wechat-article-parser 0.0.1__tar.gz → 0.0.3__tar.gz

{wechat_article_parser-0.0.1 → wechat_article_parser-0.0.3}/.gitignore

@@ -21,6 +21,7 @@ venv/
 
 # Claude Code
 .claude/
+CLAUDE.md
 
 # OS
 .DS_Store

{wechat_article_parser-0.0.1 → wechat_article_parser-0.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wechat-article-parser
-Version: 0.0.1
+Version: 0.0.3
 Summary: WeChat MP article parser - extract metadata and content from WeChat public account articles
 License-Expression: MIT
 License-File: LICENSE

{wechat_article_parser-0.0.1 → wechat_article_parser-0.0.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "wechat-article-parser"
-version = "0.0.1"
+version = "0.0.3"
 description = "WeChat MP article parser - extract metadata and content from WeChat public account articles"
 readme = "README.md"
 requires-python = ">=3.10"

wechat_article_parser-0.0.3/src/wechat_article_parser/__init__.py

@@ -0,0 +1,4 @@
+from .models import AccountType, ArticleResult, WeChatVerifyError
+from .parser import parse, parse_async
+
+__all__ = ["parse", "parse_async", "ArticleResult", "AccountType", "WeChatVerifyError"]

{wechat_article_parser-0.0.1 → wechat_article_parser-0.0.3}/src/wechat_article_parser/models.py

@@ -1,12 +1,27 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
+from enum import Enum
 
 
 class WeChatVerifyError(Exception):
     """微信返回了验证码/人机验证页面，而非文章内容时抛出此异常。"""
 
 
+class AccountType(str, Enum):
+    """公众号账号类型。继承自 str，既可按枚举比较也可按字符串比较。"""
+
+    UNKNOWN = ""
+    SUBSCRIPTION = "订阅号"
+    SERVICE = "服务号"
+
+    def __str__(self) -> str:
+        return self.value
+
+    def __format__(self, format_spec: str) -> str:
+        return format(self.value, format_spec)
+
+
 @dataclass
 class ArticleResult:
     """微信公众号文章的解析结果。"""
@@ -18,6 +33,7 @@ class ArticleResult:
     mp_alias: str = ""
     mp_image: str = ""
     mp_description: str = ""
+    mp_account_type: AccountType = AccountType.UNKNOWN
 
     # 文章信息
     article_id: str = ""

{wechat_article_parser-0.0.1 → wechat_article_parser-0.0.3}/src/wechat_article_parser/parser.py

@@ -11,7 +11,7 @@ import httpx
 from bs4 import BeautifulSoup, Tag
 from markdownify import MarkdownConverter
 
-from .models import ArticleResult, WeChatVerifyError
+from .models import AccountType, ArticleResult, WeChatVerifyError
 
 _USER_AGENT = (
     "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
@@ -76,6 +76,15 @@ def _normalize_image_url(url: str) -> str:
     return url
 
 
+def _service_type_to_account_type(value: str) -> AccountType:
+    """映射 WeChat new_service_type 到账号类型：0/1 → 订阅号，2 → 服务号。"""
+    if value in ("0", "1"):
+        return AccountType.SUBSCRIPTION
+    if value == "2":
+        return AccountType.SERVICE
+    return AccountType.UNKNOWN
+
+
 def _extract_picture_cdn_urls(script_text: str) -> list[str]:
     """从 picture_page_info_list 中只提取正文图片的 cdn_url，排除 watermark_info 和 share_cover 中的。"""
     urls: list[str] = []
@@ -120,8 +129,21 @@ def _extract_meta(soup: BeautifulSoup, result: ArticleResult) -> None:
             setattr(result, attr, value)
 
 
+def _extract_account_type(script_text: str, result: ArticleResult) -> None:
+    """从 new_service_type 中提取账号类型：0/1 → 订阅号，2 → 服务号。"""
+    if result.mp_account_type:
+        return
+    m = re.search(r"new_service_type:\s*'(\d+)'", script_text)
+    if m:
+        account_type = _service_type_to_account_type(m.group(1))
+        if account_type != AccountType.UNKNOWN:
+            result.mp_account_type = account_type
+
+
 def _extract_rich_text_meta(script_text: str, result: ArticleResult) -> None:
     """从富文本文章的 script 标签中提取元数据。"""
+    _extract_account_type(script_text, result)
+
     if "var hd_head_img" in script_text:
         m = re.search(r'var hd_head_img = "([^"]+)"', script_text)
         if m:
@@ -164,6 +186,8 @@ def _extract_rich_text_meta(script_text: str, result: ArticleResult) -> None:
 
 def _extract_swiper_meta(script_text: str, result: ArticleResult) -> None:
     """从图片轮播 / 纯文本 / 视频分享页面的 script 标签中提取元数据。"""
+    _extract_account_type(script_text, result)
+
     if "window.__initCgiDataConfig =" in script_text:
         m = re.search(r"d\.hd_head_img.*?:\s*'([^']+)'", script_text)
         if m:
@@ -236,18 +260,37 @@ def _extract_rich_media_content(content_tag: Tag, result: ArticleResult) -> None
         tag.decompose()
 
     # 处理含有 background-image 的 <svg> 标签
-    # 这些通常是装饰性元素（分隔线、底纹等），转为 <img> 用于 Markdown 渲染，但不计入 images 列表
+    # 部分文章用嵌套 SVG（外层 SVG > foreignobject > 内层 SVG）承载正文图片，
+    # 需从外向内收集所有图片 URL，一次性替换为多个 <img> 标签
     to_remove = []
-    for svg in soup.find_all("svg"):
-        style = svg.get("style", "")
-        if "background-image" in style:
+    for svg in soup.find_all("svg", recursive=True):
+        # 跳过已被外层 SVG 处理过的嵌套 SVG（已脱离文档树）
+        if not svg.parent:
+            continue
+        # 跳过嵌套在其他 SVG 内的 SVG，由外层统一处理
+        if svg.find_parent("svg"):
+            continue
+
+        # 收集本 SVG 及所有后代 SVG 中的 background-image 图片
+        all_svgs = [svg] + svg.find_all("svg")
+        img_tags = []
+        for s in all_svgs:
+            style = s.get("style", "")
+            if "background-image" not in style:
+                continue
             m = re.search(r'url\("([^"]+)"\)', style)
-            if m:
-                normalized = _normalize_image_url(m.group(1))
-                new_img = soup.new_tag("img", src=normalized)
-                svg.replace_with(new_img)
+            if not m:
                 continue
-        to_remove.append(svg)
+            normalized = _normalize_image_url(m.group(1))
+            img_tags.append(soup.new_tag("img", src=normalized))
+            if normalized not in seen:
+                seen.add(normalized)
+                result.images.append(normalized)
+
+        if img_tags:
+            svg.replace_with(*img_tags)
+        else:
+            to_remove.append(svg)
     for tag in to_remove:
         tag.decompose()
 

{wechat_article_parser-0.0.1 → wechat_article_parser-0.0.3}/tests/test_parser.py

@@ -11,6 +11,9 @@ TEST_URLS = [
     "https://mp.weixin.qq.com/s/0Wz3JeMbtWBL5iWJgYPS_Q",
     "https://mp.weixin.qq.com/s/DmZXjgIzq5gBo3H-YtcjVw",
     "https://mp.weixin.qq.com/s/80bysSCadvy9VbaovXBv2g",
+    "https://mp.weixin.qq.com/s/sfwGsafriO9sm6PfbQVXhw",
+    "https://mp.weixin.qq.com/s/h8E6riExCaH2Znmnprj-WQ",
+    "https://mp.weixin.qq.com/s/ySQdtsRlRmAl_skdc5HQ-A",
 ]
 
 
@@ -42,6 +45,7 @@ def _assert_result(result: ArticleResult, url: str) -> None:
     print(f"公众号ID:     {result.mp_id}")
     print(f"公众号名称:   {result.mp_name}")
     print(f"公众号别名:   {result.mp_alias}")
+    print(f"账号类型:     {result.mp_account_type}")
     print(
         f"公众号图片:   {result.mp_image[:80]}..."
         if result.mp_image
@@ -97,6 +101,7 @@ def test_fetch_all(url: str) -> None:
     print(f"公众号ID:     {result.mp_id}")
     print(f"公众号名称:   {result.mp_name}")
     print(f"公众号别名:   {result.mp_alias}")
+    print(f"账号类型:     {result.mp_account_type}")
     print(f"公众号图片:   {result.mp_image}")
     print(f"公众号简介:   {result.mp_description}")
     print(f"文章ID:       {result.article_id}")

wechat_article_parser-0.0.1/src/wechat_article_parser/__init__.py

@@ -1,4 +0,0 @@
-from .models import ArticleResult, WeChatVerifyError
-from .parser import parse, parse_async
-
-__all__ = ["parse", "parse_async", "ArticleResult", "WeChatVerifyError"]