feat: +fl.ru

app/config.py

@@ -14,6 +14,7 @@ class Settings:
     telegram_proxy_url: str | None
     scheduler_interval_minutes: int
     kwork_category_ids: list[int]
+    fl_rss_url: str | None
     keywords_include: list[str]
     keywords_exclude: list[str]
     min_price_amount: int | None
@@ -33,6 +34,7 @@ def load_settings() -> Settings:
         telegram_proxy_url=_parse_optional_text(os.getenv("TELEGRAM_PROXY_URL", "")),
         scheduler_interval_minutes=int(os.getenv("SCHEDULER_INTERVAL_MINUTES", "5")),
         kwork_category_ids=_parse_int_list(os.getenv("KWORK_CATEGORY_IDS", "41")),
+        fl_rss_url=_parse_optional_text(os.getenv("FL_RSS_URL", "https://www.fl.ru/rss/?category=5")),
         keywords_include=_parse_text_list(os.getenv("KEYWORDS_INCLUDE", "")),
         keywords_exclude=_parse_text_list(os.getenv("KEYWORDS_EXCLUDE", "")),
         min_price_amount=_parse_optional_int(os.getenv("MIN_PRICE_AMOUNT", "")),

app/sources/__init__.py

@@ -1,4 +1,5 @@
 from app.sources.base import OfferSource
+from app.sources.fl import FlSource
 from app.sources.kwork import KworkSource
 
-__all__ = ["OfferSource", "KworkSource"]
+__all__ = ["OfferSource", "FlSource", "KworkSource"]

app/sources/fl.py

@@ -0,0 +1,72 @@
+from __future__ import annotations
+
+import html
+from typing import Final
+from urllib.parse import urlparse
+from xml.etree import ElementTree
+
+import requests
+
+from app.models import Offer
+from app.sources.base import OfferSource
+
+
+class FlSource(OfferSource):
+    source_name = "fl"
+    _default_category_id: Final[int] = 5
+
+    def __init__(self, rss_url: str, timeout_seconds: int) -> None:
+        self._rss_url = rss_url
+        self._timeout_seconds = timeout_seconds
+        self._session = requests.Session()
+        self._session.headers.update(
+            {
+                "User-Agent": (
+                    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
+                    "(KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
+                )
+            }
+        )
+
+    def fetch_offers(self) -> list[Offer]:
+        response = self._session.get(self._rss_url, timeout=self._timeout_seconds)
+        response.raise_for_status()
+
+        root = ElementTree.fromstring(response.content)
+        offers: list[Offer] = []
+
+        for item in root.findall("./channel/item"):
+            url = _get_item_text(item, "link")
+            external_id = _extract_external_id(url)
+            if external_id is None:
+                continue
+
+            offers.append(
+                Offer(
+                    source=self.source_name,
+                    external_id=external_id,
+                    title=_get_item_text(item, "title", "Без названия"),
+                    description=_get_item_text(item, "description"),
+                    price="Не указан",
+                    price_amount=None,
+                    url=url,
+                    category_id=self._default_category_id,
+                    published_at=_get_item_text(item, "pubDate"),
+                )
+            )
+
+        return offers
+
+
+def _get_item_text(item: ElementTree.Element, tag_name: str, default: str = "") -> str:
+    element = item.find(tag_name)
+    if element is None or element.text is None:
+        return default
+    return html.unescape(element.text.strip())
+
+
+def _extract_external_id(url: str) -> str | None:
+    path_parts = [part for part in urlparse(url).path.split("/") if part]
+    if len(path_parts) < 2 or path_parts[0] != "projects":
+        return None
+    return path_parts[1]