parsehub 2.3.1__tar.gz → 2.3.3__tar.gz

{parsehub-2.3.1/src/parsehub.egg-info → parsehub-2.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.3.1
+Version: 2.3.3
 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
@@ -88,6 +88,7 @@ Dynamic: license-file
 | **小红书**      |  ✅  |  ✅  |                           |
 | **贴吧**        |  ✅  |  ✅  |                           |
 | **微信公众号**  |      |  ✅  |                           |
+| **微信视频号**  |  ✅  |      |                           |
 | **快手**        |  ✅  |  ✅  |                           |
 | **酷安**        |      |  ✅  |                           |
 | **皮皮虾**      |  ✅  |  ✅  |                           |
@@ -222,6 +223,7 @@ print(result)
 - `小红书`
 - `知乎`
 - `豆瓣`
+- `微信视频号`（需要填腾讯元宝 yuanbao.tencent.com 登录后的 Cookie）
 
 ```python
 from parsehub import ParseHub

{parsehub-2.3.1 → parsehub-2.3.3}/README.md

@@ -44,6 +44,7 @@
 | **小红书**      |  ✅  |  ✅  |                           |
 | **贴吧**        |  ✅  |  ✅  |                           |
 | **微信公众号**  |      |  ✅  |                           |
+| **微信视频号**  |  ✅  |      |                           |
 | **快手**        |  ✅  |  ✅  |                           |
 | **酷安**        |      |  ✅  |                           |
 | **皮皮虾**      |  ✅  |  ✅  |                           |
@@ -178,6 +179,7 @@ print(result)
 - `小红书`
 - `知乎`
 - `豆瓣`
+- `微信视频号`（需要填腾讯元宝 yuanbao.tencent.com 登录后的 Cookie）
 
 ```python
 from parsehub import ParseHub

{parsehub-2.3.1 → parsehub-2.3.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "parsehub"
-version = "2.3.1"
+version = "2.3.3"
 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"

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/parsers/parser/__init__.py

@@ -13,6 +13,7 @@ from .toutiao import *
 from .twitter import *
 from .weibo import *
 from .weixin import *
+from .wxchannels import *
 from .xhs import *
 from .xiaoheihe import *
 from .youtube import *

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/parsers/parser/bilibili.py

@@ -9,6 +9,7 @@ from loguru import logger
 
 from ...provider_api.bilibili import BiliAPI, BiliDynamic
 from ...types import (
+    ContentUnavailableError,
     DownloadResult,
     ImageParseResult,
     ImageRef,
@@ -92,6 +93,8 @@ class BiliParse(BaseParser):
         try:
             async with BiliAPI(proxy=self.proxy) as bili:
                 dynamic_info = await bili.get_dynamic_info(url, cookie=self.cookie.get_value())
+        except ContentUnavailableError:
+            raise
         except Exception as e:
             if "风控" in str(e):
                 raise ParseError(f"账号风控\n使用的cookie: {self.cookie}") from e

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/parsers/parser/twitter.py

@@ -11,6 +11,7 @@ from ...provider_api.twitter import (
 from ...types import (
     AniRef,
     AnyMediaRef,
+    ContentUnavailableError,
     ImageRef,
     MultimediaParseResult,
     ParseError,
@@ -38,12 +39,16 @@ class TwitterParser(BaseParser):
         x = Twitter(self.proxy, cookie=None)
         try:
             tweet = await x.fetch_tweet(url)
+        except ContentUnavailableError:
+            raise
         except Exception as e:
             if any(s in str(e) for s in ("error -2", "error -3")):
                 if cookie := self.cookie.get_value():
                     x2 = Twitter(self.proxy, cookie=cookie)
                     try:
                         tweet = await x2.fetch_tweet(url)
+                    except ContentUnavailableError:
+                        raise
                     except Exception as e2:
                         raise ParseError(f"Twitter 账号无权限或已被封禁\n\n使用的 Cookie: {self.cookie}") from e2
                 else:

parsehub-2.3.3/src/parsehub/parsers/parser/wxchannels.py

@@ -0,0 +1,30 @@
+from ...provider_api.wxchannels import WXChannels, WXChannelsError
+from ...types import ParseError, Platform, VideoParseResult, VideoRef
+from ..base.base import BaseParser
+
+
+class WXChannelsParser(BaseParser):
+    __platform__ = Platform.WEIXIN_CHANNELS
+    __supported_type__ = ["视频"]
+    __match__ = (
+        r"^(http(s)?://)?(weixin\.qq\.com/sph/\w+|"
+        r"channels\.weixin\.qq\.com/finder-preview/pages/sph\?.*\bid=\w+)"
+    )
+    __redirect_keywords__ = ["weixin.qq.com/sph/"]
+    __reserved_parameters__ = ["id"]
+
+    async def _do_parse(self, raw_url: str) -> VideoParseResult:
+        cookie = self.cookie.get_value()
+        if not cookie:
+            raise ValueError("微信视频号需要配置腾讯元宝 (yuanbao.tencent.com) 登录 Cookie")
+
+        cookie_text = "; ".join(f"{key}={value}" for key, value in cookie.items())
+        try:
+            video = await WXChannels(cookie=cookie_text, proxy=self.proxy).parse(raw_url)
+        except WXChannelsError as e:
+            raise ParseError(f"微信视频号解析失败: {e}") from e
+
+        return VideoParseResult(title=video.title, video=VideoRef(url=video.video_url, thumb_url=video.thumb_url))
+
+
+__all__ = ["WXChannelsParser"]

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/parsers/parser/xhs.py

@@ -5,6 +5,7 @@ import httpx
 
 from ...provider_api.xhs import XHSAPI, XHSMedia, XHSMediaType, XHSPostType
 from ...types import (
+    ContentUnavailableError,
     ImageParseResult,
     ImageRef,
     LivePhotoRef,
@@ -35,7 +36,7 @@ class XHSParser(BaseParser):
         if "/login" in url:
             raise ParseError("该帖子需要登录后查看")
         elif "/404" in url:
-            raise ParseError("帖子不存在")
+            raise ContentUnavailableError("帖子不存在")
         return url
 
     async def _do_parse(self, raw_url: str) -> Union["VideoParseResult", "ImageParseResult", "MultimediaParseResult"]:

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/provider_api/bilibili.py

@@ -12,6 +12,8 @@ from typing import Any, Self, cast
 
 import httpx
 
+from ..errors import ContentUnavailableError
+
 USER_AGENT = (
     "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/144.0.0.0 Safari/537.36"
 )
@@ -68,7 +70,7 @@ class BiliAPI:
                 case -352:
                     raise Exception("获取动态信息失败: -352 风控限制")
                 case 4101152:
-                    raise Exception("动态不可见")
+                    raise ContentUnavailableError("动态不可见")
                 case _:
                     raise Exception(f"获取动态信息失败: {mj}")
         return BiliDynamic.parse(cast(dict[str, Any], data))

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/provider_api/medium.py

@@ -7,6 +7,8 @@ from urllib.parse import urlparse
 
 from curl_cffi import requests
 
+from ..errors import ContentUnavailableError
+
 _ID_RE = re.compile(r"(?:^|-)([0-9a-f]{8,12})$")
 _GRAPHQL_URL = "https://medium.com/_/graphql"
 _GRAPHQL_QUERY = """
@@ -99,7 +101,7 @@ class Medium:
 
             post = result["data"]["post"]
             if post is None:
-                raise MediumError("内容不存在或已删除")
+                raise ContentUnavailableError("Medium 内容不存在或已删除")
 
             paragraphs = ((post.get("content") or {}).get("bodyModel") or {}).get("paragraphs") or []
             markdown_content, images = _render_paragraphs(paragraphs, post.get("title") or "")

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/provider_api/toutiao.py

@@ -10,6 +10,7 @@ import httpx
 from bs4 import BeautifulSoup
 from markdownify import MarkdownConverter
 
+from ..errors import ContentUnavailableError
 from ..utils.helpers import UA
 
 _ID_RE = re.compile(r"toutiao\.com/(?:(?:article|video|w|group|item)/|a|i)(\d+)")
@@ -67,7 +68,7 @@ class Toutiao:
             response.raise_for_status()
             data = response.json().get("data")
             if data is None:
-                raise ToutiaoError("内容不存在或已删除")
+                raise ContentUnavailableError("今日头条内容不存在或已删除")
 
             if "thread" in data:
                 return self._parse_micro_post(data["thread"])

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/provider_api/twitter.py

@@ -9,7 +9,7 @@ from typing import Literal, NamedTuple
 import httpx
 from loguru import logger
 
-from ..types import ParseError
+from ..types import ContentUnavailableError
 from ..utils.helpers import UA
 
 
@@ -79,7 +79,7 @@ class Twitter:
 
         result = result["data"]["tweetResult"].get("result")
         if not result:
-            raise ParseError("error -4: 帖子或用户不存在")
+            raise ContentUnavailableError("error -4: 帖子或用户不存在")
 
         if tweet := result.get("tweet"):
             tweet_id = tweet.get("rest_id", {})

parsehub-2.3.3/src/parsehub/provider_api/wxchannels.py

@@ -0,0 +1,129 @@
+from __future__ import annotations
+
+import html
+import re
+import secrets
+import time
+from dataclasses import dataclass
+from urllib.parse import parse_qs, urlparse
+
+import httpx
+
+from ..errors import ContentUnavailableError
+from ..utils.helpers import UA
+
+_SHARE_URL = "https://weixin.qq.com/sph/{}"
+_YUANBAO_API = "https://yuanbao.tencent.com/api/weixin/get_parse_result"
+_FEED_API = "https://channels.weixin.qq.com/finder-preview/api/feed/get_feed_info"
+_FEED_PAGE = "https://channels.weixin.qq.com/finder-preview/pages/feed"
+_ID_RE = re.compile(
+    r"(?:weixin\.qq\.com/sph/(\w+)|channels\.weixin\.qq\.com/finder-preview/pages/sph\?[^#]*?\bid=(\w+))"
+)
+
+
+@dataclass
+class WXChannelsVideo:
+    title: str
+    author: str
+    video_url: str
+    thumb_url: str | None
+
+
+class WXChannelsError(Exception):
+    pass
+
+
+class WXChannels:
+    def __init__(self, cookie: str, proxy: str | None = None):
+        self.cookie = cookie
+        self.proxy = proxy
+
+    async def parse(self, url: str) -> WXChannelsVideo:
+        match = _ID_RE.search(url)
+        if not match:
+            raise WXChannelsError("不支持的微信视频号链接")
+        share_id = match.group(1) or match.group(2)
+
+        async with httpx.AsyncClient(proxy=self.proxy, timeout=30) as client:
+            response = await client.post(
+                _YUANBAO_API,
+                json={"type": "video_channel_url", "url": _SHARE_URL.format(share_id), "scene": 1},
+                headers={
+                    "content-type": "application/json",
+                    "User-Agent": UA,
+                    "origin": "https://yuanbao.tencent.com",
+                    "referer": "https://yuanbao.tencent.com/",
+                    "cookie": self.cookie,
+                },
+            )
+            if response.status_code == 401:
+                raise WXChannelsError("Cookie 无效或已过期")
+            response.raise_for_status()
+            result = response.json()
+            if error := result.get("error"):
+                if str(error.get("code")) == "20000":
+                    raise WXChannelsError("Cookie 无效或已过期")
+                raise WXChannelsError(str(error.get("message") or error))
+            if result.get("code") != 0:
+                raise WXChannelsError(str(result.get("message") or "微信视频号解析失败"))
+
+            data = result.get("data") or {}
+            playable_url = data.get("playable_url") or ""
+            if not data.get("wx_export_id") or not playable_url:
+                raise ContentUnavailableError("微信视频号视频不存在或已删除")
+
+            playable_query = parse_qs(urlparse(playable_url).query)
+            token = (playable_query.get("token") or [""])[0]
+            export_id = (playable_query.get("eid") or [""])[0]
+            if not token or not export_id:
+                raise WXChannelsError("无法获取视频信息")
+
+            rid = f"{int(time.time()):x}-{secrets.token_hex(4)}"
+            response = await client.post(
+                _FEED_API,
+                params={"_rid": rid, "_pageUrl": _FEED_PAGE},
+                json={"baseReq": {"generalToken": token}, "exportId": export_id},
+                headers={
+                    "content-type": "application/json",
+                    "User-Agent": UA,
+                    "origin": "https://channels.weixin.qq.com",
+                    "referer": playable_url,
+                },
+            )
+            response.raise_for_status()
+            feed_result = response.json()
+
+        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()
+        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))
+        if error_text:
+            raise WXChannelsError(error_text)
+
+        feed_info = feed_data.get("feedInfo") or {}
+        video_url = (
+            ((feed_info.get("h264VideoInfo") or {}).get("videoUrl"))
+            or feed_info.get("videoUrl")
+            or ((feed_info.get("h265VideoInfo") or {}).get("videoUrl"))
+        )
+        if not video_url:
+            raise WXChannelsError("暂不支持该类型")
+
+        author_info = feed_data.get("authorInfo") or {}
+        return WXChannelsVideo(
+            title=feed_info.get("description") or data.get("desc") or "",
+            author=author_info.get("nickname") or data.get("author") or "",
+            video_url=video_url,
+            thumb_url=feed_info.get("coverUrl") or data.get("cover_url") or None,
+        )
+
+
+def _strip_html(value: str) -> str:
+    return html.unescape(re.sub(r"<[^>]*>", "", value)).strip()
+
+
+__all__ = ["WXChannels", "WXChannelsError", "WXChannelsVideo"]

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/provider_api/xhs.py

@@ -10,7 +10,7 @@ from typing import Any, cast
 import httpx
 from bs4 import BeautifulSoup
 
-from ..errors import ParseError
+from ..errors import ContentUnavailableError, ParseError
 from ..utils.helpers import UA
 
 
@@ -33,7 +33,7 @@ class XHSAPI:
             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")
+                raise ContentUnavailableError("帖子不存在")
             return result.text
 
     @staticmethod

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub/types/platform.py

@@ -21,6 +21,7 @@ class Platform(Enum):
     TWITTER = ("twitter", "Twitter")
     WEIBO = ("weibo", "微博")
     WEIXIN = ("weixin", "微信公众号")
+    WEIXIN_CHANNELS = ("weixin_channels", "微信视频号")
     XHS = ("xhs", "小红书")
     XIAOHEIHE = ("xiaoheihe", "小黑盒")
     YOUTUBE = ("youtube", "Youtube")

{parsehub-2.3.1 → parsehub-2.3.3/src/parsehub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: parsehub
-Version: 2.3.1
+Version: 2.3.3
 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
@@ -88,6 +88,7 @@ Dynamic: license-file
 | **小红书**      |  ✅  |  ✅  |                           |
 | **贴吧**        |  ✅  |  ✅  |                           |
 | **微信公众号**  |      |  ✅  |                           |
+| **微信视频号**  |  ✅  |      |                           |
 | **快手**        |  ✅  |  ✅  |                           |
 | **酷安**        |      |  ✅  |                           |
 | **皮皮虾**      |  ✅  |  ✅  |                           |
@@ -222,6 +223,7 @@ print(result)
 - `小红书`
 - `知乎`
 - `豆瓣`
+- `微信视频号`（需要填腾讯元宝 yuanbao.tencent.com 登录后的 Cookie）
 
 ```python
 from parsehub import ParseHub

{parsehub-2.3.1 → parsehub-2.3.3}/src/parsehub.egg-info/SOURCES.txt

@@ -37,6 +37,7 @@ src/parsehub/parsers/parser/toutiao.py
 src/parsehub/parsers/parser/twitter.py
 src/parsehub/parsers/parser/weibo.py
 src/parsehub/parsers/parser/weixin.py
+src/parsehub/parsers/parser/wxchannels.py
 src/parsehub/parsers/parser/xhs.py
 src/parsehub/parsers/parser/xiaoheihe.py
 src/parsehub/parsers/parser/youtube.py
@@ -59,6 +60,7 @@ src/parsehub/provider_api/toutiao.py
 src/parsehub/provider_api/twitter.py
 src/parsehub/provider_api/weibo.py
 src/parsehub/provider_api/weixin.py
+src/parsehub/provider_api/wxchannels.py
 src/parsehub/provider_api/xhs.py
 src/parsehub/provider_api/xiaoheihe.py
 src/parsehub/provider_api/zhihu.py