> dict:
+        url = f"https://daily.zhihu.com/api/7/story/{story_id}"
+        async with httpx.AsyncClient(proxy=self.proxy) as client:
+            r = await client.get(url)
+            return dict(r.json())
+
     @staticmethod
     def _get_qa_id(raw_url: str) -> tuple[str, str | None]:
         """返回问题和回答 id,  没有回答 id 时返回 None"""
@@ -315,6 +337,13 @@ class ZhihuAPI:
             raise ValueError("从链接中提取 圈子 id 错误")
         return r.group(1)
 
+    @staticmethod
+    def _get_daily_id(raw_url: str) -> str:
+        r = re.search(r"/story/(\d+)", raw_url)
+        if not r:
+            raise ValueError("从链接中提取 日报 id 错误")
+        return r.group(1)
+
 
 # --- SM4 constants (extracted from other.js VM) ---------------------------------
 SM4_ZB = [

{parsehub-2.2.0 → parsehub-2.2.2/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.2.0
+Version: 2.2.2
 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
@@ -27,8 +27,9 @@ 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>=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
@@ -72,28 +73,28 @@ Dynamic: license-file
 
 ## 🌐 支持平台
 
-| 平台            | 视频 | 图文 | 其他                |
-|-----------------|:----:|:----:|---------------------|
-| **Twitter / X** |  ✅  |  ✅  | 📝 文章             |
-| **Instagram**   |  ✅  |  ✅  |                     |
-| **YouTube**     |  ✅  |      | 🎵 音乐             |
-| **Facebook**    |  ✅  |      |                     |
-| **Threads**     |  ✅  |  ✅  |                     |
-| **Bilibili**    |  ✅  |      | 📝 动态             |
-| **抖音**        |  ✅  |  ✅  | ☀️日常              |
-| **TikTok**      |  ✅  |  ✅  |                     |
-| **微博**        |  ✅  |  ✅  |                     |
-| **小红书**      |  ✅  |  ✅  |                     |
-| **贴吧**        |  ✅  |  ✅  |                     |
-| **微信公众号**  |      |  ✅  |                     |
-| **快手**        |  ✅  |  ✅  |                     |
-| **酷安**        |      |  ✅  |                     |
-| **皮皮虾**      |  ✅  |  ✅  |                     |
-| **最右**        |  ✅  |  ✅  |                     |
-| **小黑盒**      |  ✅  |  ✅  |                     |
-| **Snapchat**    |  ✅  |      |                     |
-| **知乎**        |  ✅  |  ✅  | 🐶 问答, 专栏, 圈子 |
-| **豆瓣**        |  ✅  |  ✅  | 👥 小组话题         |
+| 平台            | 视频 | 图文 | 其他                      |
+|-----------------|:----:|:----:|---------------------------|
+| **Twitter / X** |  ✅  |  ✅  | 📝 文章                   |
+| **Instagram**   |  ✅  |  ✅  |                           |
+| **YouTube**     |  ✅  |      | 🎵 音乐                   |
+| **Facebook**    |  ✅  |      |                           |
+| **Threads**     |  ✅  |  ✅  |                           |
+| **Bilibili**    |  ✅  |      | 📝 动态                   |
+| **抖音**        |  ✅  |  ✅  | ☀️日常                    |
+| **TikTok**      |  ✅  |  ✅  |                           |
+| **微博**        |  ✅  |  ✅  |                           |
+| **小红书**      |  ✅  |  ✅  |                           |
+| **贴吧**        |  ✅  |  ✅  |                           |
+| **微信公众号**  |      |  ✅  |                           |
+| **快手**        |  ✅  |  ✅  |                           |
+| **酷安**        |      |  ✅  |                           |
+| **皮皮虾**      |  ✅  |  ✅  |                           |
+| **最右**        |  ✅  |  ✅  |                           |
+| **小黑盒**      |  ✅  |  ✅  |                           |
+| **Snapchat**    |  ✅  |      |                           |
+| **知乎**        |  ✅  |  ✅  | 🐶 问答, 专栏, 圈子, 日报 |
+| **豆瓣**        |  ✅  |  ✅  | 👥 小组话题               |
 
 ## 📦 安装
 

{parsehub-2.2.0 → parsehub-2.2.2}/src/parsehub.egg-info/requires.txt

@@ -10,8 +10,9 @@ lxml>=5.3.0
 pydantic>=1.10.19
 markdownify>=1.1.0
 markdown>=3.7
+json5>=0.12
 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-2.2.2}/test/test_core_offline.py

@@ -447,6 +447,7 @@ class TestDoubanParserResultTypes(unittest.IsolatedAsyncioTestCase):
             "title": "标题",
             "markdown_content": "",
             "text_content": "",
+            "image_layout": "vertical",  # 默认图文混排, 走 RichText 分支
             "video": None,
             "photos": [],
         }

parsehub-2.2.0/src/parsehub/parsers/parser/weixin.py

@@ -1,20 +0,0 @@
-from ...provider_api.weixin import WX
-from ...types import ImageRef, Platform, RichTextParseResult
-from ..base.base import BaseParser
-
-
-class WXParser(BaseParser):
-    __platform__ = Platform.WEIXIN
-    __supported_type__ = ["图文"]
-    __match__ = r"^(http(s)?://)mp.weixin.qq.com/s/.*"
-
-    async def _do_parse(self, raw_url: str) -> "RichTextParseResult":
-        wx = await WX.parse(raw_url, self.proxy)
-        return RichTextParseResult(
-            title=wx.title,
-            media=[ImageRef(url=i) for i in wx.imgs],
-            markdown_content=wx.markdown_content,
-        )
-
-
-__all__ = ["WXParser"]

parsehub-2.2.0/src/parsehub/provider_api/weixin.py

@@ -1,62 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, cast
-
-import httpx
-from bs4 import BeautifulSoup, Tag
-from markdown import markdown
-from markdownify import MarkdownConverter
-
-from ..types import ParseError
-from ..utils.helpers import UA
-
-
-class WXConverter(MarkdownConverter):
-    def convert_img(self, el: Any, text: Any, parent_tags: Any) -> str:
-        alt = el.attrs.get("alt", None) or ""
-        src = el.attrs.get("data-src", None) or ""
-        title = el.attrs.get("title", None) or ""
-        title_part = ' "{}"'.format(title.replace('"', r"\"")) if title else ""
-        options = cast(dict[str, Any], getattr(self, "options"))  # noqa: B009
-        if "_inline" in parent_tags and el.parent.name not in options["keep_inline_images_in"]:
-            return alt
-
-        return f"![{alt}]({src}{title_part})"
-
-
-@dataclass
-class WX:
-    title: str
-    imgs: list[str]
-    markdown_content: str
-    text_content: str
-
-    @staticmethod
-    async def parse(url: str, proxy: str | None = None) -> "WX":
-        async with httpx.AsyncClient(proxy=proxy) as client:
-            response = await client.get(url, headers={"User-Agent": UA})
-            html = response.text
-            return WX._parse_html(html)
-
-    @classmethod
-    def _parse_html(cls, html: str) -> "WX":
-        soup = BeautifulSoup(html, "lxml")
-        title_tag = soup.find("h1", {"class": "rich_media_title"})
-        title = title_tag.text.strip() if isinstance(title_tag, Tag) else ""
-        wxc = WXConverter(heading_style="ATX")
-        if isinstance(rich_media_content := soup.find("div", {"class": "rich_media_content"}), Tag):
-            imgs = [str(i.get("data-src") or "") for i in rich_media_content.find_all("img", {"class": "rich_pages"})]
-
-            markdown_content = wxc.convert(str(rich_media_content))
-            text_content = "".join(BeautifulSoup(markdown(markdown_content), "lxml").find_all(string=True))
-            return cls(title, imgs, markdown_content, text_content)
-        elif isinstance(share_content_page := soup.find("div", {"class": "share_content_page"}), Tag):
-            imgs = [str(i.get("data-src") or "") for i in share_content_page.find_all("div", {"class": "swiper_item"})]
-
-            description = soup.find("meta", {"name": "description"})
-            if not isinstance(description, Tag):
-                raise ParseError("获取内容失败")
-            markdown_content = wxc.convert(str(description.get("content") or ""))
-            text_content = "".join(BeautifulSoup(markdown(markdown_content), "lxml").find_all(string=True))
-            return cls(title, imgs, markdown_content, text_content)
-        else:
-            raise ParseError("获取内容失败")