mews.packages: add support for the news archive

src/altrepo/parser/news/packages.py

+import aiohttp
 from bs4 import BeautifulSoup
-
 import re
-
+import io
+import gzip
 from .. import models
 
-async def packages_parser(html: str, url:  str):
+from pprint import pprint
+
+async def packages_parser(html: str, url: str):
     soup = BeautifulSoup(html, "html.parser")
     pre_tag = soup.find("pre")
     if not pre_tag:
         return {}
-    text = pre_tag.get_text()
+
+    pre_text = pre_tag.get_text(strip=True)
+    if "Было удалено вложение" in pre_text and "attachment" in pre_text:
+        attachment_link = pre_tag.find("a", href=True)
+        if attachment_link:
+            attachment_url = attachment_link["href"]
+            text = await _fetch(attachment_url)
+        else:
+            return models.PackagesModel(**{"added": [], "removed": [], "updated": [], "url": "none"})
+    else:
+        text = pre_tag.get_text()
 
     lines = text.strip().splitlines()
     sections = {"added": [], "removed": [], "updated": []}
     current_section = None
     current_package = {}
+    seen_changelog = False
 
     for line in lines:
         # Смена секции
@@ -23,18 +37,21 @@ async def packages_parser(html: str, url:  str):
                 sections[current_section].append(current_package)
             current_section = "added"
             current_package = {}
+            seen_changelog = False
             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 = {}
+            seen_changelog = False
             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 = {}
+            seen_changelog = False
             continue
 
         if current_section == "removed":
@@ -50,22 +67,27 @@ async def packages_parser(html: str, url:  str):
 
         match = re.match(r"^(\S+)\s+-\s+(.*)", line)
         if match:
-            if current_package:
+            if current_package and current_section:
                 sections[current_section].append(current_package)
-                current_package = {}
 
-            current_package["name"] = match.group(1)
-
-            current_package["description"] = await _clean_description(match.group(2))
+            current_package = {
+                "name": match.group(1),
+                "description": await _clean_description(match.group(2)),
+            }
+            seen_changelog = False
             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:
+        if (
+            current_package
+            and current_section != "removed"
+            and not seen_changelog
+        ):
+            match = re.match(r"^\*\s+\w+\s+\w+\s+\d+\s+\d+\s+(.+?) <([^@\s>]+)(?:@altlinux| на altlinux)>", line)
+            if match:
                 current_package["maintainer_name"] = match.group(1).strip()
                 current_package["maintainer_nick"] = match.group(2).strip()
+                seen_changelog = True
+            continue
     if current_package and current_section:
         sections[current_section].append(current_package)
     
@@ -79,3 +101,14 @@ async def _clean_description(desc: str):
     desc = re.sub(r'\s+', ' ', desc)
     desc = re.sub(r'\[\d+[KMG]?\]', '', desc).strip()
     return desc
+
+async def _fetch(url: str) -> str:
+    async with aiohttp.ClientSession() as session:
+        async with session.get(url) as response:
+            response.raise_for_status()
+            compressed_data = await response.read()
+
+    with gzip.GzipFile(fileobj=io.BytesIO(compressed_data)) as gz:
+        text = gz.read().decode('utf-8')
+
+    return text

src/handlers/news.py

 from telegrinder import Dispatch, Message
 from telegrinder.rules import Command, Argument
+from telegrinder.node import Error
 
 from altrepo import altrepo
 
@@ -30,8 +31,15 @@ async def news_handler(m: Message, news_type: str | None, translate: str | None)
             await m.answer("Новостей пока нет.")
             return
         
-        added, removed, updated, info_message = await format_packages(packages_data, bool(translate))
-        
+        if bool(translate):
+            await m.answer("Начался перевод, это может занять до 10 минут.")
+
+        try:
+            added, removed, updated, info_message = await format_packages(packages_data, bool(translate))
+        except:
+            await m.answer("перевод не удался :(")
+            return
+
         await m.answer(f"{added}{removed}{info_message}")
         for msg in updated:
-            res = await m.answer(msg)
+            await m.answer(msg)

src/services/news/packages.py

@@ -27,6 +27,7 @@ async def format_packages(packages: PackagesModel, translate: bool | None = None
         removed_message += "Удалены:\n"
         for package in packages.removed:
             removed_message += await _format_removed_package(package)
+        removed_message += "\n"
 
     if packages.updated:
         updated_messages = await _format_updated_packages(packages, translate)
@@ -54,7 +55,7 @@ async def _format_package(package: PackageElementModel, translate: bool):
 async def _format_removed_package(package: RemovedPackageElementModel):
 
     message = HTMLFormatter(
-        bold(link(f"{repo}srpms/{package.name}", text=package.name))) + "\n\n"
+        bold(link(f"{repo}srpms/{package.name}", text=package.name))) + "\n"
     return message