feat(dufe): 新增 mode=auto 自动签到，非签到码逻辑以 bot 为基准同步
- mode=auto: 通知列表(getMessageAll+busiMessage/list)发现签到活动 (bot ginkgo 同款过滤, 按 signInId 去重) → 逐个自动签到 - 连续重试: 首次+最多5次间隔3s (对齐 bot MAX_SIGNIN_ATTEMPTS/SIGNIN_BACKOFF), token 失效重登录一次立即重试; 限流中断本轮; 结果聚合 data.results 列表 - 基准同步 (bot ginkgo): 移植限流防护体系(check_response/is_rate_limited/ safe_error/_LoginErrors/_request), parse_course_url courseId 放宽 [0-9A-Za-z]+, commit_sign_in 错误包装, fetch_sign_in_info 增加 check_response 与 sess/token 注入 (auto 模式请求内复用登录态) - 验证: 免凭据单测 + 假凭据 401 线路测试 + bj 真账密只读联调 (notices=20/busi=18/活动12 类型解析正确)
This commit is contained in:
RRRosmontis
@@ -6,17 +6,27 @@ Ginkgo (DUFE) sign-in code query service.
|
||||
Endpoint: GET|POST /dufe/ginkgostu_sign_in
|
||||
params: username, password(base64), url(base64)
|
||||
[commit=true] optional, default true: also POST the code back
|
||||
[mode=auto] optional: fetch the notification list, discover
|
||||
sign-in activities and auto sign-in each one
|
||||
(bot ginkgo parity, consecutive retries);
|
||||
results returned as an aggregated list.
|
||||
mode=auto 时 url 参数可省略。
|
||||
Listen: 127.0.0.1:9005 (WSGI: waitress)
|
||||
"""
|
||||
|
||||
import base64
|
||||
import binascii
|
||||
import html as _html
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
import sys
|
||||
import time
|
||||
import urllib.parse
|
||||
import uuid
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from email.utils import parsedate_to_datetime
|
||||
from html.parser import HTMLParser
|
||||
|
||||
try:
|
||||
import requests
|
||||
@@ -43,6 +53,17 @@ GINKGO = "https://ginkgostu.dufe.edu.cn"
|
||||
SSO = "https://sso.dufe.edu.cn"
|
||||
CUSTOM_CODE = "kb_dconline"
|
||||
|
||||
NOTICE_PAGE = GINKGO + "/notice"
|
||||
SYSTEM_PAGE = GINKGO + "/notice/system"
|
||||
|
||||
PAGE_SIZE = 20 # 单类单次抓取条数（与 bot ginkgo 一致）
|
||||
# 自动签到重试参数（与 bot ginkgo 的 MAX_SIGNIN_ATTEMPTS / SIGNIN_BACKOFF 一致：
|
||||
# 首次 + 最多 5 次重试，每次间隔 3 秒）
|
||||
MAX_SIGNIN_ATTEMPTS = 6
|
||||
SIGNIN_BACKOFF = (3, 3, 3, 3, 3)
|
||||
|
||||
TZ8 = timezone(timedelta(hours=8))
|
||||
|
||||
UA = ("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
|
||||
"(KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36")
|
||||
|
||||
@@ -65,13 +86,183 @@ class AuthError(Exception):
|
||||
|
||||
|
||||
class NoSignInCodeError(Exception):
|
||||
"""The sign-in activity exists but has no code configured."""
|
||||
"""The numeric-code activity exists but has no code configured."""
|
||||
|
||||
|
||||
class UnsupportedSigninType(Exception):
|
||||
"""The activity requires a flow this service cannot safely automate."""
|
||||
|
||||
|
||||
SIGNIN_TYPE_NAMES = {
|
||||
0: "二维码签到",
|
||||
1: "数字码签到",
|
||||
2: "普通签到",
|
||||
3: "直播签到",
|
||||
}
|
||||
|
||||
|
||||
def signin_type_label(value):
|
||||
try:
|
||||
signin_type = int(value)
|
||||
except (TypeError, ValueError):
|
||||
return "未知签到类型"
|
||||
return SIGNIN_TYPE_NAMES.get(signin_type, "未知签到类型(%s)" % signin_type)
|
||||
|
||||
|
||||
class UpstreamError(Exception):
|
||||
"""Remote service returned an unexpected or erroneous response."""
|
||||
|
||||
|
||||
class RateLimitedError(Exception):
|
||||
"""An upstream explicitly refused requests due to throttling."""
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------
|
||||
# Rate-limit detection & credential-safe errors
|
||||
# (synced from bot ginkgostu.py 2026-09-23; bot is the baseline)
|
||||
# ------------------------------------------------------------------------------
|
||||
_RATE_MESSAGE = re.compile(
|
||||
r"too\s+many\s+requests|rate[\s_-]*limit(?:ed|ing|\s+exceeded)?|"
|
||||
r"request(?:s)?\s+throttl|throttl(?:ed|ing)|"
|
||||
r"(?:请求|访问|操作|登录|登陆|接口|提交).{0,12}(?:过于频繁|太频繁|频繁|频率.{0,6}(?:超|限制))|"
|
||||
r"(?:限流|请求次数.{0,8}(?:超限|超出|超过)|访问次数.{0,8}(?:超限|超出|超过))",
|
||||
re.I,
|
||||
)
|
||||
_RATE_CODES = {"429", "4290", "40029", "90029", "RATE_LIMIT", "RATE_LIMITED", "RATE_LIMIT_EXCEEDED",
|
||||
"TOO_MANY_REQUESTS", "REQUEST_TOO_FREQUENT", "THROTTLED",
|
||||
"THROTTLING", "FREQUENT_REQUESTS"}
|
||||
_FIELDS = ("code", "msg", "message", "error")
|
||||
|
||||
|
||||
def _status(value):
|
||||
try:
|
||||
return int(value)
|
||||
except (ValueError, TypeError):
|
||||
return 0
|
||||
|
||||
|
||||
def _explicit(value, depth=0):
|
||||
if depth > 3:
|
||||
return False
|
||||
if isinstance(value, dict):
|
||||
for key in _FIELDS:
|
||||
item = value.get(key)
|
||||
if key == "code" and isinstance(item, (str, int)):
|
||||
if str(item).strip().upper().replace("-", "_") in _RATE_CODES:
|
||||
return True
|
||||
elif isinstance(item, dict):
|
||||
if _explicit(item, depth + 1):
|
||||
return True
|
||||
elif isinstance(item, str) and _RATE_MESSAGE.search(item[:1024]):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
class _LoginErrors(HTMLParser):
|
||||
"""Extract only explicitly marked login error elements; ignore scripts/notices."""
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.stack = []
|
||||
self.messages = []
|
||||
|
||||
def handle_starttag(self, tag, attrs):
|
||||
attrs = dict(attrs)
|
||||
marker = (attrs.get("id", "") + " " + attrs.get("class", "")).lower()
|
||||
explicit = bool(re.search(r"(?:^|[\s_-])(?:error|errors|errormsg|errormessage)(?:$|[\s_-])", marker))
|
||||
ignored = tag in ("script", "style", "template") or bool(self.stack and self.stack[-1][2])
|
||||
active = explicit or bool(self.stack and self.stack[-1][1])
|
||||
if tag not in ("input", "br", "img", "meta", "link", "hr", "wbr", "source"):
|
||||
self.stack.append((tag, active, ignored))
|
||||
|
||||
def handle_endtag(self, tag):
|
||||
for index in range(len(self.stack) - 1, -1, -1):
|
||||
if self.stack[index][0] == tag:
|
||||
del self.stack[index:]
|
||||
break
|
||||
|
||||
def handle_data(self, data):
|
||||
if self.stack and self.stack[-1][1] and not self.stack[-1][2]:
|
||||
self.messages.append(data)
|
||||
|
||||
|
||||
def is_rate_limited(status, payload=None, text=""):
|
||||
"""Check HTTP status and explicit error fields, never arbitrary payload data/HTML."""
|
||||
status = _status(status)
|
||||
if status == 429 or _explicit(payload):
|
||||
return True
|
||||
# Plain response bodies are evidence only on HTTP errors, and must be short.
|
||||
if status >= 400 and isinstance(text, str):
|
||||
plain = text.strip()
|
||||
if len(plain) <= 1024 and not re.search(r"<[^>]+>", plain):
|
||||
return bool(_RATE_MESSAGE.search(plain))
|
||||
return False
|
||||
|
||||
|
||||
def _valid_retry_after(value):
|
||||
if not isinstance(value, str) or not value.strip():
|
||||
return False
|
||||
value = value.strip()
|
||||
if re.fullmatch(r"[0-9]+", value):
|
||||
return True
|
||||
try:
|
||||
return parsedate_to_datetime(value).tzinfo is not None
|
||||
except (ValueError, TypeError, OverflowError):
|
||||
return False
|
||||
|
||||
|
||||
def check_response(response, what="upstream"):
|
||||
"""Return response unchanged, or raise RateLimitedError before caller parsing.
|
||||
|
||||
`what` is deliberately not interpolated: URLs and upstream bodies may contain
|
||||
credentials. Safe to use as a requests response hook through a small lambda.
|
||||
"""
|
||||
if response is None:
|
||||
return response
|
||||
status = _status(getattr(response, "status_code", 0))
|
||||
message = "上游请求过于频繁，请稍后重试"
|
||||
if status == 429:
|
||||
raise RateLimitedError(message)
|
||||
headers = getattr(response, "headers", {}) or {}
|
||||
retry_after = next((v for k, v in headers.items() if str(k).lower() == "retry-after"), None)
|
||||
if status >= 400 and _valid_retry_after(retry_after):
|
||||
raise RateLimitedError(message)
|
||||
try:
|
||||
payload = response.json()
|
||||
except (ValueError, TypeError, AttributeError):
|
||||
payload = None
|
||||
text = getattr(response, "text", "") or ""
|
||||
if is_rate_limited(status, payload, text):
|
||||
raise RateLimitedError(message)
|
||||
# Login pages can return HTTP 200 with an explicit error element. Never scan
|
||||
# the whole successful HTML document, inline scripts, or announcement text.
|
||||
if payload is None and isinstance(text, str) and "<" in text:
|
||||
parser = _LoginErrors()
|
||||
try:
|
||||
parser.feed(text[:262144])
|
||||
except (ValueError, TypeError):
|
||||
pass
|
||||
if _RATE_MESSAGE.search(" ".join(parser.messages)[:1024]):
|
||||
raise RateLimitedError(message)
|
||||
return response
|
||||
|
||||
|
||||
def safe_error(exception):
|
||||
"""Propagate explicit throttling, otherwise return a credential-free diagnostic.
|
||||
|
||||
Never stringify arbitrary exceptions: requests URLs, query strings, tokens,
|
||||
passwords and JSON decode snippets can all include secrets.
|
||||
"""
|
||||
if isinstance(exception, RateLimitedError):
|
||||
raise exception
|
||||
response = getattr(exception, "response", None)
|
||||
if response is not None:
|
||||
check_response(response, "request error")
|
||||
status = _status(getattr(response, "status_code", 0))
|
||||
if status:
|
||||
return "upstream HTTP %d" % status
|
||||
return "upstream request or response error (%s)" % type(exception).__name__
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# Part 1: Pure-python AES-128
|
||||
# ==============================================================================
|
||||
@@ -247,12 +438,20 @@ def new_session():
|
||||
|
||||
|
||||
def parse_course_url(url):
|
||||
m = re.search(
|
||||
r"/course/detail/(?P<courseId>\d+)/(?P<batchNo>[^/]+)/"
|
||||
r"(?P<weekTimeId>\d+)/signin/(?P<signInId>\d+)/(?P<type>\d+)", url)
|
||||
if not m:
|
||||
parts = urllib.parse.urlsplit(str(url or ""))
|
||||
m = re.fullmatch(
|
||||
r"/course/detail/(?P<courseId>[0-9A-Za-z]+)/(?P<batchNo>[^/]+)/"
|
||||
r"(?P<weekTimeId>\d+)/signin/(?P<signInId>\d+)/(?P<type>\d+)/?",
|
||||
parts.path)
|
||||
try:
|
||||
port = parts.port
|
||||
except ValueError:
|
||||
port = -1
|
||||
if (parts.scheme != "https" or parts.username is not None or parts.password is not None
|
||||
or port not in (None, 443)
|
||||
or (parts.hostname or "").lower() != "ginkgostu.dufe.edu.cn" or not m):
|
||||
raise ValueError(
|
||||
"URL is not a sign-in page (missing /signin/<signInId>/<type>): %s" % url)
|
||||
"URL is not a sign-in page (missing /signin/<signInId>/<type>)")
|
||||
return m.groupdict()
|
||||
|
||||
|
||||
@@ -321,18 +520,46 @@ def exchange_token(sess, cfg, code):
|
||||
headers={"Content-Type": "application/x-www-form-urlencoded"})
|
||||
try:
|
||||
j = r.json()
|
||||
except ValueError as e:
|
||||
raise UpstreamError("authLogin returned non-JSON: %s" % e)
|
||||
if j.get("code") != "2000":
|
||||
raise AuthError("OAuth code exchange refused: %s"
|
||||
% json.dumps(j, ensure_ascii=False))
|
||||
except ValueError:
|
||||
raise UpstreamError("authLogin returned non-JSON") from None
|
||||
if not isinstance(j, dict) or j.get("code") != "2000":
|
||||
raise AuthError("OAuth code exchange refused")
|
||||
return j["data"]["token"]
|
||||
|
||||
|
||||
def login(username, password):
|
||||
"""Complete SSO login flow. Returns (sess, token).
|
||||
|
||||
auto 模式一次登录后复用同一 session/token 逐个活动签到，
|
||||
对齐 bot ginkgo 复用轮询缓存登录态的思路（请求内级）。"""
|
||||
sess = new_session()
|
||||
cfg = get_unify_config(sess)
|
||||
csrf, page_url = open_authorize(sess, cfg)
|
||||
slider = exploit_slider(sess, page_url)
|
||||
resp = submit_login(sess, page_url, csrf, username, password, slider, page_url)
|
||||
|
||||
loc = resp.headers.get("Location", "")
|
||||
m = re.search(r"[?&]code=([A-Za-z0-9_\-]+)", loc)
|
||||
if not m:
|
||||
raise AuthError(
|
||||
"Login failed: no OAuth code in redirect (HTTP %s)" % resp.status_code)
|
||||
token = exchange_token(sess, cfg, m.group(1))
|
||||
return sess, token
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# Part 4: Sign-in API
|
||||
# ==============================================================================
|
||||
|
||||
def _request(sess, method, *args, **kwargs):
|
||||
"""Also guard fake sessions and HTTPError.response before any JSON parsing."""
|
||||
try:
|
||||
response = getattr(sess, method)(*args, **kwargs)
|
||||
except requests.RequestException as exc:
|
||||
raise UpstreamError(safe_error(exc)) from None
|
||||
return check_response(response, "signin")
|
||||
|
||||
|
||||
def api_headers(token, fingerprint=None):
|
||||
return {
|
||||
"User-Agent": UA,
|
||||
@@ -345,8 +572,8 @@ def api_headers(token, fingerprint=None):
|
||||
|
||||
|
||||
def call_api(sess, path, data, token):
|
||||
return sess.post(GINKGO + path, data=data, timeout=20,
|
||||
headers=api_headers(token))
|
||||
return _request(sess, "post", GINKGO + path, data=data, timeout=20,
|
||||
headers=api_headers(token))
|
||||
|
||||
|
||||
def commit_sign_in(sess, token, sign_in_id, batch_no, referer, code):
|
||||
@@ -368,14 +595,14 @@ def commit_sign_in(sess, token, sign_in_id, batch_no, referer, code):
|
||||
headers["Referer"] = referer
|
||||
|
||||
try:
|
||||
r = sess.post(
|
||||
r = _request(sess, "post",
|
||||
GINKGO + "/student/signIn/InTheSign",
|
||||
data={"signInId": str(sign_in_id), "code": str(code)},
|
||||
timeout=20,
|
||||
headers=headers,
|
||||
)
|
||||
except requests.RequestException as e:
|
||||
return False, "request to InTheSign failed: %s" % e, None
|
||||
except (requests.RequestException, UpstreamError) as e:
|
||||
return False, "request to InTheSign failed: %s" % safe_error(e), None
|
||||
|
||||
if r.status_code != 200:
|
||||
return False, "InTheSign returned HTTP %d" % r.status_code, None
|
||||
@@ -383,76 +610,349 @@ def commit_sign_in(sess, token, sign_in_id, batch_no, referer, code):
|
||||
try:
|
||||
j = r.json()
|
||||
except ValueError:
|
||||
return False, "InTheSign returned non-JSON: %s" % r.text[:200], None
|
||||
return False, "InTheSign returned non-JSON", None
|
||||
|
||||
if not isinstance(j, dict):
|
||||
return False, "Malformed InTheSign response", None
|
||||
api_code = str(j.get("code", ""))
|
||||
server_msg = (j.get("message") or j.get("msg") or "").strip()
|
||||
|
||||
if api_code == "2000":
|
||||
return True, server_msg or "accepted", j
|
||||
|
||||
if server_msg:
|
||||
reason = server_msg
|
||||
elif api_code:
|
||||
reason = "upstream returned code %s" % api_code
|
||||
else:
|
||||
reason = ("unrecognized upstream response: %s"
|
||||
% json.dumps(j, ensure_ascii=False)[:200])
|
||||
return False, reason, j
|
||||
return True, "accepted", j
|
||||
# Never return/log arbitrary upstream messages or bodies: they may contain secrets.
|
||||
return False, "InTheSign refused the sign-in request", j
|
||||
|
||||
|
||||
def fetch_sign_in_info(username, password, course_url, do_commit=True):
|
||||
def fetch_sign_in_info(username, password, course_url, do_commit=True,
|
||||
sess=None, token=None):
|
||||
route = parse_course_url(course_url)
|
||||
sign_in_id = route["signInId"]
|
||||
batch_no = route.get("batchNo")
|
||||
|
||||
sess = new_session()
|
||||
cfg = get_unify_config(sess)
|
||||
csrf, page_url = open_authorize(sess, cfg)
|
||||
slider = exploit_slider(sess, page_url)
|
||||
resp = submit_login(sess, page_url, csrf, username, password, slider, page_url)
|
||||
|
||||
loc = resp.headers.get("Location", "")
|
||||
m = re.search(r"[?&]code=([A-Za-z0-9_\-]+)", loc)
|
||||
if not m:
|
||||
raise AuthError(
|
||||
"Login failed: no OAuth code in redirect (HTTP %s)" % resp.status_code)
|
||||
auth_code = m.group(1)
|
||||
|
||||
token = exchange_token(sess, cfg, auth_code)
|
||||
if sess is None or not token:
|
||||
# 无外部登录态时自登录（保持向后兼容）：直接复用上方 SSO 流程
|
||||
sess, token = login(username, password)
|
||||
# 否则：sess/token 由调用方提供（auto 模式请求内复用同一登录态），跳过 SSO 登录
|
||||
|
||||
r = call_api(sess, "/student/signIn/getSignInInfo",
|
||||
{"signInId": sign_in_id}, token)
|
||||
check_response(r, "getSignInInfo")
|
||||
try:
|
||||
j = r.json()
|
||||
except ValueError as e:
|
||||
raise UpstreamError("getSignInInfo returned non-JSON: %s" % e)
|
||||
except ValueError:
|
||||
raise UpstreamError("getSignInInfo returned non-JSON") from None
|
||||
|
||||
if not isinstance(j, dict):
|
||||
raise UpstreamError("Malformed getSignInInfo response")
|
||||
data = j.get("data") or {}
|
||||
if not isinstance(data, dict):
|
||||
raise UpstreamError("Malformed getSignInInfo data")
|
||||
model = data.get("signInModel") or {}
|
||||
if not isinstance(model, dict):
|
||||
raise UpstreamError("Malformed getSignInInfo model")
|
||||
code = model.get("code")
|
||||
raw_type = model.get("type")
|
||||
if raw_type is None or raw_type == "":
|
||||
raw_type = route.get("type")
|
||||
try:
|
||||
signin_type = int(raw_type)
|
||||
except (TypeError, ValueError):
|
||||
raise UpstreamError("Malformed sign-in type") from None
|
||||
type_name = signin_type_label(signin_type)
|
||||
|
||||
if code is None or code == "":
|
||||
raise NoSignInCodeError(
|
||||
"Sign-in activity %s has no code configured" % sign_in_id)
|
||||
if signin_type == 1 and (code is None or code == ""):
|
||||
raise NoSignInCodeError("数字码签到未配置签到码")
|
||||
if signin_type == 2:
|
||||
code = ""
|
||||
|
||||
result = {
|
||||
"signInId": sign_in_id,
|
||||
"signInCode": code,
|
||||
"type": model.get("type"),
|
||||
"type": signin_type,
|
||||
"typeName": type_name,
|
||||
"title": model.get("title"),
|
||||
"status": data.get("signStatus"),
|
||||
}
|
||||
|
||||
if do_commit:
|
||||
ok, reason, _raw = commit_sign_in(
|
||||
sess, token, sign_in_id, batch_no, course_url, code
|
||||
)
|
||||
result["commit"] = {"success": ok, "message": reason}
|
||||
if signin_type not in (1, 2):
|
||||
result["commit"] = {
|
||||
"success": False,
|
||||
"message": "%s暂不支持自动签到，需特定流程" % type_name,
|
||||
}
|
||||
else:
|
||||
canonical_referer = GINKGO + urllib.parse.urlsplit(course_url).path
|
||||
ok, reason, _raw = commit_sign_in(
|
||||
sess, token, sign_in_id, batch_no, canonical_referer, code
|
||||
)
|
||||
result["commit"] = {"success": ok, "message": reason}
|
||||
|
||||
return result
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# Part 4b: Auto sign-in (mode=auto)
|
||||
# 通知列表发现签到活动并逐个自动签到 —— 逻辑对齐 bot ginkgo 模块：
|
||||
# fetch_all（通知+互动消息）→ _validated_signin_item（busi + 文本含"签到" +
|
||||
# 可解析课程链接）→ 按 signInId 去重 → 每活动连续重试（首次+最多5次，间隔3s，
|
||||
# token 失效重登录一次）→ 结果聚合为列表返回。
|
||||
# ==============================================================================
|
||||
|
||||
_TAG_RE = re.compile(r"<[^>]+>")
|
||||
|
||||
|
||||
def _html_to_text(raw):
|
||||
if not raw:
|
||||
return ""
|
||||
text = re.sub(r"(?i)<br\s*/?>", "\n", raw)
|
||||
text = re.sub(r"(?i)</(p|div|tr|li)>", "\n", text)
|
||||
text = _TAG_RE.sub("", text)
|
||||
text = _html.unescape(text)
|
||||
text = re.sub(r"[ \t\u3000]+", " ", text)
|
||||
text = re.sub(r"\n{2,}", "\n", text)
|
||||
return text.strip()
|
||||
|
||||
|
||||
def _parse_ts(value):
|
||||
text = (value or "").strip()
|
||||
if not text:
|
||||
return 0.0
|
||||
if text.endswith("Z"):
|
||||
text = text[:-1] + "+00:00"
|
||||
m = re.search(r"([+-]\d{2})(\d{2})$", text)
|
||||
if m:
|
||||
text = text[:m.start()] + m.group(1) + ":" + m.group(2)
|
||||
try:
|
||||
dt = datetime.fromisoformat(text)
|
||||
except ValueError:
|
||||
try:
|
||||
dt = datetime.strptime(text[:19], "%Y-%m-%d %H:%M:%S")
|
||||
except ValueError:
|
||||
return 0.0
|
||||
if dt.tzinfo is None:
|
||||
dt = dt.replace(tzinfo=TZ8)
|
||||
return dt.timestamp()
|
||||
|
||||
|
||||
def _normalize_notice(raw):
|
||||
title = (raw.get("title") or "").strip() or "(无标题)"
|
||||
ts = _parse_ts(raw.get("createTime"))
|
||||
return {
|
||||
"kind": "notice",
|
||||
"key": "N%s" % raw.get("id"),
|
||||
"id": str(raw.get("id") or ""),
|
||||
"title": title,
|
||||
"text": _html_to_text(raw.get("content") or ""),
|
||||
"ts": ts,
|
||||
"link": NOTICE_PAGE,
|
||||
"jump": "",
|
||||
}
|
||||
|
||||
|
||||
def _normalize_busi(raw):
|
||||
text = _html_to_text(raw.get("content") or "")
|
||||
jump = (raw.get("jumpUrl") or "").strip()
|
||||
if jump.startswith("http"):
|
||||
link = jump
|
||||
elif jump.startswith("/"):
|
||||
link = GINKGO + jump
|
||||
else:
|
||||
link = SYSTEM_PAGE
|
||||
ts = _parse_ts(raw.get("createTime"))
|
||||
return {
|
||||
"kind": "busi",
|
||||
"key": "B%s" % (raw.get("uuid") or ""),
|
||||
"uuid": str(raw.get("uuid") or ""),
|
||||
"id": "",
|
||||
"title": text[:120] or "(无内容)",
|
||||
"text": text,
|
||||
"ts": ts,
|
||||
"link": link,
|
||||
"jump": jump,
|
||||
}
|
||||
|
||||
|
||||
def _api_headers(token):
|
||||
return {
|
||||
"User-Agent": UA,
|
||||
"Origin": GINKGO,
|
||||
"Referer": GINKGO + "/",
|
||||
"Content-Type": "application/x-www-form-urlencoded",
|
||||
"token": token,
|
||||
"fingerprint": uuid.uuid4().hex,
|
||||
}
|
||||
|
||||
|
||||
def _call_json(sess, token, method, path, params=None, body=None, what="接口"):
|
||||
"""消息类 API 调用（对齐 bot _call）：check_response + code 必须为 2000。"""
|
||||
headers = _api_headers(token)
|
||||
if method == "GET":
|
||||
r = sess.get(GINKGO + path, params=params, headers=headers, timeout=20)
|
||||
else:
|
||||
headers["Content-Type"] = "application/json"
|
||||
r = sess.post(GINKGO + path, data=json.dumps(body if body is not None else {}),
|
||||
headers=headers, timeout=20)
|
||||
check_response(r, what)
|
||||
try:
|
||||
payload = r.json()
|
||||
except ValueError:
|
||||
raise UpstreamError("%s returned non-JSON (HTTP %s)" % (what, r.status_code))
|
||||
if not isinstance(payload, dict):
|
||||
raise UpstreamError("%s JSON must be an object" % what)
|
||||
if is_rate_limited(None, payload):
|
||||
raise RateLimitedError("%s 触发频率限制" % what)
|
||||
if str(payload.get("code")) != "2000":
|
||||
raise UpstreamError("%s returned code=%s" % (what, payload.get("code")))
|
||||
return payload
|
||||
|
||||
|
||||
def fetch_message_all(sess, token, page_size=PAGE_SIZE):
|
||||
"""取两类消息（均为全部，含已读），返回 (notices, busi) 归一化列表。"""
|
||||
j1 = _call_json(sess, token, "GET", "/student/message/getMessageAll",
|
||||
params={"pageSize": page_size, "pageNo": 1, "readFlag": 0},
|
||||
what="通知列表")
|
||||
notices = [_normalize_notice(x) for x in ((j1.get("data") or {}).get("list") or [])]
|
||||
j2 = _call_json(sess, token, "POST", "/student/busiMessage/list", body={},
|
||||
what="互动消息列表")
|
||||
busi = [_normalize_busi(x) for x in (j2.get("data") or [])]
|
||||
return notices, busi
|
||||
|
||||
|
||||
def _validated_signin_item(item):
|
||||
"""Return an annotated copy only for a real interactive sign-in activity.
|
||||
|
||||
与 bot ginkgo 的 _validated_signin_item 同逻辑：仅互动消息、文本含"签到"、
|
||||
跳转链接可解析为课程签到路由。query 参数可能携带 token，不入库不回显。"""
|
||||
if (not isinstance(item, dict) or item.get("kind") != "busi"
|
||||
or "签到" not in str(item.get("text") or "")):
|
||||
return None
|
||||
link = str(item.get("link") or "").strip()
|
||||
try:
|
||||
route = parse_course_url(link)
|
||||
except (ValueError, TypeError, AttributeError):
|
||||
return None
|
||||
row = dict(item)
|
||||
# Persist/display only the canonical path: query parameters may carry tokens
|
||||
# and must never reach receipts or push logs.
|
||||
row["link"] = GINKGO + urllib.parse.urlsplit(link).path
|
||||
# signInId is the stable activity identity（同一活动的多条消息去重）
|
||||
row["signin_activity_key"] = "S%s" % route["signInId"]
|
||||
try:
|
||||
row["signin_type"] = int(route["type"])
|
||||
except (TypeError, ValueError, KeyError):
|
||||
return None
|
||||
row["signin_type_name"] = signin_type_label(row["signin_type"])
|
||||
return row
|
||||
|
||||
|
||||
def _signin_one_with_retry(username, password, row, sess, token):
|
||||
"""对单个活动执行签到：失败连续重试（首次 + 最多 5 次，间隔 3s），
|
||||
token 疑似失效(上游错误/登录错)时重新登录一次后立即重试（对齐 bot refresh 语义）。
|
||||
|
||||
与 bot complete_signin 一致：除限流（外层中断）外，任何未确认成功都消耗重试次数；
|
||||
重试用尽记最终失败。返回 (entry, sess, token)。"""
|
||||
link = row["link"]
|
||||
base = {
|
||||
"activityKey": row.get("signin_activity_key"),
|
||||
"signInId": parse_course_url(link).get("signInId"),
|
||||
"routeType": row.get("signin_type"),
|
||||
"routeTypeName": row.get("signin_type_name"),
|
||||
"link": link,
|
||||
}
|
||||
attempts = 0
|
||||
refreshed = False
|
||||
last_err = "unknown error"
|
||||
last_data = None
|
||||
while attempts < MAX_SIGNIN_ATTEMPTS:
|
||||
attempts += 1
|
||||
try:
|
||||
data = fetch_sign_in_info(username, password, link, do_commit=True,
|
||||
sess=sess, token=token)
|
||||
last_data = data
|
||||
commit = data.get("commit")
|
||||
if isinstance(commit, dict) and commit.get("success") is True:
|
||||
entry = dict(base)
|
||||
entry.update({
|
||||
"type": data.get("type"),
|
||||
"typeName": data.get("typeName"),
|
||||
"title": data.get("title"),
|
||||
"signInCode": data.get("signInCode"),
|
||||
"status": data.get("status"),
|
||||
"success": True,
|
||||
"message": "签到成功",
|
||||
"attempts": attempts,
|
||||
})
|
||||
return entry, sess, token
|
||||
message = ((commit or {}).get("message")
|
||||
or "no commit result returned")
|
||||
last_err = str(message)
|
||||
except RateLimitedError:
|
||||
raise
|
||||
except (UpstreamError, AuthError) as e:
|
||||
# 疑似 token 失效：重登录一次后立即重试（不消耗退避间隔，对齐 bot）
|
||||
if not refreshed:
|
||||
refreshed = True
|
||||
try:
|
||||
sess, token = login(username, password)
|
||||
continue
|
||||
except Exception:
|
||||
pass # 重登录也失败：落入常规退避重试
|
||||
last_err = str(e) or type(e).__name__
|
||||
except NoSignInCodeError as e:
|
||||
last_err = str(e)
|
||||
except Exception as e:
|
||||
last_err = safe_error(e)
|
||||
if attempts < MAX_SIGNIN_ATTEMPTS:
|
||||
time.sleep(SIGNIN_BACKOFF[min(attempts - 1, len(SIGNIN_BACKOFF) - 1)])
|
||||
entry = dict(base)
|
||||
if isinstance(last_data, dict):
|
||||
entry.update({
|
||||
"type": last_data.get("type"),
|
||||
"typeName": last_data.get("typeName"),
|
||||
"title": last_data.get("title"),
|
||||
"signInCode": last_data.get("signInCode"),
|
||||
"status": last_data.get("status"),
|
||||
})
|
||||
entry.update({"success": False,
|
||||
"message": "签到失败（重试 %d 次）: %s" % (attempts, last_err),
|
||||
"attempts": attempts})
|
||||
return entry, sess, token
|
||||
|
||||
|
||||
def auto_sign_in_all(username, password):
|
||||
"""mode=auto 主流程。返回聚合结果 dict（results 为列表）。"""
|
||||
sess, token = login(username, password)
|
||||
notices, busi = fetch_message_all(sess, token)
|
||||
|
||||
activities = {}
|
||||
for item in notices + busi:
|
||||
row = _validated_signin_item(item)
|
||||
if row:
|
||||
activities.setdefault(row["signin_activity_key"], row)
|
||||
|
||||
results = []
|
||||
rate_limited = False
|
||||
for key in sorted(activities, key=lambda k: activities[k].get("ts") or 0):
|
||||
row = activities[key]
|
||||
try:
|
||||
entry, sess, token = _signin_one_with_retry(
|
||||
username, password, row, sess, token)
|
||||
except RateLimitedError:
|
||||
# 对齐 bot：限流即中断本轮，已完成的结果照常返回
|
||||
rate_limited = True
|
||||
break
|
||||
results.append(entry)
|
||||
|
||||
succeeded = sum(1 for r in results if r.get("success"))
|
||||
return {
|
||||
"mode": "auto",
|
||||
"activities": len(activities),
|
||||
"total": len(results),
|
||||
"succeeded": succeeded,
|
||||
"failed": len(results) - succeeded,
|
||||
"rate_limited": rate_limited,
|
||||
"results": results,
|
||||
}
|
||||
|
||||
|
||||
# ==============================================================================
|
||||
# Part 5: HTTP service (WSGI app)
|
||||
# ==============================================================================
|
||||
@@ -496,17 +996,24 @@ def ginkgostu_sign_in():
|
||||
url_b64 = args.get("url") or ""
|
||||
commit_arg = (args.get("commit") or "true").strip().lower()
|
||||
do_commit = commit_arg not in ("0", "false", "no")
|
||||
mode = (args.get("mode") or "").strip().lower()
|
||||
|
||||
if not (username and password_b64 and url_b64):
|
||||
if not (username and password_b64):
|
||||
return _error(400, 400,
|
||||
"Missing parameters: username, password(base64)")
|
||||
if mode != "auto" and not url_b64:
|
||||
return _error(400, 400,
|
||||
"Missing parameters: username, password(base64), url(base64)")
|
||||
|
||||
try:
|
||||
password = _b64_decode(password_b64, "password")
|
||||
course_url = _b64_decode(url_b64, "url")
|
||||
course_url = _b64_decode(url_b64, "url") if url_b64 else ""
|
||||
except ValueError as e:
|
||||
return _error(400, 400, str(e))
|
||||
|
||||
if mode == "auto":
|
||||
return _auto_response(username, password)
|
||||
|
||||
log.info("query start user=%s commit=%s", username[:2] + "***", do_commit)
|
||||
try:
|
||||
data = fetch_sign_in_info(username, password, course_url, do_commit=do_commit)
|
||||
@@ -524,28 +1031,61 @@ def ginkgostu_sign_in():
|
||||
"data": data,
|
||||
})
|
||||
|
||||
log.info("query ok user=%s code=%s", username[:2] + "***", data.get("signInCode"))
|
||||
log.info("query ok user=%s type=%s", username[:2] + "***", data.get("type"))
|
||||
return jsonify({"code": 200, "msg": "ok", "data": data})
|
||||
except AuthError as e:
|
||||
log.warning("auth failed: %s", e)
|
||||
return _error(401, 401, str(e))
|
||||
except NoSignInCodeError as e:
|
||||
log.info("no code: %s", e)
|
||||
return _error(404, 404, str(e))
|
||||
except UpstreamError as e:
|
||||
log.error("upstream error: %s", e)
|
||||
return _error(502, 502, str(e))
|
||||
except ValueError as e:
|
||||
log.warning("bad request: %s", e)
|
||||
return _error(400, 400, str(e))
|
||||
except requests.RequestException as e:
|
||||
log.error("upstream request failed: %s", e)
|
||||
except AuthError:
|
||||
log.warning("authentication failed user=%s", username[:2] + "***")
|
||||
return _error(401, 401, "Authentication failed")
|
||||
except NoSignInCodeError:
|
||||
log.info("numeric code missing user=%s", username[:2] + "***")
|
||||
return _error(404, 404, "数字码签到未配置签到码")
|
||||
except UpstreamError:
|
||||
log.error("upstream response error user=%s", username[:2] + "***")
|
||||
return _error(502, 502, "Upstream response error")
|
||||
except ValueError:
|
||||
log.warning("bad request user=%s", username[:2] + "***")
|
||||
return _error(400, 400, "Invalid request")
|
||||
except requests.RequestException:
|
||||
log.error("upstream request failed user=%s", username[:2] + "***")
|
||||
return _error(502, 502, "Upstream request failed")
|
||||
except Exception:
|
||||
log.exception("internal error")
|
||||
except Exception as exc:
|
||||
log.error("internal error type=%s", type(exc).__name__)
|
||||
return _error(500, 500, "Internal error")
|
||||
|
||||
|
||||
def _auto_response(username, password):
|
||||
"""mode=auto：发现 + 自动签到 + 聚合列表返回。"""
|
||||
log.info("auto sign-in start user=%s", username[:2] + "***")
|
||||
try:
|
||||
data = auto_sign_in_all(username, password)
|
||||
except AuthError:
|
||||
log.warning("auto sign-in authentication failed user=%s", username[:2] + "***")
|
||||
return _error(401, 401, "Authentication failed")
|
||||
except RateLimitedError:
|
||||
log.warning("auto sign-in rate limited user=%s", username[:2] + "***")
|
||||
return _error(429, 429, "Upstream rate limited, please retry later")
|
||||
except UpstreamError:
|
||||
log.error("auto sign-in upstream error user=%s", username[:2] + "***")
|
||||
return _error(502, 502, "Upstream response error")
|
||||
except requests.RequestException:
|
||||
log.error("auto sign-in upstream request failed user=%s", username[:2] + "***")
|
||||
return _error(502, 502, "Upstream request failed")
|
||||
except Exception as exc:
|
||||
log.error("auto sign-in internal error type=%s", type(exc).__name__)
|
||||
return _error(500, 500, "Internal error")
|
||||
log.info("auto sign-in done user=%s total=%s succeeded=%s rate_limited=%s",
|
||||
username[:2] + "***", data["total"], data["succeeded"],
|
||||
data["rate_limited"])
|
||||
if data["rate_limited"]:
|
||||
msg = ("partial: upstream rate limited, %d/%d activities processed"
|
||||
% (data["total"], data["activities"]))
|
||||
elif data["failed"]:
|
||||
msg = "ok with failures: %d/%d succeeded" % (data["succeeded"], data["total"])
|
||||
else:
|
||||
msg = "ok"
|
||||
return jsonify({"code": 200, "msg": msg, "data": data})
|
||||
|
||||
|
||||
@app.route("/healthz", methods=["GET"])
|
||||
def healthz():
|
||||
return jsonify({"code": 200, "msg": "ok", "data": None})
|
||||
|
||||
Reference in New Issue
Block a user