altrepo.parser: add news.sisyphus and news.p11 parsers

src/altrepo/parser/methods.py

@@ -6,6 +6,7 @@ import calendar
 import re
 
 from . import models
+from .news import packages_parser
 
 
 class BaseParser:
@@ -121,9 +122,19 @@ class NewsInfo:
 
         return models.BugsModel(**data)
 
-    async def sisyphus(self):
-        ...
-
+    async def sisyphus(self) -> models.PackagesModel | None:
+        url = (await self.news_urls()).sisyphus
+        if not url:
+            return None
+        html = await self.client.get(url, "koi8-r")
+        return await packages_parser(html)
+        
+    async def p11(self) -> models.PackagesModel | None:
+        url = (await self.news_urls()).p11
+        if not url:
+            return None
+        html = await self.client.get(url, "koi8-r")
+        return await packages_parser(html)
     
     async def _get_bug_section_name(self, line: str) -> str:
         line = line.lower()

src/altrepo/parser/models.py

@@ -23,3 +23,21 @@ class BugsModel(BaseModel):
     resolved: List[BugsElementModel] | None = None
     reopened: List[BugsElementModel] | None = None
     random: List[BugsElementModel] | None = None
+
+
+class RemovedPackageElementModel(BaseModel):
+    name: str
+    version: str
+
+
+class PackageElementModel(BaseModel):
+    name: str
+    description: str
+    maintainer_name: str
+    maintainer_nick: str
+
+
+class PackagesModel(BaseModel):
+    added: List[PackageElementModel] | None = None
+    removed: List[RemovedPackageElementModel] | None = None
+    updated: List[PackageElementModel] | None = None

src/altrepo/parser/news/__init__.py

+from .packages import packages_parser

src/altrepo/parser/news/packages.py

+from bs4 import BeautifulSoup
+
+import re
+
+from .. import models
+
+async def packages_parser(html: str):
+    soup = BeautifulSoup(html, "html.parser")
+    pre_tag = soup.find("pre")
+    if not pre_tag:
+        return {}
+    text = pre_tag.get_text()
+
+    lines = text.strip().splitlines()
+    sections = {"added": [], "removed": [], "updated": []}
+    current_section = None
+    current_package = {}
+
+    for line in lines:
+        # Смена секции
+        if re.search(r"^\s*\d+\s+ADDED package[s]?", line):
+            if current_package and current_section:
+                sections[current_section].append(current_package)
+            current_section = "added"
+            current_package = {}
+            continue
+        elif re.search(r"^\s*\d+\s+REMOVED package[s]?", line):
+            if current_package and current_section:
+                sections[current_section].append(current_package)
+            current_section = "removed"
+            current_package = {}
+            continue
+        elif re.search(r"^\s*\d+\s+UPDATED packages[s]?", line):
+            if current_package and current_section:
+                sections[current_section].append(current_package)
+            current_section = "updated"
+            current_package = {}
+            continue
+
+        if current_section == "removed":
+            if line.strip():
+                parts = line.strip().split("\t")
+                if len(parts) == 2:
+                    name, version = parts
+                    sections["removed"].append({
+                        "name": name.strip(),
+                        "version": version.strip()
+                    })
+            continue
+
+        match = re.match(r"^(\S+)\s+-\s+(.*)", line)
+        if match:
+            if current_package:
+                sections[current_section].append(current_package)
+                current_package = {}
+
+            current_package["name"] = match.group(1)
+
+            current_package["description"] = await _clean_description(match.group(2))
+            continue
+
+        match = re.match(
+            r"^\*\s+\w+\s+\w+\s+\d+\s+\d+\s+(.+?) <([a-z0-9._-]+) на altlinux>", line
+        )
+        if match and current_section != "removed":
+            if current_package:
+                current_package["maintainer_name"] = match.group(1).strip()
+                current_package["maintainer_nick"] = match.group(2).strip()
+    if current_package and current_section:
+        sections[current_section].append(current_package)
+
+    return models.PackagesModel(**sections)
+
+
+async def _clean_description(desc: str):
+    desc = desc.strip()
+    desc = re.sub(r'\s+', ' ', desc)
+    desc = re.sub(r'\[\d+[KMG]?\]', '', desc).strip()
+    return desc