wechat-article-parser 0.0.8__tar.gz → 0.0.9__tar.gz

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: wechat-article-parser
-Version: 0.0.8
+Version: 0.0.9
 Summary: WeChat MP article parser - extract metadata and content from WeChat public account articles
 License-Expression: MIT
 License-File: LICENSE
@@ -102,6 +102,7 @@ result = parse(
 | `mp_id` | `int` | 公众号 ID（解码后的整数） |
 | `mp_name` | `str` | 公众号名称 |
 | `mp_alias` | `str` | 公众号别名 |
+| `mp_user_name` | `str` | 公众号用户名（如 `aifaner383402` 或 `gh_9a1919baf888`），未获取到时为空字符串 |
 | `mp_image` | `str` | 公众号头像链接 |
 | `mp_description` | `str` | 公众号简介 |
 | `mp_account_type` | `AccountType` | 账号类型：`AccountType.SUBSCRIPTION`（订阅号）/ `AccountType.SERVICE`（服务号）/ `AccountType.UNKNOWN`（未识别） |
@@ -115,6 +116,7 @@ result = parse(
 | `article_markdown` | `str` | 文章正文的 Markdown 内容；视频分享没有文字附言时可为空 |
 | `article_publish_time` | `int` | 发布时间（Unix 时间戳） |
 | `article_display_type` | `ArticleDisplayType` | 文章展示类型：`article`、`video`、`image`、`text` 或 `unknown` |
+| `article_item_show_type` | `int \| None` | 微信页面中的原始展示类型：`0` 图文、`5` 视频、`8` 图片轮播、`10` 文字；其他已提取的数值原样保留，缺失或无法解析时为 `None` |
 | `raw_html` | `str` | 原始 HTML 网页源代码（仅在 `include_raw_html=True` 时填充，否则为空字符串） |
 | `images` | `list[str]` | 文章中提取的所有图片链接 |
 | `is_valid` | `bool` | 关键字段是否全部解析成功（属性） |
@@ -144,10 +146,11 @@ if result.article_display_type == "video":
     print("视频分享可以没有文字正文")
 
 print(result.article_display_type)  # 例如 video
+print(result.article_item_show_type)  # 例如 5
 ```
 
 `article_display_type` 是返回结果中的数据字段，包含在 `dataclasses.asdict(result)` 中，JSON 序列化时输出语义字符串。
-微信原始的 `item_show_type` 仅在解析器内部使用，不包含在返回结果中。
+`article_item_show_type` 返回微信页面中 `item_show_type` 的原始数值，也包含在 `dataclasses.asdict(result)` 中；JSON 序列化时输出数字或 `null`。
 
 ### 判断账号类型
 

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/README.md

@@ -87,6 +87,7 @@ result = parse(
 | `mp_id` | `int` | 公众号 ID（解码后的整数） |
 | `mp_name` | `str` | 公众号名称 |
 | `mp_alias` | `str` | 公众号别名 |
+| `mp_user_name` | `str` | 公众号用户名（如 `aifaner383402` 或 `gh_9a1919baf888`），未获取到时为空字符串 |
 | `mp_image` | `str` | 公众号头像链接 |
 | `mp_description` | `str` | 公众号简介 |
 | `mp_account_type` | `AccountType` | 账号类型：`AccountType.SUBSCRIPTION`（订阅号）/ `AccountType.SERVICE`（服务号）/ `AccountType.UNKNOWN`（未识别） |
@@ -100,6 +101,7 @@ result = parse(
 | `article_markdown` | `str` | 文章正文的 Markdown 内容；视频分享没有文字附言时可为空 |
 | `article_publish_time` | `int` | 发布时间（Unix 时间戳） |
 | `article_display_type` | `ArticleDisplayType` | 文章展示类型：`article`、`video`、`image`、`text` 或 `unknown` |
+| `article_item_show_type` | `int \| None` | 微信页面中的原始展示类型：`0` 图文、`5` 视频、`8` 图片轮播、`10` 文字；其他已提取的数值原样保留，缺失或无法解析时为 `None` |
 | `raw_html` | `str` | 原始 HTML 网页源代码（仅在 `include_raw_html=True` 时填充，否则为空字符串） |
 | `images` | `list[str]` | 文章中提取的所有图片链接 |
 | `is_valid` | `bool` | 关键字段是否全部解析成功（属性） |
@@ -129,10 +131,11 @@ if result.article_display_type == "video":
     print("视频分享可以没有文字正文")
 
 print(result.article_display_type)  # 例如 video
+print(result.article_item_show_type)  # 例如 5
 ```
 
 `article_display_type` 是返回结果中的数据字段，包含在 `dataclasses.asdict(result)` 中，JSON 序列化时输出语义字符串。
-微信原始的 `item_show_type` 仅在解析器内部使用，不包含在返回结果中。
+`article_item_show_type` 返回微信页面中 `item_show_type` 的原始数值，也包含在 `dataclasses.asdict(result)` 中；JSON 序列化时输出数字或 `null`。
 
 ### 判断账号类型
 

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "wechat-article-parser"
-version = "0.0.8"
+version = "0.0.9"
 description = "WeChat MP article parser - extract metadata and content from WeChat public account articles"
 readme = "README.md"
 requires-python = ">=3.10"

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/src/wechat_article_parser/models.py

@@ -68,8 +68,12 @@ class ArticleResult:
     # 文章中提取的图片列表
     images: list[str] = field(default_factory=list)
 
-    # 对外返回语义展示类型，微信原始数值仅在解析器内部使用。
+    # 语义展示类型和微信页面中的原始数值。
     article_display_type: ArticleDisplayType = ArticleDisplayType.UNKNOWN
+    article_item_show_type: int | None = None
+
+    # 当前公众号的页面全局 user_name，未提取到时为空字符串。
+    mp_user_name: str = ""
 
     @property
     def is_valid(self) -> bool:

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/src/wechat_article_parser/parser.py

@@ -229,6 +229,84 @@ def _extract_item_show_type(scripts: list[Tag]) -> int | None:
     return None
 
 
+def _extract_user_name(scripts: list[Tag]) -> str:
+    """读取全局 user_name，缺失时读取 window.cgiDataNew 的直接属性。
+
+    文章元数据脚本中该变量位于 nickname、ct 附近；不依赖行号或账号值。
+    使用词法标记跳过注释和字符串，不执行页面脚本。
+    """
+    for script in scripts:
+        if "user_name" not in script.text:
+            continue
+        history: deque[str] = deque(maxlen=4)
+        brace_depth = 0
+        for match in _JS_DATA_TOKEN_RE.finditer(script.text):
+            if match.lastgroup == "comment":
+                continue
+            token = match.group()
+            previous = tuple(history)
+            if (
+                brace_depth == 0
+                and token == ";"
+                and previous[:3] == ("var", "user_name", "=")
+                and len(previous) == 4
+                and previous[3].startswith(("'", '"'))
+            ):
+                value = _decode_text(previous[3][1:-1])
+                if value:
+                    return value
+            if token == "{":
+                brace_depth += 1
+            elif token == "}":
+                brace_depth -= 1
+            history.append(token)
+    return _extract_cgi_user_name(scripts)
+
+
+def _extract_cgi_user_name(scripts: list[Tag]) -> str:
+    """从当前文章的 cgiDataNew 对象中读取 user_name，排除嵌套账号。"""
+    for script in scripts:
+        if "cgiDataNew" not in script.text or "user_name" not in script.text:
+            continue
+        history: deque[str] = deque(maxlen=5)
+        stack: list[str] = []
+        for match in _JS_DATA_TOKEN_RE.finditer(script.text):
+            if match.lastgroup == "comment":
+                continue
+            token = match.group()
+            previous = tuple(history)
+            if not stack:
+                if (
+                    token == "{"
+                    and previous[-4:] == ("window", ".", "cgiDataNew", "=")
+                    and (len(previous) < 5 or previous[-5] != ".")
+                ):
+                    stack.append(token)
+            else:
+                # 只接受完整的字符串属性值，不读取表达式或嵌套对象的值。
+                if (
+                    stack == ["{"]
+                    and token in (",", "}")
+                    and len(previous) >= 4
+                    and previous[-4] in ("{", ",")
+                    and previous[-3].strip("\"'") == "user_name"
+                    and previous[-2] == ":"
+                    and previous[-1].startswith(("'", '"'))
+                ):
+                    value = _decode_text(previous[-1][1:-1])
+                    if value:
+                        return value
+                if token in ("{", "["):
+                    stack.append(token)
+                elif token in ("}", "]"):
+                    if stack[-1] == {"}": "{", "]": "["}[token]:
+                        stack.pop()
+                    else:
+                        stack.clear()
+            history.append(token)
+    return ""
+
+
 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:
@@ -578,7 +656,9 @@ def _parse_html(url: str, html: str) -> ArticleResult:
 
     scripts = soup.find_all("script", attrs={"type": "text/javascript"})
 
+    result.mp_user_name = _extract_user_name(soup.find_all("script"))
     item_show_type = _extract_item_show_type(scripts)
+    result.article_item_show_type = item_show_type
     result.article_display_type = _ARTICLE_DISPLAY_TYPES.get(
         item_show_type, ArticleDisplayType.UNKNOWN,
     )

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/tests/test_models.py

@@ -79,11 +79,11 @@ def test_display_type_has_semantic_string_values(expected: str) -> None:
     assert json.dumps(result.article_display_type) == json.dumps(expected)
     serialized = json.loads(json.dumps(asdict(result)))
     assert serialized["article_display_type"] == expected
-    assert "item_show_type" not in serialized
-    assert not hasattr(result, "item_show_type")
+    assert serialized["article_item_show_type"] is None
 
 
 def test_default_display_type_is_unknown() -> None:
     result = ArticleResult()
     assert result.article_display_type is ArticleDisplayType.UNKNOWN
+    assert result.article_item_show_type is None
     assert not result.is_valid

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/tests/test_parser.py

@@ -47,6 +47,7 @@ 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"公众号用户名: {result.mp_user_name}")
     print(f"账号类型:     {result.mp_account_type}")
     print(
         f"公众号图片:   {result.mp_image[:80]}..."
@@ -64,6 +65,7 @@ def _assert_result(result: ArticleResult, url: str) -> None:
     print(f"文章签名:     {result.article_sn}")
     print(f"文章标题:     {result.article_title}")
     print(f"展示类型:     {result.article_display_type}")
+    print(f"原始展示类型: {result.article_item_show_type}")
     print(
         f"封面图:       {result.article_cover_image[:80]}..."
         if result.article_cover_image
@@ -82,6 +84,7 @@ def _assert_result(result: ArticleResult, url: str) -> None:
 
     assert result.mp_id > 0, "mp_id should be positive"
     assert result.mp_name, "mp_name should not be empty"
+    assert result.mp_user_name, "mp_user_name should not be empty for these reference articles"
     assert result.article_id, "article_id should not be empty"
     assert result.article_msg_id > 0, "article_msg_id should be positive"
     assert result.article_idx > 0, "article_idx should be positive"
@@ -105,6 +108,7 @@ def test_fetch_all(url: str, proxy: str | None) -> 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"公众号用户名: {result.mp_user_name}")
     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}")
@@ -114,6 +118,7 @@ def test_fetch_all(url: str, proxy: str | None) -> None:
     print(f"文章签名:     {result.article_sn}")
     print(f"文章标题:     {result.article_title}")
     print(f"展示类型:     {result.article_display_type}")
+    print(f"原始展示类型: {result.article_item_show_type}")
     print(f"封面图:       {result.article_cover_image}")
     print(f"文章摘要:     {result.article_description}")
     print(f"发布时间:     {result.article_publish_time}")

{wechat_article_parser-0.0.8 → wechat_article_parser-0.0.9}/tests/test_type_routing.py

@@ -1,5 +1,8 @@
 """类型字段优先分发、模板细分及 HTML 兜底的离线回归测试。"""
 
+from dataclasses import asdict
+import json
+
 import pytest
 from bs4 import BeautifulSoup
 
@@ -63,6 +66,9 @@ def test_read_current_article_type(script: str, expected: int | None) -> None:
     soup = BeautifulSoup(_html(script=script), "html.parser")
 
     assert parser._extract_item_show_type(soup.find_all("script")) == expected
+    result = parser._parse_html(_URL, _html(_RICH_TEXT, script))
+    assert result.article_item_show_type == expected
+    assert json.loads(json.dumps(asdict(result)))["article_item_show_type"] == expected
 
 
 @pytest.mark.parametrize("current_assignment", ["", "window.item_show_type = '8';"])
@@ -102,6 +108,7 @@ def test_type_zero_uses_html_to_distinguish_rich_text_and_repost(
     result = parser._parse_html(_URL, _html(body, 'var item_show_type = "0";'))
 
     assert result.article_display_type is ArticleDisplayType.ARTICLE
+    assert result.article_item_show_type == 0
     assert expected in result.article_markdown
     if expected == "转载附言":
         assert "[查看原文](https://example.com/original)" in result.article_markdown
@@ -130,7 +137,7 @@ def test_known_type_takes_priority_over_other_html_templates(
     assert expected in result.article_markdown
     assert "富文本正文" not in result.article_markdown
     assert result.article_display_type is display_type
-    assert not hasattr(result, "item_show_type")
+    assert result.article_item_show_type == item_type
     if item_type == 8:
         assert result.images == ["https://mmbiz.qpic.cn/mmbiz_png/body/640"]
 
@@ -154,6 +161,7 @@ def test_known_type_without_matching_data_falls_back_to_html(item_type: int) ->
     )
 
     assert result.article_markdown == "富文本正文"
+    assert result.article_item_show_type == item_type
 
 
 def test_type_zero_without_matching_html_falls_back_to_other_templates() -> None:
@@ -196,6 +204,7 @@ def test_unrecognized_content_still_returns_metadata() -> None:
 
     assert result.article_title == "原标题"
     assert result.mp_alias == "account"
+    assert result.article_item_show_type == 999
     assert result.article_display_type is ArticleDisplayType.UNKNOWN
     assert result.article_markdown == ""
     assert not result.is_valid

wechat_article_parser-0.0.9/tests/test_user_name.py

@@ -0,0 +1,137 @@
+"""当前公众号 user_name 的位置规则及公开返回接口回归测试。"""
+
+from dataclasses import asdict
+import json
+
+import httpx
+import pytest
+
+from wechat_article_parser import ArticleResult, parser
+
+
+_URL = "https://mp.weixin.qq.com/s/tBqB3134QzILypNVUW1fdw"
+# 精简自参考页面的文章元数据脚本，保留字段上下文。
+_METADATA = """
+var nickname = htmlDecode("爱范儿");
+var appmsg_type = "9";
+var ct = "1784779200";
+var user_name = "aifaner383402";
+var fakeid = "";
+"""
+_DECOYS = """
+var ad = {biz_info: {user_name: 'gh_1e80bb81a1d2'}};
+window.cgiDataNew = {ad: {user_name: 'nested-ad-account'}};
+(function () { var user_name = 'local-account'; })();
+function report() { var user_name = 'another-local-account'; }
+var example = "var user_name = 'string-account';";
+var template = `var user_name = 'template-account';`;
+// var user_name = 'comment-account';
+/* var user_name = 'block-comment-account'; */
+var original_user_name = 'reference-account';
+var info = {userName: window.user_name};
+"""
+
+
+def _html(*scripts: str, body: str = "") -> str:
+    return body + "".join(
+        f'<script type="text/javascript">{script}</script>' for script in scripts
+    )
+
+
+@pytest.mark.parametrize("body", ["", '<div class="rich_media_content">正文</div>'])
+def test_user_name_comes_from_global_metadata(body: str) -> None:
+    result = parser._parse_html(_URL, _html(_DECOYS, _METADATA, _DECOYS, body=body))
+
+    assert result.mp_user_name == "aifaner383402"
+    assert json.loads(json.dumps(asdict(result)))["mp_user_name"] == "aifaner383402"
+
+
+@pytest.mark.parametrize(
+    ("declaration", "expected"),
+    [
+        ("var user_name = 'gh_another-account';", "gh_another-account"),
+        ('var\nuser_name /* comment */ = "other_account";', "other_account"),
+        (r'var user_name = "gh_\x61bc";', "gh_abc"),
+        ("", ""),
+        ("var user_name = '';", ""),
+        ("var user_name = null;", ""),
+        ("var user_name = another_variable;", ""),
+        ("var user_name = 'prefix' + suffix;", ""),
+    ],
+)
+def test_user_name_is_dynamic_and_missing_values_are_empty(
+    declaration: str, expected: str,
+) -> None:
+    result = parser._parse_html(_URL, _html(_DECOYS, declaration))
+    assert result.mp_user_name == expected
+
+
+def test_script_without_type_attribute() -> None:
+    result = parser._parse_html(_URL, f"<script>{_METADATA}</script>")
+    assert result.mp_user_name == "aifaner383402"
+
+
+def test_default_user_name() -> None:
+    assert ArticleResult().mp_user_name == ""
+
+
+@pytest.mark.parametrize("key", ["user_name", "'user_name'", '"user_name"'])
+@pytest.mark.parametrize("body", ["", '<div class="rich_media_content">正文</div>'])
+def test_cgi_direct_user_name_fallback(key: str, body: str) -> None:
+    data = (
+        "(function () { window.cgiDataNew = {"
+        "base_resp: {ret: '0' * 1},"
+        "ad: {user_name: 'wrong-ad'},"
+        "references: [{user_name: 'wrong-reference'}],"
+        f"{key}: 'gh_9a1919baf888'"
+        "}; })();"
+    )
+    result = parser._parse_html(_URL, _html(_DECOYS, data, body=body))
+    assert result.mp_user_name == "gh_9a1919baf888"
+
+
+def test_global_metadata_has_priority_over_cgi_fallback() -> None:
+    data = "window.cgiDataNew = {user_name: 'cgi-account'};"
+    result = parser._parse_html(_URL, _html(data, _METADATA))
+    assert result.mp_user_name == "aifaner383402"
+
+
+@pytest.mark.parametrize(
+    "data",
+    [
+        "window.cgiDataNew = {user_name: ''};",
+        "window.cgiDataNew = {user_name: 'prefix' + suffix};",
+        "other.window.cgiDataNew = {user_name: 'wrong'};",
+        "var text = \"window.cgiDataNew = {user_name: 'wrong'};\";",
+        "// window.cgiDataNew = {user_name: 'wrong'};",
+        "/* window.cgiDataNew = {user_name: 'wrong'}; */",
+    ],
+)
+def test_cgi_fallback_ignores_decoys_and_nonliteral_values(data: str) -> None:
+    result = parser._parse_html(_URL, _html(_DECOYS, data))
+    assert result.mp_user_name == ""
+
+
+@pytest.fixture
+def mock_article_http(monkeypatch):
+    transport = httpx.MockTransport(
+        lambda request: httpx.Response(200, text=_html(_DECOYS, _METADATA))
+    )
+    client = httpx.Client
+    async_client = httpx.AsyncClient
+    monkeypatch.setattr(
+        parser.httpx, "Client", lambda **kwargs: client(transport=transport, **kwargs),
+    )
+    monkeypatch.setattr(
+        parser.httpx, "AsyncClient", lambda **kwargs: async_client(transport=transport, **kwargs),
+    )
+
+
+def test_sync_parse_returns_user_name(mock_article_http) -> None:
+    assert parser.parse(_URL).mp_user_name == "aifaner383402"
+
+
+@pytest.mark.asyncio
+async def test_async_parse_returns_user_name(mock_article_http) -> None:
+    result = await parser.parse_async(_URL)
+    assert result.mp_user_name == "aifaner383402"