altrepo.parser: update news.news_urls parser

src/altrepo/parser/methods.py

 import aiohttp
-from bs4 import BeautifulSoup
-
-from datetime import datetime
-import calendar
-import re
 
 from . import models
-from .news import packages_parser
+from .news import urls_parser, packages_parser, bugs_parser
 
 
 class BaseParser:
@@ -25,102 +20,14 @@ class NewsInfo:
         self.client = client
 
     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 = 0
-        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)
+        return await urls_parser(self.client)
 
-            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 sisyphus_id:
-                if msg_id > sisyphus_id:
-                    result["p11"] = url
-        
-        if result["sisyphus"] is None:
-            result["p11"] = None
-
-        return models.NewsURL(**result)
-    
     async def bugs(self) -> models.BugsModel:
         url = (await self.news_urls()).bugs
+        if not url:
+            return None
         html = await self.client.get(url, "koi8-r")
-        soup = BeautifulSoup(html, "html.parser")
-        pre_tag = soup.find("pre")
-        if not pre_tag:
-            return {}
-        text = pre_tag.get_text()
-
-        lines = text.strip().splitlines()
-        data = {}
-        section_name = None
-        bug_pattern = re.compile(r"#(\d+)\s+([^\t]+)\s+([^\t]+)\s+([^\t]+)")
-        description_buffer = ""
-        current_bug = None
-
-        for line in lines:
-            header_match = re.match(r"^\s*(\d+)\s+(NEW|RESOLVED|REOPENED|RANDOM)\s+bugs?.*", line)
-            if header_match:
-                if current_bug and section_name:
-                    current_bug["summary"] = description_buffer.strip()
-                    data.setdefault(section_name, []).append(current_bug)
-                    current_bug = None
-                    description_buffer = ""
-
-                section_name = await self._get_bug_section_name(line)
-                continue
-
-            bug_match = bug_pattern.match(line)
-            if bug_match:
-                if current_bug and section_name:
-                    current_bug["summary"] = description_buffer.strip()
-                    data.setdefault(section_name, []).append(current_bug)
-
-                status = bug_match.group(4).strip()
-                if status == "---":
-                    status = None
-
-                current_bug = {
-                    "id": int(bug_match.group(1)),
-                    "component": bug_match.group(2).strip(),
-                    "priority": bug_match.group(3).strip(),
-                    "status": status
-                }
-                description_buffer = ""
-            elif current_bug:
-                if not line.strip():
-                    continue
-                if re.match(r"^Total\s+\d+\s+pending bugs", line.strip(), re.IGNORECASE):
-                    continue
-                description_buffer += line.strip() + " "
-
-        if current_bug and section_name:
-            current_bug["summary"] = description_buffer.strip()
-            data.setdefault(section_name, []).append(current_bug)
-
-        return models.BugsModel(**data)
+        return await bugs_parser(html)
 
     async def sisyphus(self) -> models.PackagesModel | None:
         url = (await self.news_urls()).sisyphus
@@ -135,21 +42,6 @@ class NewsInfo:
             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()
-        if "new" in line and "resolved" in line:
-            return "quickly_resolved"
-        elif "new" in line:
-            return "new"
-        elif "old" in line:
-            return "old"
-        elif "resolved" in line:
-            return "resolved"
-        elif "reopened" in line:
-            return "reopened"
-        elif "random" in line:
-            return "random"
 
 
 class ALTRepoParser:

src/altrepo/parser/news/__init__.py

+from .urls import urls_parser
 from .packages import packages_parser
+from .bugs import bugs_parser

src/altrepo/parser/news/bugs.py

+from bs4 import BeautifulSoup
+
+import re
+
+from .. import models
+
+async def bugs_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()
+    data = {}
+    section_name = None
+    bug_pattern = re.compile(r"#(\d+)\s+([^\t]+)\s+([^\t]+)\s+([^\t]+)")
+    description_buffer = ""
+    current_bug = None
+
+    for line in lines:
+        header_match = re.match(
+            r"^\s*(\d+)\s+(NEW|RESOLVED|REOPENED|RANDOM)\s+bugs?.*", line)
+        if header_match:
+            if current_bug and section_name:
+                current_bug["summary"] = description_buffer.strip()
+                data.setdefault(section_name, []).append(current_bug)
+                current_bug = None
+                description_buffer = ""
+
+            section_name = await _get_bug_section_name(line)
+            continue
+
+        bug_match = bug_pattern.match(line)
+        if bug_match:
+            if current_bug and section_name:
+                current_bug["summary"] = description_buffer.strip()
+                data.setdefault(section_name, []).append(current_bug)
+
+            status = bug_match.group(4).strip()
+            if status == "---":
+                status = None
+
+            current_bug = {
+                "id": int(bug_match.group(1)),
+                "component": bug_match.group(2).strip(),
+                "priority": bug_match.group(3).strip(),
+                "status": status
+            }
+            description_buffer = ""
+        elif current_bug:
+            if not line.strip():
+                continue
+            if re.match(r"^Total\s+\d+\s+pending bugs", line.strip(), re.IGNORECASE):
+                continue
+            description_buffer += line.strip() + " "
+
+    if current_bug and section_name:
+        current_bug["summary"] = description_buffer.strip()
+        data.setdefault(section_name, []).append(current_bug)
+
+    return models.BugsModel(**data)
+
+
+async def _get_bug_section_name(line: str) -> str:
+    line = line.lower()
+    if "new" in line and "resolved" in line:
+        return "quickly_resolved"
+    elif "new" in line:
+        return "new"
+    elif "old" in line:
+        return "old"
+    elif "resolved" in line:
+        return "resolved"
+    elif "reopened" in line:
+        return "reopened"
+    elif "random" in line:
+        return "random"

src/altrepo/parser/news/urls.py

+from bs4 import BeautifulSoup
+
+from datetime import datetime
+import re
+
+from .. import models
+
+from config import CYBERTALK_URL
+
+
+async def urls_parser(client):
+
+    now = datetime.now()
+    year_month = f"{now.year}-{now.strftime("%B")}"
+    today = now.strftime("%Y%m%d")
+    base_url = CYBERTALK_URL.format(year_month)
+    html = await client.get(f"{base_url}date.html", "koi8-r")
+    soup = BeautifulSoup(html, "html.parser")
+
+    sisyphus_id = 0
+    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} packages" in text:
+            result["sisyphus"] = url
+            sisyphus_id = msg_id
+        elif f"Sisyphus-{today} bugs" in text:
+            result["bugs"] = url
+        elif "p11/branch packages" in text and sisyphus_id:
+            if msg_id > sisyphus_id:
+                result["p11"] = url
+
+    if result["sisyphus"] is None:
+        result["p11"] = None
+
+    return models.NewsURL(**result)

src/config.py

@@ -18,3 +18,5 @@ DEFAUIL_BRANCHES = [
 ]
 
 BUGS_URL = "https://bugzilla.altlinux.org/"
+PACKAGES_URL = "https://packages.altlinux.org/ru/{repo}/"
+CYBERTALK_URL = "https://lists.altlinux.org/pipermail/sisyphus-cybertalk/{}/"
\ No newline at end of file