обновление для Кубка России

переделаны все парсеры на ссылки из базы

parsers/parser_players.py

@@ -3,10 +3,9 @@ from bs4 import BeautifulSoup
 from concurrent.futures import ThreadPoolExecutor
 
 from services.players_service import sync_team_roster
+from parsers.parser_sources import get_parser_source, source_absolute_url
 
 
-URL_TEAMS = "https://wfl.rfs.ru/tournament/1061879/teams"
-
 AMPLUA_FULL = {
     "Пз.": "Полузащитник",
     "Вр.": "Вратарь",
@@ -23,19 +22,26 @@ def fetch_html(url: str) -> str:
     return r.text
 
 
-def get_links(html: str) -> list[dict]:
+def get_links(html: str, source: dict) -> list[dict]:
     soup = BeautifulSoup(html, "html.parser")
     links: list[dict] = []
 
-    items = soup.find("ul", class_="teams__list").find_all("li")
-    for i in items:
-        href = i.find("a", class_="teams__link").get("href")
-        team_external_id = href.split("team_id=")[-1].strip()
+    teams_list = soup.find("ul", class_="teams__list")
+    if not teams_list:
+        return links
 
+    items = teams_list.find_all("li")
+    for item in items:
+        link_el = item.find("a", class_="teams__link")
+        href = link_el.get("href") if link_el else ""
+        if not href:
+            continue
+
+        team_external_id = href.split("team_id=")[-1].strip() if "team_id=" in href else ""
         links.append(
             {
                 "team_external_id": team_external_id,
-                "url": "https://wfl.rfs.ru" + href,
+                "url": source_absolute_url(source, href),
             }
         )
 
@@ -92,13 +98,14 @@ def parse_team(html: str) -> dict:
 
         full_player = name_p.get_text(strip=True) if name_p else ""
         parts = full_player.split()
+        pos_short = pos_td.get_text(strip=True) if pos_td else ""
 
         players.append(
             {
                 "player_id": player_id or "",
                 "number": number_td.get_text(strip=True) if number_td else "",
-                "pos": pos_td.get_text(strip=True) if pos_td else "",
-                "amplua": AMPLUA_FULL[pos_td.get_text(strip=True) if pos_td else ""],
+                "pos": pos_short,
+                "amplua": AMPLUA_FULL.get(pos_short, pos_short),
                 "player": full_player,
                 "lastname": parts[0] if len(parts) >= 1 else "",
                 "name": parts[-1] if len(parts) >= 2 else "",
@@ -144,9 +151,13 @@ def parse_team(html: str) -> dict:
     }
 
 
-def run_parser_players() -> None:
-    html = fetch_html(URL_TEAMS)
-    links = get_links(html)
+def run_parser_players(source_key: str | None = None) -> None:
+    source = get_parser_source(source_key)
+    print(f"[parser_players] Источник: {source['title']}")
+    print(f"[parser_players] URL: {source['teams_url']}")
+
+    html = fetch_html(source["teams_url"])
+    links = get_links(html, source)
 
     with ThreadPoolExecutor(max_workers=8) as pool:
         futures = {pool.submit(fetch_html, item["url"]): item for item in links}
@@ -169,6 +180,9 @@ def run_parser_players() -> None:
             except Exception as e:
                 print(f"[parser_players] error team={item['team_external_id']}: {e}")
 
+    if not links:
+        print("[parser_players] Команды для парсинга игроков не найдены")
+
 
 if __name__ == "__main__":
     run_parser_players()