altrepo.parser: add news.news_urls parser

poetry.lock

@@ -185,6 +185,44 @@ tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothe
 tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\""]
 
 [[package]]
+name = "beautifulsoup4"
+version = "4.13.4"
+description = "Screen-scraping library"
+optional = false
+python-versions = ">=3.7.0"
+groups = ["main"]
+files = [
+    {file = "beautifulsoup4-4.13.4-py3-none-any.whl", hash = "sha256:9bbbb14bfde9d79f38b8cd5f8c7c85f4b8f2523190ebed90e950a8dea4cb1c4b"},
+    {file = "beautifulsoup4-4.13.4.tar.gz", hash = "sha256:dbb3c4e1ceae6aefebdaf2423247260cd062430a410e38c66f2baa50a8437195"},
+]
+
+[package.dependencies]
+soupsieve = ">1.2"
+typing-extensions = ">=4.0.0"
+
+[package.extras]
+cchardet = ["cchardet"]
+chardet = ["chardet"]
+charset-normalizer = ["charset-normalizer"]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
+[[package]]
+name = "bs4"
+version = "0.0.2"
+description = "Dummy package for Beautiful Soup (beautifulsoup4)"
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "bs4-0.0.2-py2.py3-none-any.whl", hash = "sha256:abf8742c0805ef7f662dce4b51cca104cffe52b835238afc169142ab9b3fbccc"},
+    {file = "bs4-0.0.2.tar.gz", hash = "sha256:a48685c58f50fe127722417bae83fe6badf500d54b55f7e39ffe43b798653925"},
+]
+
+[package.dependencies]
+beautifulsoup4 = "*"
+
+[[package]]
 name = "certifi"
 version = "2025.7.9"
 description = "Python package for providing Mozilla's CA Bundle."
@@ -1034,6 +1072,18 @@ files = [
 cli = ["click (>=5.0)"]
 
 [[package]]
+name = "soupsieve"
+version = "2.7"
+description = "A modern CSS selector implementation for Beautiful Soup."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4"},
+    {file = "soupsieve-2.7.tar.gz", hash = "sha256:ad282f9b6926286d2ead4750552c8a6142bc4c783fd66b0293547c8fe6ae126a"},
+]
+
+[[package]]
 name = "telegrinder"
 version = "0.5.1"
 description = "Modern visionary telegram bot framework."
@@ -1228,4 +1278,4 @@ propcache = ">=0.2.1"
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.12,<4.0"
-content-hash = "a510528d6af1e3839834d33b34c1b07dd8842f5755c5d861429e32bf4432e0af"
+content-hash = "a931f25d5878e10204c31cdf053d05a4587b3b5c55056e719c2f1489525c1084"

pyproject.toml

@@ -12,7 +12,8 @@ dependencies = [
     "telegrinder (>=0.5.1,<0.6.0)",
     "pydantic (>=2.11.7,<3.0.0)",
     "pydantic-settings (>=2.10.1,<3.0.0)",
-    "peewee (>=3.18.2,<4.0.0)"
+    "peewee (>=3.18.2,<4.0.0)",
+    "bs4 (>=0.0.2,<0.0.3)"
 ]
 
 [project.urls]

src/altrepo/parser/methods.py

 import aiohttp
+from bs4 import BeautifulSoup
 
-from typing import Literal
+from datetime import datetime
+import calendar
+import re
 
 from . import models
 
@@ -10,18 +13,54 @@ class BaseParser:
     def __init__(self, session: aiohttp.ClientSession):
         self.session = session
 
-    async def get(self, url: str):
+    async def get(self, url: str, encoding: str = "utf-8"):
         async with self.session.get(url) as resp:
             resp.raise_for_status()
-            return await resp.text()
+            return await resp.text(encoding=encoding)
 
 
 class NewsInfo:
     def __init__(self, client: BaseParser):
         self.client = client
 
-    async def news_url(self, news_type: Literal["sisyphus", "p11", "bugs"]):
-        ...
+    async def news_urls(self) -> models.NewsURL:
+        now = datetime.now()
+        month_path = f"{now.year}-{calendar.month_name[now.month]}"
+        today_str = now.strftime("%Y%m%d")
+        base_url = f"https://lists.altlinux.org/pipermail/sisyphus-cybertalk/{month_path}/"
+
+        html = await self.client.get(f"{base_url}date.html", "koi8-r")
+        soup = BeautifulSoup(html, "html.parser")
+
+        sisyphus_id = -1
+        result = {"sisyphus": None, "bugs": None, "p11": None}
+
+        for li in soup.find_all("li"):
+            a = li.find("a")
+            if not a or not a.get("href"):
+                continue
+
+            href = a["href"]
+            text = a.get_text(strip=True)
+
+            match = re.search(r"(\d+)\.html", href)
+            if not match:
+                continue
+            msg_id = int(match.group(1))
+            url = base_url + href
+
+            if f"Sisyphus-{today_str} packages" in text:
+                result["sisyphus"] = url
+                sisyphus_id = msg_id
+            elif f"Sisyphus-{today_str} bugs" in text:
+                result["bugs"] = url
+            elif "p11/branch packages" in text and msg_id > sisyphus_id:
+                result["p11"] = url
+        
+        if result["sisyphus"] is None:
+            result["p11"] = None
+
+        return models.NewsURL(**result)
 
     async def sisyphus(self):
         ...

src/altrepo/parser/models.py

 from pydantic import BaseModel
 from typing import List, Dict, Any
+
+
+class NewsURL(BaseModel):
+    sisyphus: str | None = None
+    p11: str | None = None
+    bugs: str | None = None