Files
MoviePilot/app/modules/indexer/parser/hdarea.py
jxxghp a0e27c4424 feat(indexer): map Piggo resource labels
Resolve site labels from the Piggo catalog and dispatch connectivity, ticket parsing, and throttling through indexer capabilities.
2026-11-12 06:45:16 +08:00

177 lines
8.1 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""
通过高清视界用户汇总 API 读取身份、流量、做种和未读消息数量。
"""
import json
from typing import Any, Optional
import app.modules.indexer.spider.hdarea as hdarea_rules
from app.adapters.network.http import RequestUtils
from app.application.site.throttle import defer_site_request, site_request_config, wait_for_site_request
from app.domain import torrent as torrent_rules
from app.foundation import temporal as time_tools
from app.modules.indexer.parser import SitePage, SiteParserBase, SiteSchema
from app.runtime.log import logger
from app.runtime.settings import get_runtime_setting
from app.schemas.exception import RateLimitExceededException
class HDAreaSiteUserInfo(SiteParserBase):
"""
高清视界 API 用户数据解析器,失败时不探测 NexusPHP 页面或发布半份身份。
"""
schema = SiteSchema.HDArea
request_mode = "apikey"
allow_schema_fallback = False
def __init__(self, site_name: Optional[str], url: str, site_cookie: Optional[str], apikey: Optional[str],
token: Optional[str], request_utils: Optional[RequestUtils] = None, ua: Optional[str] = None,
emulate: bool = False, proxy: Optional[bool] = None, api_url: Optional[str] = None) -> None:
"""
保留解析器构造合同,但禁用网页 Cookie、会话与浏览器仿真。
:param site_name: 站点展示名称
:param url: 网页地址,用于站点流控和默认 API 地址
:param site_cookie: 保留旧合同,不用于 API 认证
:param apikey: 具备 read 权限的 API Key
:param token: 保留旧合同,不替代 API Key
:param request_utils: 可注入的 HTTP 客户端
:param ua: 请求 User-Agent
:param emulate: 保留旧合同,不启动浏览器
:param proxy: 是否使用站点代理
:param api_url: 资源声明的 API 基础地址
"""
super().__init__(site_name=site_name, url=url, site_cookie=None, apikey=apikey, token=token,
request_utils=request_utils or RequestUtils(), ua=ua, emulate=False, proxy=proxy,
api_url=api_url)
def parse(self) -> None:
"""
只请求用户汇总 API,完整校验后才发布用户 ID,避免把错误响应保存为有效统计。
"""
self.userid = None
self.err_msg = None
response = None
rate_site = site_request_config(self._site_url)
apikey = str(self.apikey or "").strip()
try:
if not apikey:
raise ValueError(hdarea_rules.KEY_REQUIRED)
self._parse_site_page({})
wait_for_site_request(rate_site)
response = self._request_utils.get_res(
url=f"{self._base_url}/user/profile", cookies=None, headers=self._addition_headers,
proxies=get_runtime_setting("PROXY") if self._proxy else None, timeout=60, allow_redirects=False,
)
if response is None:
raise ValueError("无法连接 HDArea API")
try:
payload = response.json()
except ValueError:
payload = None
data = hdarea_rules.response_data(response.status_code, payload, apikey)
self._parse_user_base_info(data)
except (TypeError, ValueError, RateLimitExceededException) as err:
self.err_msg = str(err).replace(apikey, "[已隐藏]") if apikey else str(err)
if torrent_rules.rate_limit_cooldown(self.err_msg) is not None:
defer_site_request(rate_site, self.err_msg)
logger.warning(f"{self._site_name} 用户数据刷新失败:{self.err_msg}")
finally:
if response is not None:
response.close()
self.close()
def _parse_site_page(self, html_text: SitePage) -> None:
"""
配置 REST API 来源并禁用所有独立 PHP 页面。
:param html_text: 保留基类签名,不解析 HTML
"""
self._base_url = str(self._api_url or f"{self._site_url.rstrip('/')}/api/v1").rstrip("/")
self._addition_headers = {"X-API-Key": str(self.apikey or "").strip(), "Accept": "application/json",
"User-Agent": self._ua}
self._user_basic_page = self._user_detail_page = self._user_traffic_page = None
self._torrent_seeding_page = self._user_mail_unread_page = self._sys_mail_unread_page = None
def _parse_user_base_info(self, html_text: SitePage) -> None:
"""
一次投影用户汇总字段,字节、魔力和人数校验完毕后才公开身份。
:param html_text: 已校验信封的 data 对象或其 JSON 文本
:raises ValueError: 用户身份、账号状态或必要统计字段无效
"""
data: dict[str, Any] = json.loads(html_text) if isinstance(html_text, str) else html_text
if data.get("enabled") is False:
raise ValueError("HDArea 账号已被禁用")
if not isinstance(data.get("username"), str) or not data["username"].strip():
raise ValueError("HDArea API 用户名无效")
user_id = hdarea_rules.integer(data.get("id"), minimum=1)
upload = hdarea_rules.integer(data.get("uploaded"))
download = hdarea_rules.integer(data.get("downloaded"))
user_level = data.get("class_name") or str(data.get("class") or "")
if not isinstance(user_level, str):
raise ValueError("HDArea API 用户等级无效")
ratio = (
hdarea_rules.number(data["share_ratio"])
if data.get("share_ratio") is not None else (upload / download if download else 0.0)
)
values = {
"username": data["username"], "user_level": user_level,
"join_at": time_tools.normalize_datetime(data.get("added")), "upload": upload, "download": download,
"ratio": ratio,
"bonus": hdarea_rules.number(data.get("seedbonus", 0)),
"seeding": hdarea_rules.integer(data.get("seeding_count")),
"seeding_size": hdarea_rules.integer(data.get("seeding_size")),
"leeching": hdarea_rules.integer(data.get("leeching_count", 0)),
"uploaded": hdarea_rules.integer(data.get("uploaded_torrents_count", 0)),
"completed": hdarea_rules.integer(data.get("completed_torrents_count", 0)),
"message_unread": hdarea_rules.integer(data.get("unread_messages_count", 0)),
}
for name, value in values.items():
setattr(self, name, value)
self.userid = user_id
def _parse_user_traffic_info(self, html_text: str) -> None:
"""
汇总 API 已提供流量,不再读取 PHP 页面。
:param html_text: 保留基类签名,不读取页面
"""
def _parse_user_detail_info(self, html_text: str) -> None:
"""
汇总 API 已提供等级、注册时间和魔力,不再读取用户详情页。
:param html_text: 保留基类签名,不读取页面
"""
def _parse_user_torrent_seeding_info(self, html_text: str, multi_page: bool = False) -> Optional[str]:
"""
直接使用汇总 API 做种数量和字节体积,不重复请求做种分页。
:param html_text: 保留基类签名,不读取页面
:param multi_page: 保留基类签名,不进行页面翻页
:return: 没有后续页面
"""
return None
def _parse_message_unread_links(self, html_text: str, msg_links: list[str]) -> Optional[str]:
"""
保留汇总 API 未读数量,不额外读取或标记私人消息。
:param html_text: 保留基类签名,不读取页面
:param msg_links: 不添加 PHP 消息地址
:return: 没有消息后续页面
"""
return None
def _parse_message_content(self, html_text: str) -> tuple[Optional[str], Optional[str], Optional[str]]:
"""
本次适配只提供未读数量,不自动访问私人消息正文。
:param html_text: 保留基类签名,不读取页面
:return: 空标题、时间和正文
"""
return None, None, None